# Audit/verify Definition Of Done

> Verifies Definition of Done checks and generates a DoD report.

- Skill: `majiayu000/audit-verify-definition-of-done` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds add majiayu000/audit-verify-definition-of-done`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/audit-verify-definition-of-done/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/audit-verify-definition-of-done

---


# Audit: Verify Definition of Done

## 1. Context

This skill verifies Definition of Done checks for a session and emits a DoD report under the runtime context.

## 2. Inputs

- **context** (required): Bounded context name (safe path segment).
- **session_id** (required): Session identifier (safe path segment).
- **required_artifacts** (optional): Semicolon-delimited required artifact paths.
- **allow_empty_diff** (optional): Allow empty git diff (`true`/`false`).
- **test_command** (optional): Override test command (default: `bun test`).
- **check_command** (optional): Override fpf check command (default: `bun packages/fpf/bin/fpf check`).
- **agent_type** (optional): Agent type performing the DoD check.
- **agent_model** (optional): Agent model identifier.
- **role_assignment** (optional): RoleAssignment for U.Work logging (default: ProxyAuditor).
- **decisions** (optional): Semicolon-delimited DRR ids/paths.
- **timestamp_start** (optional): ISO-8601 timestamp for deterministic output.

## 3. Outputs

- `runtime/contexts/<context>/audits/dod/<session_id>.<timestamp>.dod.md`

## 4. Procedure

1. Validate inputs and resolve required artifacts (including the session record).
2. Run git diff, tests, and fpf check (unless overridden).
3. Write a DoD report with pass/fail status.
4. Emit U.Work via `telemetry/log-work` when available.