DomainKits

Comprehensive domain analyze workflow. Call when a user wants to understand a specific domain's full picture — registration status, safety, DNS configuration, cross-TLD distribution, and current website usage. When to use: user asks 'what can you tell me about example.com?', wants to evaluate a domain before purchasing, or needs a technical analyze. Do NOT use for domain name ideas (use name_advisor), availability checks (use available), or expired domain evaluation (use expired_analysis). Workflow: 1. Gather data using these atomic tools in parallel: - whois for registration details, registrar signals, and expiry dates. - backlink_summary for SEO profile — domain rank, backlink count, referring domains, spam scores, and link quality distribution. - safety for Google Safe Browsing status. - dns for MX, A, and CNAME records — signals of active usage or abandonment. - tld_check to see how many TLDs share this prefix. 2. If tld_check shows high registration count, investigate further: - whois the .com/.net/.org variants to check if the same registrar holds multiple TLDs (brand protection signal) or different registrars (popular keyword signal). - web_search the TLD variants to see if they resolve to the same site. 3. Visit the domain via web_fetch or web_search to determine current usage: active business, parked page, for-sale landing, or no content. 4. Use web_search to investigate the domain's market background: recent sale history (NameBio, Sedo, Afternic), related news or brand events, legal disputes (UDRP, trademark conflicts), and any notable context that affects valuation or risk. This step is critical — technical data alone is insufficient for a complete analyze. 5. Synthesize all findings into a concise analyze report including backlink profile metrics (rank, referring domains, spam risk, link type distribution). Present facts with key signals clearly flagged. Do NOT make buy/don't-buy judgments — present evidence and let the user decide. 6. After presenting the report, ask the user about their goals before suggesting next steps. Tailor follow-up based on their answer: - Wants to purchase → suggest valuation_cma for pricing, brand_match for trademark risk. - Domain is listed for sale → provide the sale link, suggest brand_match. Disclose affiliate links. - Wants alternatives → suggest plan_b. - Wants monitoring → suggest set_monitor. Key principles: present facts, not recommendations. Flag signals clearly (e.g., enterprise registrar = corporate-held, MX present = active email, no A record = possibly abandoned). Every claim must come from tool data. Disclose affiliate links when presenting registration or sale URLs.

Check domain availability with pricing. Final validation before registration. Best practices: - Input must be a fully qualified domain name including TLD (e.g., 'example.com', not just 'example'). - If status='available': present reg_url and price clearly. If price is significantly higher than standard registration (~$10-15 for .com), flag it as a premium/reserved domain — the registry is charging a premium price. - If status='registered': state clearly the domain is taken. Do not automatically suggest alternatives — let the user decide if they want to explore other options. - If status='expiring': domain is in the expiration pipeline — can be backordered via reg_url, not directly registered. - If status='reserved': registry-reserved domain — not available for registration. - If status='unknown': check was inconclusive — do not assume available or unavailable. - For batch checking multiple domains, use bulk_available instead — it checks up to 10 at once. - This tool is the definitive availability check. Other tools (tld_check, deleted, expired) may show signals of availability, but only this tool or bulk_available confirms registrability and returns actual pricing. - Disclose affiliate links when aff=true.

SEO backlink analysis powered by DataForSEO. Use when: (1) user explicitly requests SEO analysis or domain valuation, (2) evaluating expiring/deleted domains before acquisition. Do NOT call for general browsing or availability checks. Key fields and interpretation: - rank: Domain authority on a 0-1000 logarithmic scale (based on PageRank). Each point higher is exponentially harder. Reference points: apple.com/iphone ~848, stackoverflow.com ~740, forbes.com ~650, ahrefs.com/blog ~395. - backlinks_spam_score: Spam score of all incoming backlinks (0-100). 0-30 low, 31-60 medium (warrants investigation), 61-100 high (significant risk). - target_spam_score: Spam score of the domain itself (0-100). Same thresholds. - Always calculate key ratios from the raw data: backlinks per referring domain (total_backlinks / referring_main_domains — high ratio like 500+ means a few domains contribute most links), referring IPs vs referring domains (low ratio suggests shared infrastructure, potential PBN signal), broken backlinks as percentage of total (high percentage means decaying link profile), follow vs nofollow distribution from referring_links_attributes (near 100% follow is unusual for a natural profile). - referring_links_platform_types: If message-boards or web2.0 platforms dominate, this can indicate low-quality link building. - referring_links_tld: Note presence or absence of .edu/.gov links. - new vs lost backlinks and referring domains indicate whether the profile is growing or shrinking. Caveat — passive referrals on aged domains: Some low-quality or scraper sites automatically link to old domains (abandoned blogrolls, scraped content, auto-generated pages). A small amount of this noise is normal for aged domains — Google's algorithms can identify and ignore these junk links, so a few low-quality referrals should not be treated as a risk signal. However, a large volume of junk referrals is a different story — it may indicate the domain was used for black-hat SEO, link schemes, or was targeted by malicious backlink attacks. As with everything, degree matters: a handful of scraper sites is background noise; thousands of them is a red flag. Present facts and data. Do NOT make buy/don't-buy judgments — let the user interpret the signals.

