A multi-agent quality gate that performs automated parallel reviews for simplification, consistency, and robustness.

Install

mkdir -p .claude/skills/qc && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11868" && unzip -o skill.zip -d .claude/skills/qc && rm skill.zip

Installs to .claude/skills/qc

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Quality gate. 5 parallel agents review changes. All must pass.
62 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Review code for descriptive naming and error handling
  • Identify overcomplicated logic and reduce indirection
  • Check consistency with existing codebase patterns
  • Assess reliable for edge cases and regression risk
  • Evaluate changes for task relevance and unnecessary refactoring

How it works

Five parallel agents review code changes based on specific criteria, and all agents must pass for the changes to be approved.

Inputs & outputs

You give it
Code changes (DIFF), file names (FILES), and task description (TASK)
You get back
JSON output from 5 parallel agents indicating pass/fail and issues

When to use qc

  • Validate code before merging
  • Review changes for consistency
  • Check for over-complicated logic
  • Verify edge case handling

About this skill

QC Gate

Setup

DIFF=$(git diff main)
FILES=$(git diff main --name-only)
TASK="{task description or 'general changes'}"

Read 1-2 unmodified files from same directories for pattern context.

Agents

Spawn all 5 in parallel. All output raw JSON only, no markdown.

1: Code Review (sonnet)

DIFF: ${DIFF}

- Descriptive naming?
- Errors caught with useful messages?
- No hardcoded values, commented code, debug statements?
- No TODO without ticket ref?
- No obvious bugs?
- No useless comments?

{"pass": bool, "issues": [...]}

2: Simplification (sonnet)

DIFF: ${DIFF}

- Is this overcomplicated? Can I solve the same problem in a simpler manner?
- Can I reduce indirection?
- Can I reduce surface area?
- Premature abstraction? Premature Optimization? YAGNI violations?
- Dead code?
- Three similar lines > one abstraction

{"pass": bool, "issues": [...]}

3: Consistency (sonnet)

DIFF: ${DIFF}
PATTERNS: ${PATTERN_FILES}

- Matches existing codebase patterns?
- Proper types, no any, no unsafe casts?
- Idiomatic error handling?
- Changes internally consistent?
- Is logic isolated and composable?
- Are there existing tests if neccesary?

{"pass": bool, "issues": [...]}

4: Robustness (sonnet)

TASK: ${TASK}
DIFF: ${DIFF}

- Actually solves the problem?
- Edge cases: empty, null, zero, negative, boundaries, concurrency?
- Regression risk: changed signatures, shared state, removed exports?
- Maintains API contracts?

{"pass": bool, "issues": [...]}

5: Scope (haiku)

TASK: ${TASK}
FILES: ${FILES}
DIFF: ${DIFF}

- Solved the problem or just the symptom?
- Changes unrelated to task?
- Unnecessary refactoring?

{"pass": bool, "issues": [...]}

Results

CheckVerdictIssues
Code Review✓/✗...
Simplification✓/✗...
Consistency✓/✗...
Robustness✓/✗...
Scope✓/✗...

ALL PASS: Ready to commit.

ANY FAIL: List issues, fix them, run /qc again.

Same issue 3x: Escalate to user.

Notes

  • Invalid JSON? Retry once. Still broken? Mark fail.
  • Large diffs (>500 lines): run simplification file-by-file.

When not to use it

  • When a single agent review is sufficient
  • When large diffs require file-by-file simplification outside the scope of this skill
  • When an agent produces invalid JSON output repeatedly

Limitations

  • All 5 agents must pass for approval.
  • Invalid JSON output from an agent results in a retry, then a fail.
  • Large diffs (>500 lines) may require simplification file-by-file.

How it compares

This skill automates a multi-faceted code review process with parallel agents, providing a structured and complete quality gate compared to a single manual review.

Compared to similar skills

qc side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
qc (this skill)06moReviewIntermediate
verification-before-completion910moNo flagsBeginner
mutation-testing55moReviewAdvanced
workflow-patterns12moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry