Use during scam detection to recognize Berlin rental fraud patterns. Reference before classifying any listing as ok, review, or block.

Use when adding a new capability to an existing project. Smaller than build (no full spec) but bigger than fix. Incremental, behind a feature flag where appropriate, with rollback path.

Review staged + unstaged changes and split them into one commit per logical change. Use whenever the user says "atomic commit", "commit my changes", "split this into commits", or has multiple unrelated edits sitting in the working tree — even if they don't say "atomic". Runs repo-native type-checker and linter before each commit and refuses to bundle unrelated changes.

Use to auto-resolve build errors. Reads compiler/linker/bundler output, classifies, suggests minimal-diff fixes. Different from /heal (which is multi-strategy retry across build/test/lint).

Use tmux to run and test our interactive CLI/TUI end-to-end. Includes how to start, send keys, capture output, and cleanly stop (double Ctrl+C).

Provides automated, context-aware code reviews focusing on logic errors and style violations. Use during Pull Request cycles to identify potential bugs and maintain high code quality standards.

macOS-only Dayflow review for a local Dayflow SQLite database at `~/Library/Application Support/Dayflow/chunks.sqlite`. Generate daily or weekly summaries, productivity insights, and timeline reports. Use when reviewing local Dayflow time usage or trends.

Clean up AI-generated slop from code changes. Use when the user says "deslop", "clean up code", "remove slop", "review for AI artifacts", "check for anti-patterns in diff", or before committing to ensure code quality. Also activates when reviewing staged changes or preparing a commit.

Monitor and debug Eve jobs with CLI follow, logs, wait, and diagnose commands. Use when work is stuck, failing, or you need fast status.

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

Execute implementation plans one commit at a time. Follow the order from brainstorm, implement, test REAL, commit.

Use when the user reports a bug, says "fix X", "X is broken", "X doesn't work". Bounded-scope, root-cause-first. Adds a regression test before declaring done. Refuses to expand into refactor.

Fix GitHub issues using gh CLI. Use when asked to fix, resolve, or address a GitHub issue. Creates fixes on separate branches, runs tests locally, and creates PRs when tests pass. Requires gh CLI authenticated and repo cloned locally.

Fix animation performance issues.

# Go Test Fixer Skill

Use when build/test/lint/typecheck is failing and the user wants automatic recovery. Self-healing loop — retries with DIFFERENT strategies, not the same one twice. Bounded retry count.

Delivers changes in thin vertical slices. Use when implementing any feature or refactor that touches more than one file or feels too large to land safely in one pass.

Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

Launch ephemeral debug container in running pod for interactive debugging. Use when you need to debug a pod without restarting it.

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

# Peer Review

Quality gate checklist to run before committing or creating a PR. Use when finishing implementation, checking work quality, or preparing to commit. Triggered by "preflight", "self review", "ready to commit", "check my work", "quality gate".

Create or update a pull request for the current branch in the tldraw repository. Use when the user invokes pr, asks to create a PR, update an existing PR, push current branch changes for review, or prepare a pull request.

MUST BE USED when user asks to: review code, review PR, check my code, look at my changes, review changes. Reviews pull requests and code changes, evaluating quality and providing actionable feedback.

Prioritize assumptions using an Impact × Risk matrix and suggest experiments for each. Use when triaging a list of assumptions, deciding what to test first, or applying the assumption prioritization canvas.

Analyze and optimize pytest suites to improve speed, identify flaky tests, and increase coverage. Use to maintain high-quality, fast-running test pipelines.

<!-- plugin/skills/qa-hardening/SKILL.md -->

Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.

Use for refactoring — same behaviour, better structure. Test-coverage gate enforced. Extract-then-rename ordering. Refuses to mix in feature changes or bug fixes.

Build, test, and explain regular expressions against sample text or files using CLI tools (rg, python) and specific regex flavors. Use when asked to craft, debug, or validate regexes or search patterns.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Resolve code review comments by verifying validity, then proposing multiple architectural solutions (not naive fixes) for confirmed issues. Use when addressing review feedback or analyzing comment validity.

This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".

OCaml Result type patterns using OCaml 5.x stdlib. Use when Claude needs to: (1) Handle errors with Result types, (2) Chain Result operations with let*, (3) Extract values from Ok/Error, (4) Refactor code using local let* bindings to use Result.Syntax

Execute AL test codeunits. Use al-runner for fast pure-logic tests (no BC required). Use bc-test for full integration tests against a running BC instance.

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

Review changed code for reuse, quality, and efficiency, then fix any issues found.

Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.

Use when the user invokes TDD discipline, says "write test first", "test-driven", "/tdd". Strict red-green-refactor. Refuses to write production code before a failing test exists.

Test automation strategies and best practices

Generates dbt tests including schema tests, data quality tests, and freshness checks. Use when adding tests to dbt models or implementing data quality validation.

Test planning and strategy patterns

Use when adding or modifying non-trivial code - requires happy-path AND sad-path tests covering every return permutation, blocks declaring "done" if production code grew without matching test additions.

Clean and reorganize transcript .txt files for clearer English grammar, punctuation, and paragraph flow. Use when asked to fix line breaks, merge fragments into sentences, normalize punctuation, or produce a reflowed transcript saved as a new file.

Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.

Use when planning Rails features or breaking down work into PRs - enforces 2-5 file PRs, bug fix separation, and one-sentence scope test

# Code Reviewer

Review and simplify code to reduce complexity and improve maintainability

Use for code review and quality feedback from Codex. Triggers on "codex review code", "codex code review", "have codex review this", "get codex feedback on code".

Use for systematic debugging and root cause analysis with Codex. Triggers on "codex debug", "codex root cause", "have codex investigate this bug", "codex find the issue".

Debugs code issues by analyzing errors, tracing execution flow, identifying root causes, and suggesting fixes. Use when the user says "this isn't working", "I'm getting an error", "why is this broken?", or pastes an error message.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Final quality review producing a human-readable report

Use when checking what PRs are waiting for your review, or when starting your day to see what needs attention

Create and run a Crabshell I investigation document from Codex. Use for evidence-heavy research that needs multiple source types, cross-review, and documented conclusions; not for quick questions.

Activate when user mentions "codex review", "code review", "fix pr code review". This skill provides guidance on how to effectively collaborate with codex to do a interate code review.

Analyze counterparty contract changes against agreement/schedules, flag conflicts, and produce severity-rated counterpositions.

# Literature Review

End of day memory maintenance. Runs distillation, updates state files, prunes stale info. Runs in background with no user interaction.

End of day memory maintenance. Runs distillation, updates state files, prunes stale info. Runs in background with no user interaction.

Auto-assembles review panel using deterministic rules, dispatches agents against plan file, collects verdicts.

Decide which automated review comments to fix vs skip. Use after receiving feedback from hooks, GitHub bots, or review agents.

Analyze and improve business processes. Trigger with "this process is slow", "how can we improve", "streamline this workflow", "too many steps", "bottleneck", or when the user describes an inefficient process they want to fix.

Use when the user finishes a code change and wants format / lint / type-check / tests run together, or asks "is this clean?" / "any issues?". On-demand replacement for prior chained quality gates.

Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.

Automated code refactoring suggestions and implementation.

Review recent conversations to find improvements for CLAUDE.md files.

This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR

Analyze code for simplification opportunities. Use when user says "simplify", "reduce complexity", "clean up code", "remove duplication", "too complicated", or wants to reduce technical debt.

Generate unit tests from source files using AI. Use when adding test coverage.

Run test suite and return structured pass/fail results. Supports scoped runs by directory, file, or test name pattern. Triggers on run tests, execute tests, test results, check tests, verify tests pass.

A test skill with resources

Scan open pull requests, assess risk and complexity, and build a prioritized review queue. Used by digital twin personas to reduce PR review cognitive load.

Evaluate, compare, and manage vendor relationships. Trigger with "evaluate this vendor", "compare vendors", "vendor review", "should we renew", "RFP", or when the user is making procurement or vendor decisions.

Activates after code changes to suggest or run verification steps. Provides test-after-action patterns for different file types and frameworks.

Review the past week's activity and suggest a prioritised plan for the coming week

End-to-end structured workflow test - exercises every stage from INTENT through BUILD, then cleans up

Use when the user says "yeet" or "/yeet" to quickly stage, review, commit, and push all changes with a provided message

Create accessibility testing plans covering assistive technologies and WCAG criteria.

Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.

Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.

Autonomous maintenance orchestrator that continuously finds and dispatches work

Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something

# Browser QA — Automated Visual Testing & Interaction

Interactive review and promotion of high-confidence memories to CLAUDE.md

Review code against project rules. Use when reviewing code quality or ensuring compliance with conventions.

Use this skill after completing multiple, complex software development tasks before informing the user that work is complete.

Structured deal assessment using MEDDIC, BANT. Risk scoring, required evidence by stage, red flag detection, coaching points.

Full debugging workflow — reproduce the bug with a failing test, perform root cause analysis, then implement a minimal fix.