Skill Verify Auditor — Development agent for Claude Code
Rubric compliance auditor for skill Self-Verify steps (dispatch marker skill-verify: ).
How to install Skill Verify Auditor
Installs to ~/.claude/agents/gggodlin-claude-pr-review-skill-verify-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/GGGODLIN/claude-pr-review/HEAD/agents/skill-verify-auditor.md -o ~/.claude/agents/gggodlin-claude-pr-review-skill-verify-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Verify Auditor does
name: skill-verify-auditor description: Rubric compliance auditor for skill Self-Verify steps (dispatch marker `skill-verify:`). Use when a SKILL.md's Self-Verify step requires checking a finished report or deliverable against a fixed rubric, with BOTH the deliverable text and the rubric fully embedded in the prompt. Returns per-rule PASS/FAIL lines plus a final VERDICT line in the exact format the rubric specifies. Do not use for verifying work against a spec or repo state (task
Alternatives in Development
- Chain Executor — Executes delegated chain steps with context isolation 186 ★
- Architecture Guardian — Use to verify MacMagazine module boundaries and system compliance are intact after adding/moving code or editi 169 ★
- Mathodology Problem Analyst — Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable 137 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Marker
Strict university marker that grades a draft assignment against its brief and rubric, criterion by criterion,
Sticky Fingers
Use this agent for independent adversarial verification of a deliverable against a rubric — santa-method's sec
Reconcile Agent
Reads the findings from finished steps and works out what they change for the steps not yet built — stale path
Draft Critic
Use when a finished draft must be attacked before it goes into the form — prose quality, evidence gaps, rubric
Gauge
Review agent — the judgment gate. Use to review a deliverable, draft, plan, or change for quality, correctness
Dry Run Enforcer
Verify the trading codebase defaults to dry-run (paper/simulated) mode and that live order placement requires
Related Skills
Review UX Live
Live browser-walk UX review using the console-idiom rubric. Requires a browser MCP (Playwright, Chrome DevTool
ADR Conformance
You are an architect checking finished work against the Architecture
Forgeflow Adoption
Print a concise Forgeflow adoption pack with fit guidance, first-trial steps, proof boundaries, and decision r