Provides parallel, multi-stage code reviews to find blind spots after implementation.

Install

mkdir -p .claude/skills/gated-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11499" && unzip -o skill.zip -d .claude/skills/gated-review && rm skill.zip

Installs to .claude/skills/gated-review

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.

Find blind spots that implementers miss through independent, layered verification. Use when the user has finished implementing a feature or fix and wants thorough verification before integrating. Make sure to use this skill whenever implementation is done, even if the user says 'it works, just push it.' DO NOT TRIGGER for: typo-only fixes, README/documentation-only changes, config file changes, formatting/linting commits, or dependency version bumps with no code changes.
475 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Dispatch `ironflow:spec-compliance-reviewer` subagent for spec compliance review
  • Dispatch `ironflow:code-quality-reviewer` subagent for code quality review
  • Dispatch `ironflow:reuse-reviewer` subagent for reuse and pattern review (large projects only)
  • Collect and merge findings from multiple reviewer subagents
  • Coordinate fixes with the implementer based on review findings
  • Gate progression between review phases

How it works

The orchestrator agent dispatches reviewer subagents in parallel for spec compliance, code quality, and reuse review. It collects their findings, coordinates fixes, and gates progression to serial verification stages like full regression and smoke tests.

Inputs & outputs

You give it
implemented feature or fix (changed files, spec path, summary)
You get back
verified code ready for integration or a list of issues requiring fixes

When to use gated-review

  • Reviewing feature implementation
  • Bug fix verification
  • Spec compliance check
  • Integration gatekeeping

About gated-review

Coordinates subagents to independently verify spec compliance, code quality, and testing regressions. Acts as a gatekeeper to ensure code meets standards before integration.

Find blind spots that implementers miss through independent, layered verification. Use when the user has finished implementing a feature or fix and wants thorough verification before integrating. Make sure to use this skill whenever implementation is done, even if the user says 'it works, just push

When not to use it

  • When the changes are typo-only fixes
  • When the changes are documentation-only (README)
  • When the changes are config file changes, formatting/linting commits, or dependency version bumps with no code changes

Limitations

  • The skill does not trigger for typo-only fixes, documentation-only changes, config file changes, formatting/linting commits, or dependency version bumps with no code changes.
  • Reuse and Pattern Review is only for large projects (monorepo, modular-packages, enterprise codebase).
  • The process involves two main phases: Parallel Code Review and Serial Verification.

How it compares

This skill uses independent, layered verification by multiple subagents to find blind spots, unlike a single manual review.

Compared to similar skills

gated-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gated-review (this skill)04moReviewAdvanced
python-testing-patterns772moReviewIntermediate
dependency-upgrade265moReviewIntermediate
test-cases577moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry