Use when the user asks for a periodic review of their GitHub activity, wants a summary of what they've been working on, asks "what have I done recently", "review my commits", "summarize my GitHub activity", or wants a cross-repository progress report. Also use when asked to review team activity, lab progress, or multi-repo development summaries. Defaults to 2-week window. Creates thematic report in scratch/.

Use when the user wants to add, edit, remove, reorder, or revalidate tenets in AGENTS.md, or manage tenet exceptions. Validates new and edited tenets against the codebase at add-time, surfaces evidence for the user to review, but never persists evidence to AGENTS.md. Use the governor-bootstrap skill instead when no tenets exist yet.

Document lessons, update rules/templates/docs. Use to capture learnings after review.

Score and filter solutions on feasibility, novelty, and deduplication. Produces reviewed_solutions.md as the single source of truth for downstream stages. Use when the user says "review solutions", "evaluate ideas", "filter solutions", or invokes /ideation:review.

Implement actionable items from a review - pick items by number, implement them, and mark them as resolved in the review document.

When the user wants to optimize internal linking, fix orphan pages, or improve link structure. Also use when the user mentions "internal links," "internal linking," "anchor text," "link equity," "internal linking strategy," or "orphan pages." For IA, use website-structure.

Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2). **Use when:** - The auditor integration tests assert PASS verdict on a canonical input **Triggers:** "known-good fixture", "auditor PASS smoke", "skill-auditor regression" **Not ideal for:** - Real-world use (this is a test fixture)

Guide users through targeted manual verification after code changes. Use when asked to "test this", "verify it works", "QA this", "walk me through testing", "smoke test", "sanity check", "regression test", "acceptance test", or after implementing a feature or bug fix that still needs human validation. Favor this skill for focused verification of the current change; use a broader exploratory-testing skill for open-ended bug hunting across an entire app.

Multi-model code review — dispatch, poll, and collect results from multiple AI model CLIs

This skill should be used when the user asks to "validate a plugin", "optimize plugin", "check plugin quality", "review plugin structure", or "run plugin optimizer".

Reference data for detecting the test platform (VSTest vs Microsoft.Testing.Platform) and test framework (MSTest, xUnit, NUnit, TUnit) from project files. DO NOT USE directly — loaded by run-tests, mtp-hot-reload, and migrate-vstest-to-mtp when they need detection logic.

Use this skill when updating the PolicyEngine skills source repo or the generated policyengine-claude wrapper — adding skills, fixing skill routing, updating years in code examples, reordering skills, or tuning skill descriptions. Triggers: "update plugin", "fix skill", "wrong skill loaded", "update year", "plugin maintenance", "skill routing", "skill description", "policyengine-claude plugin", "policyengine-skills".

MUST BE USED when user asks to: open a PR, create a PR, submit a PR, make a PR, prepare a PR, push changes for review. Prepares pull requests by analyzing branch changes, reviewing commits, creating the PR on GitHub, and ensuring compliance with project standards.

Review all unresolved PR review threads, address them by making necessary code changes, and commit the changes appropriately.

Use when setting up comprehensive QEMU debugging for Breenix - investigating interrupt handling bugs, debugging memory management issues, analyzing boot sequence problems, tracing hardware interactions, or inspecting CPU state during failures.

Systematic quality verification procedures for code review and delivery. Use when validating completed work, conducting code reviews, or ensuring production readiness.

Answer a question and preserve the Q→A for later review. Use when the user runs `/question <x>` (answer it, then save), or right after you give a substantive answer worth keeping to a question interjected mid-session ("why X over Y", "how does Y work", decisions, rationale, tradeoffs). Not for routine instructions you execute or quick status checks/acknowledgements ("ok", "thanks", "pushed yet?").

Use proactively when refactoring Ruby on Rails code. Applies Rails conventions, Sandi Metz rules, and idiomatic Ruby patterns while maintaining test coverage.

Use when receiving code review feedback, processing PR comments, or needing to evaluate suggestions before implementing - requires technical verification not blind agreement

This skill should be used when processing code review feedback, responding to reviewer comments, or when feedback seems unclear or technically questionable. Requires verification before implementing.

Safely identify and remove dead code with test verification at every step. Use when Codex needs to clean unused exports, files, dependencies, helpers, wrappers, re-exports, or duplicate code without risking regressions. Trigger for dead-code cleanup, unused dependency audits, stale utility removal, cleanup refactors, or requests to reduce code safely before or alongside maintenance work.

Systematic approach to safely refactoring code with tests. Use when user says 'refactor', 'clean up code', 'simplify', 'reduce complexity', or 'technical debt'.

Refactor code with safety checks and pattern application. Use when user says "refactor this code", "clean up this function", "simplify this logic", "extract this into a separate function", "apply the strategy pattern here", "reduce the complexity of this module", or "reorganize this file structure".

This skill should be used when the user asks to "reply to PR comments", "respond to review comments", "reply to PR

Resume implementing a plan - Claude picks up where you left off by reading the plan, latest review, and current branch state, then works through the next actionable items.

Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.

Interactive review of pending mistake reports from the learning loop. Walk through each report with the user, accepting/rejecting/discarding as appropriate.

Reviews PR comments from GitHub (Copilot, reviewers), evaluates against actual code, replies with reasoning, and resolves threads. Triggers on "review pr comments", "address pr feedback", "fix pr comments", or "review copilot suggestions".

Conversational session to review and assign delta priorities

Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.

Diagnose and fix semantic-release issues when a specific version is not being released. Use when semantic-release skips a version, fails to release, or when troubleshooting after git push --force, squashed commits, permission errors, or reference already exists.

Configure which review agents activate for this project during /review-pr

Read-only: extracts and tabulates order notes and custom attributes for ops review of gift messages and special instructions.

Read-only: lists orders by fraud risk level with indicator details for building a manual review queue.

Review changed code for reuse, quality, and efficiency, then fix issues found. Use when asked to "simplify", "review changes", "clean up my diff", or after completing a feature to polish before commit. Launches 3 parallel review agents covering code reuse, code quality, and efficiency.

Review skills for quality, size, progressive disclosure, and effectiveness. Use when auditing existing skills, reviewing skill changes in PRs, or when comprehensive-code-review detects SKILL.md files in a diff.

Refactors brittle snapshot tests into resilient, focused assertions. Provides strategies for reducing snapshot size, extracting meaningful assertions, and maintaining snapshots. Use for "snapshot testing", "snapshot refactoring", "brittle tests", or "assertion improvement".

Sprint retrospective — review what was planned vs. accomplished, capture lessons learned, identify what worked and what didn't. Use at the end of a sprint or after a deadline event (demo, release). Produces actionable takeaways for the next sprint.

Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. This skill should be used when the user says "review", "simplify", "code review", or wants a one-shot code review without persistent reviewers.

Filters and submits accumulated QA learnings as a GitHub issue (with optional PR) on the plugin repo. Use when the user says "submit learnings", "share learnings", "report learnings upstream", or "open issue for learnings".

Google Play Console submission requirements, testing tracks, and policy reference. Use when preparing Android apps for Play Store, understanding review timelines, or configuring in-app products.

Review and sync captured feedback to Product Forge

This skill should be used when the user reports a "bug", "not working", "fix this", "debug", "test failing", or when investigating unexpected behavior. Four-phase framework ensuring root cause understanding before attempting solutions.

Act as a wise, effective teacher who makes the user deeply understand the current coding session — the problem, the solution, and the broader context. Use when the user says "teach me", "make sure I understand this", "walk me through what we did", "/teach", or wants to internalize a change, bug fix, or feature before moving on.

Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.

Write and run tests for code

Test-driven development methodology (RED-GREEN-REFACTOR). Use when implementing features, fixing bugs, or changing behavior - write failing test first, then minimal code to pass.

Review test quality, coverage, and completeness. Analyzes for missing edge cases, assertion quality, and coverage gaps.

Branch, evaluate, prune, expand — structured search over solution space. Use for architecture with multi-step decisions, refactor planning, or complex debug hypothesis trees. Paper: Yao et al. 2023.

QA cycling workflow - test, verify, fix, repeat until goal met

QA an analysis before sharing -- methodology, accuracy, and bias checks

Active QA verification - full validation before completion

Captures human source verification for tracks, timestamps it, and updates track files. Use when sources need human review before generation.

Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.

Architecture documentation generation and maintenance for World Weaver

Complete workflow for conducting thorough code reviews with structured feedback

Execute and generate RSpec tests for Ruby projects with let bindings, before hooks, and mocking support

Manage Linux servers with user administration, process control, storage, and system maintenance.

Use when the user is addressing pull request review comments locally and asks for help evaluating, implementing, or drafting responses to reviewer feedback - requires technical rigor and verification, not performative agreement or blind implementation

Review project state, find gaps, assess change impact

Address review feedback on a PR (hv-managed or standalone) and update it — parallelizing across files with implementer subagents when the feedback spans 3+ independent files. Use after /hv:review-pr requests changes, or to act on human review comments and push the fixes back to the PR.

List all Architecture Decision Records with their status and summaries. Use when the user wants to see all decisions, review ADR history, or find a specific decision.

Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.

Interact with running Clojure REPLs via nREPL. Evaluate Clojure code, query namespaces, test functions, and debug live Clojure systems. Use when working with .clj/.cljc/.cljs files and a REPL is available.

Build high-signal PR context for review with diff analysis, risk assessment, and discussion questions

Review branch changes for test gaps, logic edge cases, failure modes, and integration risks

Use when requesting code review, receiving code review feedback, before merging, or when handling reviewer suggestions - covers both giving and receiving review

Use when receiving code review feedback, before implementing suggestions. Requires technical verification, not performative agreement or blind implementation.

Comprehensive code review and analysis. AUTO-TRIGGERS when user asks to review, refactor, debug, critique, or analyze code.

Use only when pr-review-resolver asks Codex to fix one selected PR review issue with bounded owned files. This resolver-managed worker edits code and reports validation results, but never updates PR review comments or .pr-review-cache state.

Create or update pull requests with conventional commits. Use when user says "create a PR for these changes", "submit this for review", "open a pull request", "push these changes and create a PR", "I'm ready to submit this work", or "create PR and link to issue

Coordinate a multi-repo refactor by fanning out subagents per repo, gathering changes onto a single feature branch named cook/refactor-<slug>-<short-sha>, and pushing for review. Pairs with the branch-guard PreToolUse hook to make pushes to main physically impossible.

Run Dart tooling workflows for static analysis, dependency conflict resolution, and test migration to package:checks. Use when fixing analyzer errors, resolving pub dependency conflicts, or modernizing test assertions.

Use this skill when debugging code with AI assistance. Activate when the user has a bug, error, unexpected behavior, needs to understand why code isn't working, wants to analyze stack traces, or is troubleshooting issues in their application.

Post-decision analysis - review outcomes against predictions, identify lessons, update patterns

View execute-mode session status — phase, plan_hash, drift, change_log, test results, 3-dimension verdict table, rollback log, discoveries

Discover project types, build commands, test commands, and language-specific guidelines for the current workspace. Use when the user says "what kind of project", "detect project", "build command", "test command", "project type", asks what language or framework the code uses, or wants to know how to build, test, or format the project. Also use early in any session before making changes.

Automatically discover software engineering practice skills when working with code review, documentation, pair programming, production debugging, performance profiling, deployment strategies, or software engineering practices. Activates for engineering development tasks.

Review existing Encore.ts code for best practices and common anti-patterns.

Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets. Trigger: Any commit creation, review, or branch cleanup.

Find and synthesize research papers, whitepapers, PDFs, technical reports, and academic sources with Firecrawl. Use when the user wants a literature review, paper summary, research landscape, or sourced synthesis from PDFs and scholarly/industry publications.

A test skill that responds to the magic word "flarglebargle" with a compliment. Use for testing skill activation and trigger functionality.

Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix

Safely upgrade a Ruby gem with changelog review, breaking changes analysis, bundle update, test run, and commit. Use when the user asks to upgrade, bump, or update a gem, or to review outdated gems.

Review and interactively address PR comments. Use when the user wants to review PR feedback, go through PR comments, or address reviewer requests on a pull request.

Automatically creates comprehensive pull requests to the dev branch when user indicates their feature/fix is complete and ready for review. Use when user mentions creating PR, submitting for review, or indicates work is done. Examples - "create a PR", "ready for review", "open a pull request", "submit this to dev", "all tests passing, let's get this reviewed".

Use when reviewing Go code or preparing code for review. Quick-reference checklist covering naming, error handling, concurrency, testing, imports, documentation, and common pitfalls. Based on Go Wiki CodeReviewComments.

Start the workday: review yesterday, create today's daily memory, load tasks, prepare agenda. Use when beginning the day.

Default entry point for fixclaude. Detects whether CLAUDE.md exists in the current project and routes to the appropriate subcommand: init (create new) or update (augment existing). Handles symlinks transparently. Use when the user says "fixclaude", "fix claude", "install fixclaude", or "install claude fixes".

List QA test procedures with status and priority

Use when "literature review", "research synthesis", "systematic review", "academic search", or asking about "find papers", "cite sources", "research gaps", "meta-analysis", "bibliography"

Merge the current feature branch into main and (optionally) clean up the branch and worktree. Prefers fast-forward (--ff-only) for linear history; falls back to a merge commit (--no-ff) when the branch has diverged or the user wants the merge commit preserved. Interactive cleanup at the end. USE WHEN asked to "merge to main", "merge and cleanup", "integrate the feature branch", or "finish this branch" — i.e. a direct local merge with no review gate. For PR-based delivery (push → open a PR → link a work item → clean up after merge), use the `ship` skill instead.

Review and analyze product metrics with trend analysis and actionable insights

Patterns for debugging mobile-specific issues on iOS Safari and Android Chrome. Use this skill when encountering viewport, keyboard, or touch-related bugs that only reproduce on real mobile devices. Don't use for general debugging (use /playbook:debug instead), or for desktop browser issues.

Use when bootstrapping documentation for a repository for the first time — generates AGENTS.md, CLAUDE.md, README.md, and docs/*.md from codebase analysis using staged exploration, user review, and generation. Supports --auto to skip review.

Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. Use when multiple previous fix attempts have failed repeatedly, when dealing with intricate system interactions, or when a methodical root cause analysis is needed. Do not use for simple troubleshooting. Triggers after multiple failed debugging attempts on the same complex issue.