You're viewing a demo portfolio

Join the waitlist
PRSM

submit_skill_verdict

Active

Tool of OpenAccountants

declared in 1.4.0

Call this AFTER the signed-in user has run a skill and reviewed its REAL output (e.g. a computed VAT return), to record their structured quality verdict against the skill and its current version. This is the highest-value feedback the platform collects — especially from accountants, whose verdicts are treated as gold. Use when the user is acting as a REVIEWER grading the AI's output ('that return is wrong', 'the figures came out off', 'rate this', 'here's what the skill got wrong'). This is product-quality QA on the SKILL — NOT a taxpayer handoff (for that, use request_accountant_review) and NOT a generic bug report (that's submit_feedback). Pass the worksheet the skill produced when you have one; the server foot-checks it.

Parameters schema

{
  "type": "object",
  "required": [
    "skill_slug",
    "rating"
  ],
  "properties": {
    "score": {
      "type": "number",
      "description": "Optional 0-100 quality score the reviewer may add."
    },
    "rating": {
      "enum": [
        "solid",
        "minor_issues",
        "significant_issues",
        "dangerous"
      ],
      "type": "string",
      "description": "The reviewer's overall verdict on the skill's output. solid = correct and file-ready; minor_issues = small/cosmetic problems; significant_issues = materially wrong figures; dangerous = would cause a wrong filing or a penalty. Required."
    },
    "findings": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "box": {
            "type": "string",
            "description": "Return box/line id (e.g. '45')."
          },
          "was": {
            "type": "string",
            "description": "What the skill output."
          },
          "note": {
            "type": "string",
            "description": "Why."
          },
          "figure": {
            "type": "string",
            "description": "Name of the figure being corrected (e.g. 'output VAT')."
          },
          "should_be": {
            "type": "string",
            "description": "What it should have been."
          }
        }
      },
      "description": "Structured corrections — each item identifies a figure/box and what it was vs. what it should be."
    },
    "scenario": {
      "type": "string",
      "description": "What was being computed — e.g. 'Q1 2026 Malta VAT3, standard-rated sales + EU acquisitions + a blocked entertainment input'."
    },
    "worksheet": {
      "type": "object",
      "description": "Optional structured worksheet JSON the skill produced (WORKSHEET_CONTRACT.md shape: { jurisdiction, tax_type, period, currency, lines:[...], boxes:[...], result:{type,amount} }). If provided, the server foot-checks the arithmetic and stores the recon status.",
      "additionalProperties": true
    },
    "skill_slug": {
      "type": "string",
      "description": "Slug of the skill that produced the output being judged, e.g. 'malta-vat-return'. Required."
    },
    "suggestion": {
      "type": "string",
      "description": "Free-text fix or improvement for the skill."
    },
    "output_summary": {
      "type": "string",
      "description": "Prose summary of what the skill actually produced — the figures / return lines the reviewer is judging."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.700.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

OpenAccountants

https://github.com/openaccountants/openaccountants

2/7 registries
View full server →