Plan Audit

Audit an implementation against a plan (dev-docs/plans/*). Use when a user asks to check for gaps, logic errors, or missing tests relative to a plan or Work Items.

49 stars 21 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lllyys/vreader --skill plan-audit
Manual install
git clone --depth 1 https://github.com/lllyys/vreader.git /tmp/vreader
mkdir -p ~/.claude/skills
cp -r /tmp/vreader/.claude/skills/plan-audit ~/.claude/skills/plan-audit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Plan Audit

## Overview

Audits completed work against a plan (WIs + acceptance + tests) and reports gaps, logic errors, and missing coverage with file/line references.

## Workflow (Audit)

1) **Locate the plan**
   - Prefer `dev-docs/plans/<plan>.md`.
   - If unclear, ask for the plan path or the WI list.

2) **Extract audit checklist**
   - For each WI, list:
     - Goal
     - Acceptance criteria
     - Tests required
     - Touched areas (files/symbols)

3) **Map implementation to WIs**
   - Use `git log`, `git show --stat`, `rg`, and file inspection.
   - Record which files/commits satisfy each WI.

4) **Gap & correctness analysis**
   - Check each acceptance item vs actual behavior.
   - Find logic errors, edge-case failures, and incomplete flows.
   - Validate test coverage against the “Tests (first)” section.
   - If the plan references specs, verify implementation matches those specs.
   - If the plan is missing acceptance/tests, record it as a plan-quality gap.

5) **Report findings**
   - Order by severity: Critical → High → Medium → Low.
   - Each finding must include:
     - WI reference
     - File path + line
     - Why it violates the plan
     - Expected behavior per plan

## Output Format (required)

- **Findings (ordered by severity)**  
  - `File:line` and WI reference
  - Impact and suggested fix
- **Plan Gaps Summary**  
  - WI‑### → missing/partial acceptance items
- **Test Coverage Gaps**  
  - Missing tests, broken tests, or “test not written”
Read the full skill on GitHub

Details

Skill name
plan-audit
Repository
lllyys/vreader
Path
.claude/skills/plan-audit/SKILL.md
Repo updated
6 August 2026

FAQ

What does the Plan Audit skill do?

Audit an implementation against a plan (dev-docs/plans/*). Use when a user asks to check for gaps, logic errors, or missing tests relative to a plan or Work Items.

How do I install the Plan Audit skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add lllyys/vreader --skill plan-audit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Plan Audit popular?

It lives in lllyys/vreader, which has 49 GitHub stars and 21 forks.

Related skills

AI Coding Agents

49

lllyys/vreader

Comprehensive guide for using Codex CLI (OpenAI) and Claude Code CLI (Anthropic) - AI-powered coding agents. Use when orchestrating CLI commands, automating tasks, configuring agents, or troubleshooting issues.

AI, LLMs & Agents21

Dispatch

49

lllyys/vreader

Parallel lane dispatch — the ONLY sanctioned multi-item fan-out (feature #130, rule 55). Use when the user asks to fix several bugs at once ('fix #a #b #c'), implement independent feature WIs in parallel, or run a dispatch batch. Orchestrates worktree-isolated implementer lanes on leased simulators, validates HANDOFFs, and runs the serial integration tail (rebase → re-test → tracker/docs → version-at-slot → PR → merge-from-worktree → tag). A single item degrades to the inline /fix-issue or /feature-workflow flow.

Git & Code Review21

Feature Workflow

49

lllyys/vreader

Run the binding 6-gate feature workflow end-to-end per rule 47 (Plan → Independent Plan Audit → TDD Implementation → Implementation Audit Loop → Device/Integration Verification → Merge). Use this skill whenever the user wants to implement a new feature in vreader, asks 'implement feature #N', 'work on feature 47', 'start the feature workflow', 'plan + build feature X', or describes building a new capability that doesn't yet exist. NOT for fixing broken implementations (that's fix-issue). The skill drives the row from `TODO` → `VERIFIED` through six gates that must never be skipped — author/aud

Productivity & Notes21

Test All Device

49

hw-native-sys/simpler

Run the full hardware (onboard) CI pipeline (examples + tests/st) with automatic platform and device detection. Use when the user asks to run all device/hardware tests or the full onboard CI locally.

Testing & QA102

Perf Runtime Device

49

hw-native-sys/simpler

Benchmark the hardware performance of all scene tests under a runtime (tests/st/<arch>/<runtime>/, $ARGUMENTS). Use when the user asks to benchmark all examples of a runtime on hardware.

Testing & QA102

Test All Sim

49

hw-native-sys/simpler

Run the full simulation CI pipeline (examples + tests/st) on a2a3sim/a5sim. Use when the user asks to run all sim tests or the full simulation CI locally.

Testing & QA102

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.