Brand conflict and trademark risk detection workflow. Call when a user wants to check whether a domain name carries brand-related risks before registering or purchasing it. When to use: user asks 'is this domain safe to register?', wants to assess UDRP risk before purchase, or needs trademark conflict checking as a follow-up from name_advisor or analyze. Do NOT use for general technical analysis (use analyze), domain name brainstorming (use name_advisor), or DNS/registration checks only (use dns, whois). Workflow: 1. Extract the prefix from the domain (e.g., nicefloor.com → nicefloor). If the prefix contains a well-known brand name (google, apple, amazon, microsoft, etc.), immediately warn the user about high UDRP risk before proceeding. Ask the user about their intent: are they assessing risk before registration, or holding the domain and looking for potential buyers? This determines the framing of the analysis. Do NOT call any tools before the user responds. 2. After the user responds, gather data in parallel: - web_search '[prefix] company' to discover existing commercial use — note founding year, business scale, industry, and whether the company actively uses this keyword as a brand. - tld_check to see how many TLDs have this prefix registered. - If tld_check shows high registration, whois the .com/.net/.org variants to check if the same registrar holds multiple TLDs (brand protection signal) or different registrars (popular keyword signal). Use web_search to verify if they resolve to the same website. 3. Run trademark database checks across all four major databases. Primary method is Claude for Chrome — open each database, search for [prefix], and read results directly. If Claude for Chrome is not available, fall back to providing pre-filled links as described below. Present findings from each database inline as they come in — do not wait for all four before reporting. USPTO: - Chrome: navigate to https://search.uspto.gov/search?query=[prefix]&affiliate=web-sdmg-uspto.gov and read results directly. - Fallback (no Chrome): USPTO supports URL query parameters — provide this pre-filled link for the user to open: https://search.uspto.gov/search?query=[prefix]&affiliate=web-sdmg-uspto.gov - Extract: number of trademark hits, registrant names, goods/services classes, live vs dead status. EUIPO: - Chrome: navigate to https://euipo.europa.eu/eSearch/, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): EUIPO uses a JavaScript interface — URL parameters cannot pre-fill search. Provide the entry link and instruct the user: 'Please open https://euipo.europa.eu/eSearch/ and search for [prefix].' - Extract: EU trademark hits, registrant names, classes, status. WIPO: - Chrome: navigate to https://branddb.wipo.int/en/quicksearch, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): provide entry link and instruct: 'Please open https://branddb.wipo.int/en/quicksearch and search for [prefix].' - Extract: international trademark hits, registrant names, designating countries, status. TMview: - Chrome: navigate to https://www.tmdn.org/tmview/#/quicksearch, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): provide entry link and instruct: 'Please open https://www.tmdn.org/tmview/#/quicksearch and search for [prefix].' - Extract: aggregate hits across all participating offices, notable registrants. If a database is unreachable or returns an error, note it in the report and continue — do not halt the workflow. 4. Synthesize all findings into a report, framed according to the user's stated intent (risk-focused or opportunity-focused). The report must include: - Discovered entities: websites/companies using this keyword, their business, scale, founding year. - TLD distribution: cross-TLD registration pattern and registrar correlation. - Trademark database summary: hits per database, live marks found, relevant classes. If no hits found in a database, state that clearly — absence of results does not guarantee the mark is clear. - Risk assessment based on the three UDRP principles (confusing similarity, rights or legitimate interests, bad faith). For generic word combinations, note that risk is typically lower. Factor in registration age. Do NOT make legal conclusions. - Disclaimer: 'For reference only, does not constitute legal advice. Trademark searches are not exhaustive — consult a qualified IP attorney before making registration or investment decisions.' 5. After presenting the report, ask the user what they want to do next. Tailor follow-up based on their response: - Wants to proceed with registration → suggest available or bulk_available. - Wants deeper analysis → suggest analyze. - Wants alternatives → suggest plan_b or name_advisor. - Wants to find buyers → use web_search findings to identify potential buyers, suggest valuation_cma. - Wants monitoring → suggest set_monitor. Key principles: present facts, not legal judgments. Do NOT claim a trademark exists or does not exist based on partial results. Claude for Chrome reads all four databases directly — the user should never need to search manually when Chrome is available. When Chrome is unavailable, always provide actionable fallback links with clear search instructions. Always end with the legal disclaimer. Disclose affiliate links.

Batch check domain availability with pricing. Check up to 10 domains per call. This is the verification gate — any domain recommended to a user must pass through this tool first. Do not present domains as available based on other tools' signals (e.g., tld_check showing 'might_available', or domains found in deleted/expired feeds) without confirming here. Input format: comma-separated full domain names including TLD (e.g., 'aitools.com,getai.io,smartai.app'). Maximum 10 per call — for larger batches, make multiple calls. Interpreting results: - status 'available': Confirmed registrable. price and reg_url will be present. - status 'registered': Currently owned — not available for standard registration. - status 'expiring': In the expiration pipeline — can be backordered, not directly registered. reg_url will point to a backorder service. - status 'reserved': Registry-reserved domain — not available for registration. - status 'unknown': Check was inconclusive — do not assume available or unavailable. Best practices: - Always disclose affiliate links when aff=true. - When multiple domains return available, prioritize shorter names and .com over alternatives when presenting results. - If all checked domains come back registered, this is useful signal in itself — the namespace is saturated for that keyword pattern.

Check how many TLDs have specific keywords registered. Batch-compare keyword popularity by cross-TLD registration distribution. Best practices: - Use comma-separated keywords for side-by-side comparison (max 10): keywords='ai,tech,cloud,smart'. This is the tool's core strength — comparing relative popularity across multiple keywords in one call. - Interpreting total count: 100+ TLDs registered = highly competitive, well-known keyword. 50-100 = moderate popularity. 20-50 = niche but recognized. <20 = low market interest or very new concept. - The popular vs cctld vs other breakdown reveals the keyword's reach: high popular count (com/net/org/io/ai) = commercially validated. High cctld count = global brand interest or defensive registration. High other count = speculative gTLD registrations. - Use this to compare synonyms or variations before deciding which keyword to invest in — e.g., compare 'automate' vs 'automation' vs 'autoflow' to see which has stronger market validation. - Pairs well with tld_check for drilling into a single keyword's full TLD-by-TLD breakdown after identifying winners here.

Search domains that have completed the deletion cycle and are open for immediate registration at standard cost — no auction or backorder needed. These are the highest-value finds: domains with history available at regular price. Best practices: - Always use no_hyphen=true and no_number=true unless the user specifically wants them — the vast majority of hyphenated and numeric deleted domains are low-quality. - keyword defaults to 'contain' matching (substring), producing false positives (e.g., 'agent' matches 'magenta'). Use position=start or position=end for precise results. - sort=age_desc surfaces domains with the longest history first — a 20+ year old deleted .com at standard registration cost is a rare find worth highlighting. - sort=tld_counter_desc finds keywords popular across TLDs — if prefix_tld_count is high (20+) and the .com just dropped, that is notable. - For brandable names: combine length=5-10, type=all_alpha, no_hyphen=true, no_number=true. - hold=no_hold filters out domains still under registry hold that cannot yet be registered. - register_url links to Dynadot (affiliate). Disclose when presenting to users.

Query DNS records for a domain. Returns A, AAAA, MX, NS, TXT, CNAME, SOA. Key signals: MX present = active email. NS pointing to marketplace (Sedo, Afternic) = parked/for-sale. TXT with SPF/DKIM = active operations. No records at all = unconfigured/abandoned.

Monitor changes to premium .com domains in the past 7 days. The monitored pool consists of short-character .com domains (typically 1-4 letters) and high-value English single-word and two-word .com domains. This is not a general domain monitor — it specifically tracks the most valuable segment of the .com namespace. Change types: - Domain Transfer: Registrar changed — indicates ownership or management change. Report the old and new registrar as facts. Do not assume the reason (could be a sale, corporate restructuring, registrar migration, or portfolio consolidation). - Domain Expired: Domain entered expiration cycle. Report the fact. Do not characterize rarity or value unless verified with additional data. - New Registration: A previously unregistered premium name was registered. - Nameserver Change: NS records updated. An NS change to a domain marketplace (e.g., sedo.com, afternic.com, thisdomain.forsale) is a possible sale signal but not a certainty — report the old and new NS as facts. Best practices: - date_range=1d for last 24 hours, 3d for last 72 hours, all for full 7-day window (default). - length=1-3 or length=4 focuses on the shortest, most premium domains. - reason filters to a specific change type — use 'Domain Transfer' or 'Domain Expired' for the most newsworthy events. - sort=length_asc surfaces the shortest (most valuable) domains first. - has_digit=false filters to letter-only domains for higher quality results. - All interpretations must be evidence-based. Report what changed, not why. If the user wants to understand the reason behind a change, suggest whois or web_search to investigate further.

Creative domain name generation workflow. Call when a user already knows their target keyword or has a specific taken domain and wants registrable creative variations (e.g., 'I want a domain with the word flow', 'getflow.com is taken, give me variations'). Do NOT call when the user's requirements are vague or they don't have a keyword yet (use name_advisor), when they want alternatives across lifecycle stages like expired/deleted (use plan_b), or when they want trend-based ideas (use trend_hunter). Key difference from name_advisor: this tool assumes the user already knows what keyword they want. If the user is unsure or exploring, use name_advisor instead. This is a multi-turn workflow. Stop and wait for user input at every checkpoint. Workflow: 1. Keyword Analysis & Confirmation — extract the core keyword from user input (e.g., getflow.com → flow). Briefly state your understanding of the keyword and industry context, then confirm with the user: is the keyword correct? TLD preference (.com only or open to others)? Style preference (short and punchy vs descriptive)? Do NOT generate any domain names or call any tools until the user confirms. If the user seems unsure about their keyword, suggest switching to name_advisor. 2. Generate & Verify — generate 20-30 creative variants based on confirmed preferences. Strategies include: TLD swaps for short keywords (.io, .ai, .app, .co), industry-relevant prefixes/suffixes (get-, -ly, -hub, -lab), coined words and portmanteaus, word + modifier combinations. Before finalizing, scan every candidate for unintended sensitive words, medical terms, or offensive abbreviations created by concatenation. Verify all candidates with bulk_available — every domain presented to the user must be confirmed available, no exceptions. Present only verified domains grouped by strategy, each with register_url. 3. Iterate or Finalize — based on user feedback: generate more variations in a preferred direction, suggest brand_match for a finalist, adjust strategy if needed, or suggest plan_b if the user wants expired/aged alternatives. Key principles: - Every domain presented must be verified available via bulk_available. No exceptions. - Available domains include register_url (Dynadot affiliate). - Disclose affiliate links.

Search domains entering the deletion cycle, expired, in redemption, or pending delete. Unlike 'deleted' domains (which are free to register), these require backorder or have time-sensitive acquisition windows. Two modes: - Keyword search: provide 'keyword' to search across all TLDs by keyword matching. Optionally add 'tld' to narrow results. - TLD browse: provide 'tld' WITHOUT 'keyword' to browse all expiring domains under a specific TLD. Use filters (status, age_range, length, type, etc.) to narrow results progressively. This mode is for exploratory discovery when the user wants to see what is expiring in a TLD, not for keyword-based search. Note: TLD browse mode only supports gTLDs (com, net, org, xyz, etc.), not ccTLDs (ai, co, de, etc.). When the user provides a keyword, always use keyword search mode. Only use TLD browse mode when the user explicitly wants to explore a TLD without a specific keyword in mind. Lifecycle stages: - expired: Domain has lapsed but has not entered redemption. Typically enters expired auction at the registrar, acquisition requires bidding, not standard registration. - redemption: Owner can still reclaim by paying a redemption fee (~$80+). For premium names in this stage, consider using set_monitor to track status changes, or whois to find the registrar and suggest the user contact the owner directly with an offer. - pending_delete: Final stage, drops in 1-5 days. Highest urgency. Good names at this stage rarely survive manual registration, backorder via the register_url (Gname) is recommended. Best practices: - Always use no_hyphen=true and no_number=true unless the user specifically wants them. - In keyword mode, keyword defaults to 'contain' matching. Use position=start, position=end, or position=middle to control where the keyword appears. - In TLD browse mode, combine filters (status, age_range, length, type) to get precise, small result sets. Do not request unfiltered TLD results. - sort=age_desc prioritizes domains with the longest history, but age alone does not guarantee value. For high-value candidates, verify clean history with safety checks. - status=pending_delete is the most actionable filter, these domains drop soonest. - auction_date='today' or 'tomorrow' narrows to imminent drops. - register_url links to Gname (affiliate). Disclose when presenting to users.

Deep due diligence workflow for expired or expiring domains. Call when a user wants to evaluate an expired domain's history, SEO value, safety, and commercial potential before backordering or acquiring it — including as a follow-up when browsing results from expired or deleted tools. Do NOT call if the domain is not in any expired status (use analyze instead), if the user wants domain name ideas (use name_advisor), or if the user wants to check availability of a new domain (use available). This is a multi-turn workflow. Stop and wait for user input at every checkpoint. Workflow: 1. Status Verification — run whois first. Confirm the domain is actually in an expired status (expired, redemption, pending-delete). If it is NOT expired, stop immediately, inform the user, and hand off to the analyze workflow. This gate check is mandatory. 2. Data Collection — gather all available data in parallel: backlink_summary (SEO backlink profile, domain rank, spam score, referring domains distribution -- essential for evaluating expired domain value), safety (Google Safe Browsing -- critical risk signal for expired domains), dns (residual records indicate previous usage), keyword_data (search volume and CPC for commercial value), tld_check (cross-TLD registration count as popularity signal), web_fetch the Wayback Machine timeline (https://web.archive.org/web/*/{domain}) for historical usage, and web_search site:{domain} to check residual Google indexing. 3. Due Diligence Report — synthesize all findings into a structured report covering: domain status and key dates, backlink profile (rank, total backlinks, referring domains, spam scores, link quality distribution), safety warnings, keyword commercial value, historical usage from Wayback, Google index status, cross-TLD distribution, and consolidated risk/opportunity signals. Then ask the user about their goal (SEO recovery, brand building, or investment/resale) and whether they want to explore specific aspects further. Let the user choose the direction — do not decide for them. 4. Tailored Follow-up — based on user's stated goals, guide them to the appropriate next step: backorder process and timeline, set_monitor for status tracking, plan_b for alternatives, valuation_cma for market context, or brand_match before committing. Key principles: - Present facts and acquisition opportunities. Do NOT make buy/don't-buy judgments. - Objectively flag ALL risk signals — do not downplay or hide them. - Backorderable domains must include backorder_url (Gname affiliate). - Always include Wayback link: https://web.archive.org/web/*/{domain} - Always include deep analysis link: https://dataforseo.com/?aff=199596 - Disclose affiliate links.

Retrieve opportunity discovery strategies. Check at conversation start when memory is enabled and strategies_count > 0. REQUIREMENTS: - Requires registered account (member or above). - Requires memory to be enabled. For each strategy where can_run=true: 1. Read the strategy field — this is the user's investment thesis. 2. Execute using ALL available capabilities — domain tools, web_search, web_fetch, your own knowledge and judgment. 3. Compare with last_result to surface only NEW opportunities since last run. 4. Call update_strategy to save current results. 5. Present findings with register_url and actionable next steps. 6. If any discovered domain shows high potential (strong keyword, aged), proactively suggest: "Want me to add this to your monitoring list so we can track changes?" If no strategies exist, show available preset strategies the user can activate.

Google Ads keyword data: search volume, competition, and CPC. Use when evaluating a keyword's commercial search demand — one call per keyword is sufficient. Interpreting results: - search_volume: Average monthly Google searches. >10k with CPC >$2 indicates strong commercial intent. 1k-10k with CPC $0.5-$2 is niche but viable. <1k with CPC <$0.5 suggests limited commercial demand. - competition: 0 to 1 score representing advertiser density. Higher means more advertisers bidding on this keyword. - competition_level: LOW, MEDIUM, or HIGH. Low competition + decent volume = underserved opportunity. - low_cpc / high_cpc: Cost-per-click range in USD. Reflects what advertisers are willing to pay. Higher CPC generally correlates with higher commercial value for domains matching this keyword. In domain investment context, the combination of search_volume and CPC is the primary value signal — volume alone without advertiser spend may indicate informational intent rather than commercial intent.

Deep keyword intelligence for domain investment. Call when a user wants to understand the full picture of a specific keyword in the domain market — demand, supply, competition, and opportunities. This is a data-intensive workflow: every claim must be backed by tool output. When to use: User asks about a keyword's investment potential, market landscape, or opportunity analysis. Not for analyzing a specific domain (use analyze), browsing trends (use trend_hunter), or market overviews (use market_beat). Methodology — three phases, each building on the previous: 1. Demand: Establish how much the market wants this keyword. - keyword_data for commercial search value (volume, CPC, competition). - keywords_trends (both hot and emerging) for registration momentum. - web_search is MANDATORY — do NOT substitute with your own knowledge. Execute at least two searches: '{keyword} news 2026' for industry context, and '{keyword} domain sold price' for transaction history. Only include claims that come from search results. If search returns nothing relevant, state 'no recent news or transactions found' — do not fill the gap with training data. Do NOT attribute keyword popularity to a specific event or project unless keywords_trends data shows a clear spike AND web_search confirms the connection. Common English words have natural baseline demand — not every trend needs a catalyst explanation. 2. Supply: Map the current domain inventory, focused on .com as the primary lens unless the user requests otherwise. - tld_check for cross-TLD saturation. - active for total .com inventory and for-sale ratio (forsale count / total count). Also compare keyword-as-prefix vs keyword-as-suffix to gauge market maturity. - deleted for domains available at standard registration cost. - expired for domains in the expiration pipeline that can be backordered. - aged with has_sale=true for secondary market listings. 3. Competition: Assess whether the window is opening or closing. - nrds comparing recent .com registration velocity across time periods (0-10 days vs 10-20 days). Accelerating velocity means act fast; decelerating means the peak may have passed. - From the same nrds results, assess registration quality — high ratios of hyphens, numbers, or excessive length indicate a junk/speculative market rather than serious investment. - Analyze the naming patterns in recent registrations to identify what is driving demand. For example, if most new domains combine the keyword with 'ai', 'cloud', 'tech', that points to a tech trend; if they combine with 'game', 'machine', 'play', that points to entertainment. If patterns are diverse with no clear theme, the keyword likely has natural baseline demand across multiple sectors. This pattern analysis is based on the nrds results already retrieved — no additional tool calls needed. Synthesize into an intelligence report: keyword verdict (invest / watch / avoid) with confidence level, demand profile, supply profile, competition profile, and recommended next steps tailored to the verdict. Let the data tell the story — if data is contradictory, present both sides. After the report, offer relevant next steps: deep analysis on a specific domain, brand conflict check, monitoring setup, strategy tracking, or analyzing a different keyword.

Get trending keywords in domain registrations. Its mainly used for investors to find new chances, but could also be used as brand protection. Three modes: - hot: High-volume keywords (e.g., 'app', 'shop', 'group'). These are established 'blue chip' terms — high volume but high competition. Results include weekly breakdown (w1-w4) to spot momentum shifts. Quality metrics use 28-day data. - emerging: Keywords with sudden registration spikes in the last 7-14 days, often driven by news events, product launches, or viral moments. Compare w4 (current week) vs w3 to assess momentum. Quality metrics use W4-only data to reflect the spike period accurately. Use web_search to investigate what is driving the spike — a spike without an identifiable cause is suspicious. - prefix: Popular naming patterns (e.g., 'get...', 'my...', 'the...'). Results include tld_count — if a prefix has high tld_count but .com is still available, that is actionable. Use bulk_tld to check which specific TLDs are taken vs available. Quality metrics (hot and emerging only, fields vary by user tier): - com_ratio: .com registrations as a proportion of total. Above 15% suggests real interest; below 5% suggests bulk speculation on cheap TLDs. - most_tld: The dominant TLD for this keyword. If a non-.com TLD dominates, the trend is likely driven by bulk registration on that TLD rather than broad organic interest. - pos_start_ratio / pos_end_ratio: Where the keyword appears in domain names. High start ratio (e.g., 'aitools.com') suggests the keyword drives the domain concept. High end ratio (e.g., 'myai.com') suggests it is used as a modifier. - forsale_pct: Percentage of domains with NS pointing to sale platforms (Sedo, Afternic, Atom). Global baseline ~1.8%. Well above baseline (>5%) indicates strong investor interest. This is a lower bound — actual investor activity is likely higher. - top_ns + top_ns_ratio: The most common nameserver and its share. High ratio (>60%) with a single private NS suggests coordinated bulk operation (e.g., PBN/site farm) rather than organic trend. Cross-reference with NS identity: sale platform NS = distributed investor consensus; registrar default NS = recently registered, not yet configured; private/unknown NS at high concentration = likely single-entity bulk action. - top_registrar: The registrar with the highest volume. Investor-favored registrars (Dynadot, NameSilo, Spaceship, Porkbun) vs end-user registrars (GoDaddy, Wix, Squarespace) reveal who is driving the trend. - peak_day: The single day with highest registrations. If peak_day accounts for a large share of total, the trend is likely event-driven or a single bulk registration event rather than sustained organic interest. - building_count: Domains with NS pointing to building infrastructure (Cloudflare, AWS, Vercel, Netlify). Higher values suggest real adoption intent. Scope: By default (scope=all), counts registrations across all gTLDs. With scope=com, narrows to .com registrations only, filtered to pure-letter domains (no digits or hyphens). Rankings and counts differ between scopes since .com is a subset. A keyword that ranks high across all TLDs may not appear in the .com list, and vice versa. TLD distribution metrics (com_ratio, most_tld) are not included in .com scope. Scope is available for hot and emerging only; prefix always uses all TLDs. Data methodology: Registration counts are based on semantic keyword extraction using DomainKits' proprietary word segmentation engine (https://github.com/ABTdomain/dksplit), not simple substring matching. Bulk registration noise is automatically filtered from emerging results. WHOIS data is sourced from daily RDAP snapshots. Brand protection registrars (CSC, MarkMonitor, etc.) are excluded.

Search currently registered domains with marketplace listing data. These are live domains owned by someone — not available for free registration. Use status=forsale to filter to domains the owner has listed for sale, or use results as acquisition targets to approach owners directly. Best practices: - keyword defaults to 'start' matching. Use position=end or position=contain for broader results. - status=forsale is the most actionable filter — these owners are actively seeking buyers. - Results include a marketplace field indicating which platform the domain is listed on (e.g., 'se' for Sedo, 'go' for GoDaddy, 'at' for Atom, 'vn' for Venture, 'pd' for PerfectDomain). Domains without a marketplace value are registered but not actively listed for sale. - sort=length_asc surfaces the shortest (most premium) names first. - The components field shows how the domain name segments into recognizable words — useful for evaluating brandability. - Disclose affiliate links when presenting register_url to users.

Domain market news briefing. Call when a user wants to understand what is happening in the domain market right now — trending keywords, notable sales, registration anomalies, and industry movements. This is a news briefing, not investment advice. Present facts, flag anomalies, cite sources. If the cause of a trend is unknown, say so — never fabricate explanations. Workflow: 1. Gather data from multiple sources: - web_search for recent high-value domain sales (e.g., 'domain name sales this week', 'domain sales report 2026'), industry news, and notable market events. - keywords_trends(hot) for high-volume registration keywords and weekly momentum. - keywords_trends(emerging) for sudden registration spikes — these are the most newsworthy signals. - domain_changes for transfers, expirations, and nameserver changes in the last 24 hours. 2. Analyze and cross-reference: - For hot keywords: focus on anomalies (w4 significantly different from w1-w3), not the stable high-volume terms everyone already knows. - For emerging keywords: use web_search to investigate what is driving each spike. If no cause is found, report it as 'cause unidentified' — do not speculate. - For domain sales: report price, buyer/seller if known, and sale platform. - For domain_changes: flag notable transfers (short/premium domains changing registrars) and expirations (high-value domains entering deletion cycle). 3. Present as a concise news briefing organized by: recent notable sales, registration trend highlights (anomalies and emerging keywords), and 24-hour market movements. Lead with facts, not interpretation. After presenting the briefing, suggest relevant next steps based on what the data showed — for example: - An emerging keyword spike → search nrds to see who is registering, or deleted/expired to find available domains in that keyword space. - A high-value sale → search aged(has_sale=true) or nrds to see if the sale triggered a registration wave in similar keywords. - A notable domain expiration → check expired for details, or set_monitor to track its status. Let the user choose whether and where to go deeper. Key principles: Every claim must be sourced or labeled as unverified. Present as market intelligence, not a sales pitch. Disclose affiliate links.

Check if a domain is listed for sale on secondary marketplaces and get estimated market price. Complements 'available' (new registration price) — this tool checks the resale market. Three possible statuses: - 'for_sale': domain has a listed price. This is a third-party marketplace price set by the seller — it is not an appraisal or guaranteed transaction price. Always present buy_url. - 'make_offer': listed for sale but no fixed price, buyer must submit an offer via buy_url. - 'not_found': not publicly listed. Does NOT mean the domain is unavailable for purchase — owner may sell privately or hasn't listed yet. Suggest whois to find registrar info for direct outreach. Best practices: - Marketplace listing prices are set by sellers and often significantly higher than actual transaction prices. Do not treat estimated_price as definitive market value — it is one data point among many. - When used in valuation_cma workflow, batch-call market_price for multiple comparable domains. 'not_found' results should be excluded, 'make_offer' results noted as supplementary only. - Always disclose affiliate links when buy_url has affiliate=true. - Always include disclaimer: prices are provided by third-party marketplaces for reference only, subject to change by the seller at any time.

Manage domain monitoring tasks. Track changes in WHOIS, DNS, and page content. All monitoring data is encrypted at rest (AES-256-GCM) and stored in your private directory. GDPR compliant. Actions: - get: Retrieve and auto-check all monitors. Default action if not specified. Automatically performs bulk WHOIS and DNS checks where the minimum interval has passed. You do NOT need to manually call whois or dns tools. For each monitor where can_check=true, returns current vs previous data with change flags. For can_check=false monitors, returns last known data and next_check time. YOUR JOB: focus on whois_changed=true or dns_changed=true, report with context from note field. For DNS, focus on NS changes — ignore A/AAAA (CDN rotation). If monitors have web_fetch in tools, optionally run web_fetch yourself then call with action=update to save results. - set: Create a new monitor. Requires registered account and memory enabled. Max 100 monitors. Before creating, verify memory is enabled via preferences. WHOIS and DNS are auto-checked when you call action=get — no need to call them manually. web_fetch is optional and must be run manually. - update: Save web_fetch page results for a monitor. WHOIS and DNS are auto-saved by action=get — you only need this for web_fetch page content. Typical flow: call action=get (auto-checks WHOIS/DNS), run web_fetch yourself, then call action=update with the page summary. The whois and dns parameters are accepted for backward compatibility but normally not needed. - delete: Remove a monitor task. Requires registered account (member or above) and memory enabled for all actions.

A professional domain naming consultation workflow. Call when a user is looking for domain name ideas, starting a new project and needs a domain, or has vague/open-ended domain requirements. Do NOT call when the user already has a specific name to check (use available/bulk_available) or already knows their keyword and wants variations (use domain_generator). This is a multi-turn consulting engagement — conversation first, recommendations second. Never skip the diagnosis phase, and never generate domain suggestions before understanding the user's needs. Workflow: 1. Needs Diagnosis — ask the user questions to understand their project. Start with the essentials (project/industry, target audience, domain purpose), then follow up with budget guidance, TLD preference, and style preference (textural/imagery vs keyword-based). Ask 1-2 questions at a time, not all at once. Do NOT generate any domain names or call any tools in this phase. Even if the user's description seems clear, confirm user persona and brand tonality before proceeding. 2. Semantic Leap — based on confirmed requirements, generate 3-5 metaphor directions that abstract one level up from the industry. Do NOT coin words directly from industry keywords unless the user mentioned them. Examples: travel → docking point → berth; notes → ideas → notion. Present the directions to the user and let them choose before generating any candidates. 3. Domain Search & Verification — along the chosen direction, generate at least 10 candidate names. Every candidate must pass a quality check: does it feel natural in conversation? Does it evoke imagery? Stripped of all context, does the word alone have quality? If you hesitate, discard it. Then use bulk_available, deleted, expired, aged, and tld_check to verify acquisition paths and costs. For deleted and expired searches, try each keyword in different positions (start, end) to maximize coverage. Present results layered by acquisition method: directly registrable → listed for sale → contact owner → monitor/backorder, each with estimated cost. 4. Iterative Refinement — based on user feedback, either generate more candidates in the same direction (with independent thinking — do not reuse previous coining patterns as templates), explore a new metaphor direction (return to step 2), or run brand_match on a finalist. If the current best is already strong, say so — do not force-generate low-quality options to show effort. Key principles: - Communication before generation — better to ask one more question than to blindly generate irrelevant domains. - A good name feels natural, evokes imagery, and has quality on its own. A bad name requires excessive explanation, feels forced, or mismatches the use case. - Help users save money while meeting their needs, but also surface purchase and backorder opportunities when relevant. - All statements must be data-backed. Do not speculate. Minimize etymology explanations — a good name does not need explaining. - Disclose affiliate links.

Search newly registered domains (last 60 days). Use for tracking competitor registrations, spotting trending keywords, monitoring brand squatting, or finding resale opportunities. Two modes: - Keyword search: provide 'keyword' to search across all TLDs by keyword matching. Optionally add 'tld' to narrow results. - TLD browse: provide 'tld' WITHOUT 'keyword' to browse all newly registered domains under a specific TLD. Use filters (days_range, period, length, type, etc.) to narrow results progressively. This mode is for exploratory discovery when the user wants to see what is being registered in a TLD, not for keyword-based search. Note: TLD browse mode only supports gTLDs (com, net, org, xyz, etc.), not ccTLDs (ai, co, de, etc.). When the user provides a keyword, always use keyword search mode. Only use TLD browse mode when the user explicitly wants to explore a TLD without a specific keyword in mind. Best practices: - In keyword mode, keyword defaults to 'contain' matching. Use position=start, position=end, or position=middle to control where the keyword appears. - In TLD browse mode, combine filters (days_range, period, length, type) to get precise, small result sets. Do not request unfiltered TLD results. - Always use no_hyphen=true unless specifically looking for hyphenated domains, hyphenated registrations are mostly low-quality spam. - sort=tld_counter_desc surfaces keywords registered across many TLDs simultaneously, a strong signal of trending demand. - period=6+ filters for domains registered for 6-10 years, indicating serious projects rather than speculative 1-year registrations. - prefix_tld_count in results indicates how many TLDs share the same prefix, values above 10 suggest the keyword is being actively pursued by multiple registrants. - Disclose affiliate links when presenting register_url to users.

Reverse NS lookup. Find all gTLD domains hosted on a specific nameserver. Useful for mapping domain portfolios, understanding the scale of a nameserver's usage, and discovering what domains share infrastructure. Best practices: - sort=length_asc surfaces the shortest (most premium) domains first — large portfolios often contain hidden short-letter gems. - pure_alpha=true is the cleanest way to filter for letter-only domains. This is stricter than no_number + no_hyphen combined, as it excludes any non-letter character. - keyword filters by substring within domain names on that nameserver — useful for finding domains in a specific niche or vertical. - min_len and max_len require exact integers (e.g., '4'), not range syntax like '<5'. - If results fill a full page (10+), check total and paginate — large nameservers may host thousands of domains. - Look for patterns in results: similar naming conventions (brand-us.com, brand-uk.com) indicate portfolio clustering by the same owner.

Domain alternatives workflow. Call when a user's target domain is unavailable and they need alternative options across different lifecycle stages — for example after available or bulk_available returns unavailable, or as a follow-up from analyze or name_advisor when a candidate is taken. Do NOT call when the user is starting from scratch without a target (use name_advisor), already knows their keyword and wants creative variations (use domain_generator), or wants to analyze the taken domain itself (use analyze). This is a multi-turn workflow. Stop and wait for user input at every checkpoint. Workflow: 1. Understand User Needs — extract core keywords from the unavailable domain (e.g., getflow.com → keyword: flow, pattern: prefix+root). Then ask the user: what appealed to you about this domain (the keyword, the length, the sound)? Are you open to other TLDs or .com only? Would you consider purchasing a registered domain, or only free registration / backorder? Do NOT search until the user responds — their motivation determines the entire search strategy. 2. Lifecycle Search — search by priority: deleted (free registration, highest priority) → expired (backorderable) → aged (registered, only if user is willing to purchase). For each tool, try the keyword in different positions (start, end) to maximize coverage — e.g., searching 'flow' at start and end will surface very different results. If a strong match is found in deleted, note it as a top recommendation. 3. Creative Variants — based on what the user liked about the original domain, generate 15-20 creative variants respecting their TLD preference (default .com). Avoid concatenations creating sensitive words or offensive abbreviations. Verify all with bulk_available. 4. Present Results — organize all findings layered by acquisition method from easiest to most involved: free registration (deleted + available variants) → backorderable (expired) → purchasable (aged for-sale) → monitorable (worth watching). Every domain must include the appropriate acquisition link. Ask the user which options interest them. 5. Follow-up — based on user choice: generate more variations, run brand_match, set up set_monitor, do deeper analysis with analyze or expired_analysis, or run valuation_cma. Key principles: - Default to .com only unless user specifies otherwise. - Every domain presented must include an acquisition link (register_url, backorder_url, or sale link). - Disclose affiliate links.

Manage user preferences and memory settings. Actions: - get: Check if memory is enabled and retrieve saved preferences. Default action if not specified. - set: Save preferences. Requires explicit user consent before enabling memory. memory_enabled must be true before any other preferences, monitors, or strategies can be saved. - delete: Delete all stored user data permanently (preferences, monitors, strategies). GDPR Article 17: Right to erasure. All user data is encrypted at rest using AES-256-GCM and stored in isolated user directories. No one — including DomainKits staff — can read your data. Fully GDPR compliant. When action=get: - If reason="not_configured", ask the user with a clear choice: "I can remember your preferences, monitoring tasks, and discovery strategies across sessions. All data is encrypted. Would you like to enable this?" Only call with action=set and memory_enabled=true after explicit user consent. - MONITOR HANDLING: If monitors_count > 0, check monitors_summary. If can_check_count > 0, call get_monitors to auto-check domains. If can_check_count == 0, all monitors are in cooldown — inform the user when next check is available (next_check field), do NOT call get_monitors. The domains list lets you answer "what am I monitoring?" without triggering a check. - If strategies_count > 0, proceed to call get_strategies.

Domain registration and renewal prices by TLD from Dynadot. Check registration, renewal, and transfer costs before purchasing. Best practices: - Use comma-separated values for multi-TLD comparison: tld='com,io,ai,xyz'. - Results include register_url (Dynadot affiliate link). Always display this link when showing prices and disclose affiliate status. - Prices are in USD. Registration price is for the first year; renewal price is the ongoing annual cost — highlight the difference when they diverge significantly (e.g., some TLDs have low introductory registration but high renewal).

Check domain safety via Google Safe Browsing, and check Google search index status. Returns two pieces of data: (1) safe — whether Google Safe Browsing flags the domain for malware, phishing, social engineering, or unwanted software, including specific threat types if flagged; (2) index — whether the domain has pages indexed in Google and an estimated count. A flagged domain is a critical risk signal — it likely has a problematic history (malware distribution, phishing, spam operations) that may be difficult or impossible to recover from. This is especially important when evaluating expired or aged domains for acquisition. An unindexed domain may indicate it was previously penalized or has been dormant.

Domain buyer discovery workflow. Call when a user wants to find potential end-user buyers for a domain they own or are considering selling. When to use: user asks 'who would buy this domain?', 'help me sell [domain]', or wants to find buyers as a follow-up after keyword_intel or plan_b. Do NOT use when the user wants to buy a domain (use plan_b), check domain value only (use valuation_cma), or analyze a domain technically (use analyze). Workflow: 1. Extract the core keyword(s) from the domain. Use web_search '[keyword] company OR brand OR product' to discover who is already operating under this name or close variants. Note their business type, current domain, scale, and how long they've been using the keyword. This research step is mandatory — do not skip it. 2. Categorize potential buyers into three tiers by purchase motivation: - Tier 1 — Domain Upgraders: companies already operating under this exact name or a close variant (on .net, .io, a hyphenated version, or with a prefix/suffix added), who would naturally want the cleaner or shorter version. These are the highest-intent buyers — they've already built equity around the keyword and this domain is a direct upgrade for them. - Tier 2 — Strategic Expansioners: companies in the same industry whose product, feature, or campaign aligns with what this domain describes. Acquiring it is a strategic fit that strengthens positioning. - Tier 3 — New Brand Builders: funded startups or new ventures that haven't fully launched yet but would find this name ideal. 3. Use Claude for Chrome to research buyers on LinkedIn in three layers. Open LinkedIn in the browser and execute the following searches in order: Layer 1 — Find Domain Upgraders (highest priority): Switch to the Companies tab. Search using the exact keyword and close variants: "[keyword]" OR "[keywords]" OR "[keyword]-[common suffix]" Scan results for companies whose name or description contains the keyword but whose website is on an inferior domain (not the clean .com). These are Tier 1 buyers. Layer 2 — Find Strategic Buyers: Search Companies tab by industry theme: "[industry vertical] [keyword theme]" Apply Industry filter (e.g., Events Services, Software, Media) to narrow results. Identify Tier 2 candidates whose business would be strengthened by owning this domain. Layer 3 — Find Decision Makers at identified companies: For each promising company from Layers 1 and 2, switch to the People tab and use Boolean search to locate the right contact: ("CMO" OR "VP Marketing" OR "Chief Marketing" OR "Brand Director" OR "Head of Brand" OR "Head of Marketing") AND "[company name]" NOT (intern OR assistant) Record: full name, title, LinkedIn profile URL. 4. Synthesize findings into a prioritized buyer list. Present Tier 1 first, then Tier 2, then Tier 3. For each entry include: company name, current domain they operate on, reason they are a strong buyer candidate, and decision maker contact if found. 5. After presenting the buyer list, ask the user what they want to do next. Tailor follow-up based on their response: - Wants a price before outreach → suggest valuation_cma for a data-backed asking price, market_price to check existing listings. - Wants to draft outreach → help write a personalized email for each Tier 1 buyer, emphasizing the specific upgrade value to their existing brand. - Wants to list the domain → suggest Afternic, Sedo, or Dan.com depending on domain type. - Wants more buyer leads → suggest brand_match to identify additional companies using the keyword, or nrds to see who has recently registered variants. Key principles: focus on upgrade motivation, not conflict framing. Every buyer candidate must be grounded in data from web_search or LinkedIn results. Do not speculate about intent. Present the buyer list as opportunity intelligence, not legal risk assessment. Disclose affiliate links when presenting marketplace URLs.

