About

Imported from shipshitdev/skills (skills/qa-reviewer/SKILL.md). Install upstream with npx skills add shipshitdev/skills --skill qa-reviewer. Copyright stays with the author.

QA Reviewer: Systematic Work Verification

Name: qa-reviewer
Author: shipshitdev

Purpose

Structured framework for reviewing AI agent work before finalizing changes. Catches bugs, verifies accuracy, ensures completeness, validates solutions match requirements.

When to Use

User says "check your work" or "review this"
After completing complex multi-step implementations
Before committing major refactors
When modifying commands or skills
After implementing new features
Proactively after any task >5 steps

QA Workflow Phases

1. Context Gathering

Review original task and requirements
List all deliverables (files created/modified/deleted)
Check critical rules in the applicable AGENTS.override.md / AGENTS.md chain and explicitly configured fallback files; include CLAUDE.md for Claude-specific rules

2. Requirement Verification

Create checklist of all requirements
Verify solution alignment
Check for edge cases

3. Accuracy Verification

Verify file paths exist
Confirm patterns match codebase
Cross-reference citations

4. Bug Detection

Check syntax (markdown, code, paths)
Look for logic errors
Verify project-specific rules

5. Completeness Audit

Reconcile todo list
Verify all mentioned files changed
Check for side effects

6. Optimization Review

Evaluate solution quality
Check pattern consistency
Consider alternatives

Quick Verification Commands

# Verify file exists
ls -la <file-path>

# Check balanced code blocks
grep -c '```' file.md

# Find violations
grep -r "console\.log" <files>
grep -r ": any" <files>

Project Rules Check

No console.log (use logger)
No any types
No inline interfaces
Applicable AGENTS files intact and scoped overrides intentional
Configured fallback instruction files exist and are nonempty
.agents/ folders untouched
Multi-tenancy preserved

Final Assessment Categories

Approve - Ready to commit
Conditional - Fix issues first
Reject - Significant problems

For complete workflow phases, output format template, common issue patterns, and advanced techniques, load ${CLAUDE_SKILL_DIR}/references/full-guide.md when performing a comprehensive QA pass or when the task has more than three deliverables.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/shipshitdev-skills-qa-reviewer/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

shipshitdev-skills-qa-reviewer.ocm.jsonjson

{
  "ocm": "1",
  "id": "shipshitdev-skills-qa-reviewer",
  "kind": "skill",
  "name": "qa-reviewer",
  "description": "Runs a structured multi-phase verification pass on completed AI agent work — catching bugs, missed requirements, and incorrect assumptions before changes are committed. Triggers on: \"check your work\", \"review this\", after complex multi-step implementations, before committing major refactors, or proactively after any task longer than five steps.",
  "publisher": "shipshitdev",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "quality-assurance",
      "verification",
      "code-review",
      "accuracy",
      "completeness",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Runs a structured multi-phase verification pass on completed AI agent work — catching bugs, missed requirements, and incorrect assumptions before changes are committed. Triggers on: \"check your work\", \"review this\", after complex multi-step implementations, before committing major refactors, or proactively after any task longer than five steps."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/shipshitdev/skills",
      "path": "skills/qa-reviewer/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/shipshitdev/skills/blob/HEAD/skills/qa-reviewer/SKILL.md",
      "key": "shipshitdev/skills/skills/qa-reviewer/SKILL.md"
    }
  },
  "instructions": "# QA Reviewer: Systematic Work Verification\n\n## Purpose\n\nStructured framework for reviewing AI agent work before finalizing changes. Catches bugs, verifies accuracy, ensures completeness, validates solutions match requirements.\n\n## When to Use\n\n- User says \"check your work\" or \"review this\"\n- After completing complex multi-step implementations\n- Before committing major refactors\n- When modifying commands or skills\n- After implementing new features\n- Proactively after any task >5 steps\n\n## QA Workflow Phases\n\n### 1. Context Gathering\n\n- Review original task and requirements\n- List all deliverab",
  "cost": {
    "context_tokens": 574
  }
}

Fetch it by URL: GET /api/v1/registry/shipshitdev-skills-qa-reviewer/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.