Manage personalized opportunity discovery strategies — let AI periodically execute your investment logic and discover new opportunities. All strategy data is encrypted at rest (AES-256-GCM). GDPR compliant. Actions: - get: Retrieve all strategies with run status and available presets. Default action if not specified. Shows can_run status, runs_today, and available preset strategies not yet activated. - set: Create a new strategy. Describe the domains you want in natural language, or activate a preset by preset_id. Examples: "Monitor all domains with 'ai' keyword, 10+ years of history, about to expire, .com", "Track newly registered domains containing 'claw', letters only, .io", "Discover crypto-related keywords with high TLD registration volume". Limits: Member 1 / Premium 3 / Platinum unlimited. - update: Record execution result for a strategy. Call after running a strategy to save the result summary. Subject to daily run limits and minimum interval between runs. - delete: Remove a strategy. Requires registered account (member or above) and memory enabled for all actions.

Check a keyword prefix's registration status across all TLDs. Returns total registration count (gTLDs + ccTLDs) and status of core TLDs (com, net, org, io, ai, de). This is a saturation and popularity metric — the total count indicates how widely a keyword has been claimed across the TLD namespace. Interpreting results: - count >200: Keyword is widely recognized — either high market demand or strong brand protection (or both). Cross-reference with keyword_data and active to determine which. - count 50-200: Worth attention — check if there are still opportunities available. - count <50: Not a particularly popular keyword in the domain market. - gtlds_count vs cctlds_count ratio: High ccTLD registration suggests international interest in the keyword. The tlds field shows status for core TLDs (com, net, org, io, ai, de) with values: 'registered', 'for_sale', 'expiring', or 'might_available'. Note that 'might_available' means the prefix is not found in our database for that TLD — confirm with the 'available' tool before assuming registrability. Best practices: - The prefix parameter must NOT contain the TLD extension — use 'openai' not 'openai.com'. - If .com shows 'might_available' for an established keyword, this is unusual and worth verifying. - If .com shows 'for_sale' or 'expiring', this is a potential acquisition opportunity worth flagging.

gTLD rankings by registration volume. See which gTLDs have the most new registrations today or the most total active domains. Best practices: - type='newly' ranks by today's new registrations — useful for spotting which TLDs are currently hot. Sudden spikes in a usually quiet TLD may signal a promotion or speculative wave. - type='active' ranks by total active domain count — reflects overall market size and maturity. - Compare newly vs active to find TLDs with disproportionate registration activity relative to their size (high new-to-active ratio = momentum signal). - type='newly' data has a one-day lag — it reflects yesterday's registrations, not today's. - The key insight from newly rankings is relative change, not absolute numbers. A TLD jumping significantly in rank or showing unusual registration volume compared to its typical level is the signal worth investigating — use tld_trends for historical baseline and web_search to identify the cause. - This data pairs well with tld_trends: tld_rank shows today's snapshot, tld_trends shows the trajectory over time.

gTLD registration trends over time. Analyze historical registration patterns for specific gTLDs — spot hype cycles, compare competing extensions, or check long-term health. Two modes: - action='data' + tld (single TLD): deep-dive into one TLD's trend over time. Use this to answer 'is .ai still hot?' or 'is .net dying?'. - action='compare' + tlds (comma-separated, max 5): side-by-side comparison. Use this to answer 'should I buy the .io or .ai version?' by comparing registration momentum. Best practices: - Focus on ma7 (7-day moving average) slope rather than raw daily numbers — daily counts are noisy, the moving average reveals the real trend direction. ma7 trending up = genuine momentum, flat = stable, declining = cooling off. - Compare ma7 vs ma14 for trend acceleration: ma7 crossing above ma14 = momentum building, ma7 dropping below ma14 = momentum fading. - type='newly' shows registration velocity (new domains per day) — best for detecting hype cycles and short-term momentum shifts. - type='active' shows total installed base — best for market size comparison and long-term health assessment. - When comparing TLDs, note the absolute scale difference — a TLD with 100K active domains showing 500 new/day has very different dynamics than one with 10M active showing 500 new/day. - Mutually exclusive inputs: action='data' requires 'tld' (single). action='compare' requires 'tlds' (comma-separated). Do not mix them. - days must be one of the allowed values: 7, 14, 30, 60, 90, 180. Use 30 for short-term momentum, 90-180 for trend confirmation. - Pairs well with tld_rank for today's snapshot context, and price to check registration costs for trending TLDs.

Trend discovery and domain opportunity workflow. Call when a user wants to explore what keywords are trending in domain registrations and whether those trends represent real investment opportunities. When to use: User asks what's trending, wants to find opportunities based on registration momentum, or wants to explore hot/emerging keywords. Not for analyzing a specific domain (use analyze), deep-diving a known keyword (use keyword_intel), or getting a market news briefing (use market_beat). This is a MULTI-TURN workflow. Present findings at each phase and wait for the user to choose direction before proceeding. Do not batch all phases into a single response. Let users choose which keywords to explore — do not decide for them. Methodology — three phases, each gated by user input: 1. Discover: Surface trending keywords using keywords_trends (hot, emerging, or prefix depending on user interest). The results already include pre-computed quality metrics for hot and emerging types: com_ratio, digit_ratio, most_tld, and most_tld_ratio. Present the data with quality assessment: - com_ratio above 0.15 = genuine interest; below 0.05 = likely bulk speculation on cheap TLDs. - most_tld_ratio above 0.7 on a non-.com TLD = trend driven by bulk registration, not organic demand. - digit_ratio above 0.2 = low-quality speculative registrations. Flag any keywords with suspicious quality signals. Ask the user which keyword(s) they want to investigate further. Stop and wait. 2. Assess market catalyst: For the user's chosen keyword, investigate what is driving the trend. - web_search is MANDATORY — do not substitute with your own knowledge. Execute at least two separate searches: one for domain transaction history (e.g., '{keyword} domain sold price 2026') and one for industry news (e.g., '{keyword} news 2026'). Domain transactions are the single strongest catalyst for registration spikes — a high-value sale (e.g., keyword.com selling for six or seven figures) routinely triggers a wave of speculative registrations on the same keyword. Always check for this first. Industry news (product launches, funding rounds, regulatory changes) is the second catalyst layer. If neither search returns relevant results, state that clearly — do not fill the gap with training data. - Synthesize the quality metrics from Phase 1 with the catalyst research into a clear verdict: real trend (strong quality metrics + identifiable catalyst), speculative (weak quality metrics or no catalyst), or uncertain. Present the assessment and recommended search direction. Stop and wait for user confirmation before searching for domains. 3. Find opportunities: Based on the assessment, search for available domains. - deleted and expired for domains available at registration cost or via backorder. - aged with has_sale=true for secondary market listings. - All domains presented to the user MUST be verified via bulk_available before recommending. - Disclose affiliate links. After presenting opportunities, offer relevant next steps: deep analysis on a specific domain (analyze), brand conflict check (brand_match), monitoring setup (set_monitor), or exploring a different keyword.

Search for unregistered short .ai domains. Find rare 3-letter and 4-letter pattern domains still available for registration. Pattern types: - CVCV: Consonant-Vowel-Consonant-Vowel (e.g., 'bora', 'mito') — most brandable, sounds like real words. - VCVC: Vowel-Consonant-Vowel-Consonant (e.g., 'amon', 'ivan') — name-like quality. - CCVV: Double consonant + double vowel (e.g., 'bloo', 'staa') — unique/distinctive. - 3letter: Any remaining 3-letter .ai domains — extremely rare and high-value. Best practices: - For brandable names: use type=CVCV or type=VCVC, sort=count_desc to surface names with validated demand across other TLDs. - For undiscovered gems: use tld_count=0-10, sort=count_asc — low cross-TLD registration may indicate overlooked opportunities. - For ultra-premium: use type=3letter — 3-letter .ai domains are the scarcest inventory. - tld_count interpretation: high (50+) = validated demand, the name is desirable across TLDs; low (<10) = less widely registered, may be undiscovered or niche. - Always verify availability with the 'available' tool before recommending registration — availability can change at any time. - .ai is the premium TLD for AI/tech companies; short .ai domains are high-value due to scarcity.

Check your current usage and remaining quota for all tools. Shows daily limits, usage counts, and rate limits for your tier.

Domain Comparative Market Analysis (CMA) valuation workflow. Call when a user wants to estimate a domain's market value by finding comparable domains listed for sale. When to use: user asks 'how much is this domain worth?', wants a price estimate, needs market context for buying/selling, or asks for comparable domain pricing. Do NOT use for single common word + TLD domains (e.g., travel.com, music.com) — these are unique assets where CMA does not apply; decline and explain why. Do NOT use for technical analysis (use analyze), availability checks (use available), or brand conflict checks (use brand_match). CMA applies to: compound words (cloudpay), coined brands (spotify), industry word + modifier (healthymag), prefix/suffix combos (getflow, appnova). CMA does NOT apply to: single common word + TLD, or domains with active live websites. Workflow: 1. Pre-screening: validate the domain is suitable for CMA. If it is a single common word + TLD, refuse and explain. Then ask the user one question: what they value most about this domain — the keyword meaning, the length, the age, or something else? This determines the direction of comparable search (e.g., semantic vs structural vs age-based comps), NOT the valuation itself. Do NOT ask about intended use — valuation must be objective and data-driven regardless of whether the user plans to build, flip, or hold. Do NOT call any tools before the user responds. 2. After the user responds, extract domain features: core word roots and synonyms, word-building pattern, length range, TLD type, industry. Then: - web_search site:{domain} to check if it has a live website. If actively in use, refuse valuation. - tld_check to see cross-TLD distribution. If the domain appears unregistered, inform the user and do not proceed. Present extracted features and screening results. Confirm with the user before proceeding. 3. Search for comparable domains and retrieve prices: - aged with has_sale=true to find listed domains with the same core keyword, same TLD, similar length. Check synonyms if insufficient results. - active with status=forsale as supplement if fewer than 10 candidates. - market_price for each candidate. market_price returns three possible statuses: * 'for_sale': has a listed price and a buy_url — this is the primary data source for CMA. * 'make_offer': listed but no fixed price — note as supplementary only. * 'not_found': exclude from comp pool. - market_price sources prices from 2nd layer and other integrated marketplaces via API. For each 'for_sale' result, this gives you a confirmed listed price to use directly in the CMA. - After presenting the comp table, also surface the buy_url for each 'for_sale' comparable. If buy_url has affiliate=true, disclose this clearly: 'These are affiliate links — DomainKits may earn a commission if you make a purchase through them. Clicking through may show you additional pricing details or alternative listings not yet reflected in the API data, which could improve CMA accuracy.' The user is not required to click — the CMA proceeds with API prices either way. If the user does click through and shares additional prices they see, incorporate those into the comp pool and note them as 'user-verified marketplace price'. - Filter all comps by semantic relevance, structural similarity, length match, and price reasonableness. Remove outliers and negative-meaning domains. Select 3-5 best comparables. - If fewer than 3 'for_sale' priced comps remain after filtering, warn the user: 'Fewer than 3 priced comparables found — CMA confidence is low. Results should be treated as directional only.' Present comparable table and wait for user feedback before proceeding to valuation. 4. Derive valuation with optional adjustments: - web_search for historical sales of similar domains on NameBio as cross-validation. - keywords_trends for keyword registration heat, plus web_search for industry tailwinds. Rising heat = premium, declining = discount. Present the complete valuation report including: comparable table with source noted per price (API or user-verified), premium/discount factors with data sources cited, valuation range with reasoning, historical sales if found, trend adjustment, uncertainty statement (market volatility, listing vs transaction gap), and general action suggestions (buy-low-sell-high principles, NOT specific buy/sell recommendations). MUST include compliance statement: 'This valuation is derived from public listing prices on third-party marketplaces, for reference only, and does not constitute official appraisal or investment advice. Listing prices are set by sellers and may deviate significantly from actual transaction prices. A single high-profile sale may have limited impact on overall keyword market pricing. However, multiple high-value transactions on the same keyword — especially exact-match domains — indicate broader market repricing and carry significantly more weight in valuation.' After presenting, suggest next steps: plan_b for alternatives, set_monitor for price tracking, brand_match for acquisition risk. Key principles: every claim about value must cite specific tool data. Never fabricate prices, traffic estimates, or quantitative claims. Never give buy/sell recommendations — present data, let the user decide. Always disclose affiliate links when surfacing buy_url.

Query WHOIS/RDAP registration info for a domain. Returns registrar, dates, status codes, and nameservers. Nameservers can indicate if a domain is parked for sale (e.g., Sedo, Afternic). Status codes can reveal special states such as expired, pendingDelete, or redemptionPeriod.