Use after plan is written to validate implementation plans across completeness, quality, feasibility, and scope dimensions - spawns specialized validators for failed dimensions and refines plan interactively before execution

Write human-readable test criteria for requirements. No code, no pseudocode — only observable outcomes. Iterator-native, succinct, imperative mood.

Run comprehensive PR checks including reviewing CodeRabbit comments, ensuring PR description quality, running pre-commit hooks, tests, and validation. Use on an existing PR to address review feedback.

This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns

Use when generating a Product Requirements Document from a high-level idea, feature request, or product vision — covers discovery questions, structured PRD drafting, section-by-section review, and transition to implementation planning

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.

Evaluate captured screenshots for layout issues, masked elements, and rendering problems. Use after taking screenshots to validate visual correctness and automatically resize viewport if elements are unexpectedly clipped.

Orchestrate the full R publication pipeline: CRAN submission for distribution, JOSS paper for DOI and peer review, optionally a JSS methods paper. Coordinates audits, drafting, and review cycles.

This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings.

Analyze code for SOLID violations and suggest targeted improvements

Refactor existing AGENTS.md to follow progressive disclosure principles

Use when analyzing and refactoring multiple skills across a project. Use when user says "refactor skills", "cleanup skills", "consolidate skills", "skill review". Use when skills overlap, are redundant, or need cross-skill consolidation. NOT for improving a single skill (use improving-skills instead).

Retrieve code diff from a local git commit. Use this as the first step in a code review pipeline when reviewing local commits.

Synthesizes accumulated QA learnings from .qa-learnings/ledger.md into prioritized, actionable plugin improvements. Use when the user says "review learnings", "what have we learned", "improve the plugin", "learnings report", or "synthesize QA feedback".

Review implementation plans for completeness and feasibility. Use when user says "review this plan before I start", "is this implementation plan complete", "check if this plan aligns with our patterns", "give me feedback on my implementation strategy", or "validate this plan before we execute it".

Code review checkpoint using codex review CLI. Returns structured result with pass/fail status and issues. Use when: 'code review', 'review changes', 'codex review', 'check my code'.

Address PR review feedback and request re-review. Use this when the user needs to handle PR comments, respond to code review, or iterate on feedback from reviewers.

Ship a feature branch: prepare a clean PR (strip working files with intelligent suggestions), create/update the GitHub PR, then merge to main with GPG signing when ready. Detects lifecycle stage automatically. Use when: "ship", "prep pr", "create pr", "open pr", "merge to main", "submit for review", "push for review", "ship this branch".

Build features with tests-before-code rigor — use for new features needing test coverage

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

Guides through the complete TDD workflow with Red-Green-Refactor cycle

Identify hidden assumptions about users in code that could exclude or harm. A focused analysis asking "What am I assuming about the person using this?"

Surface test-suite debt — skipped tests, untested public APIs, flaky patterns (retries, sleeps), missing edge cases. Pattern-based static analysis; does not run coverage tools. Use when tests feel unreliable or before a release.

Update Graphite PR stacks by addressing review comments and syncing PRs. Use when user says "update my graphite stack", "address the review comments on my stack", "sync my PR stack after these changes", "submit my entire stack to Graphite", or "I need to update all the PRs in my stack".

Use at the start of every session before any response or action. Also invoke whenever uncertain which gambit skill applies, when about to implement / debug / refactor / test / plan / brainstorm, or when a user request could match any gambit skill even at 1% probability.

Diagnose and fix Webflow CLI issues including installation problems, authentication failures, build errors, and bundle problems. Uses CLI diagnostic flags (--version, --help, --verbose, --debug-bundler) for troubleshooting.

Execute and generate xUnit tests for C#/.NET projects with FluentAssertions and Moq support

This skill should be used when the user asks to "run matrix diagnostics", "check matrix health", "fix matrix issues", "troubleshoot matrix", or mentions matrix not working. Runs comprehensive diagnostics on the Matrix plugin and automatically fixes issues.

Use when reviewing code or PRs in the llama-stack repository (llamastack/llama-stack on GitHub). Provides specialized knowledge about Llama Stack's architecture, testing patterns (recordings folders), backward compatibility requirements, distributed system considerations, and code review focus areas specific to this project.

Fetch GitHub PR review feedback, judge each comment, implement valid fixes, verify, and optionally reply.

Stress-test solutions using the STRIKE framework. Systematically attack proposals to find weaknesses before deployment.

Use this skill when reviewing AI-generated code. Activate when the user has code generated by an AI assistant and wants to review it, validate AI output, check for common AI mistakes, ensure code quality of generated code, or verify that AI-generated code follows best practices before merging.

Minimal smoke test for OpenClaw setup skill. Validate official channel discovery workflow, DingTalk/Feishu integrations, Discord token configuration, and gateway health checks with non-destructive commands.

Validate App Store submission readiness, submit prepared versions, and monitor review status with current asc commands. Use when shipping or troubleshooting review submissions.

Validate App Store submission readiness, submit prepared versions, and monitor review status with current asc commands. Use when shipping or troubleshooting review submissions.

Ban `as` type assertions in a package via the `@typescript-eslint/consistent-type-assertions` lint rule, replacing them with compiler-verified type-safe alternatives. Use when enabling the assertion ban in a new package or fixing violations in an existing one.

Deep post-fix bug analysis across five dimensions: root cause categorization, fix failure analysis, prevention mechanisms, systematic expansion, and knowledge capture. Updates .trellis/spec/ guides with lessons learned to prevent recurring bugs. Use when a debugging session completes, after fixing a tricky bug, when the same class of bug keeps recurring, or when you want to capture debugging insights into project documentation.

Fix build, lint, and type errors

Build a personalized PR review skill by mining GitHub review history. Extracts review patterns, communication style, priorities, and blind spots — generates a calibrated review-as-me skill that posts inline comments on PRs. Use for onboarding, cloning review style, or creating a reviewer persona.

This skill should be used when the user asks to "clean up the code", "cleanup", "do a cleanup pass", "review and fix code quality", "scan and fix tech debt", "simplify and refactor", "simplify recent changes", "code quality sweep", "tidy up", "refactor this", "refactor pass", "simplification pass", "dead code removal", "reduce complexity", "code review pass", or wants a combined scan-fix-verify workflow that finds issues, fixes safe ones, and reports the rest.

Prepare branch for code review by building context, identifying issues, and suggesting improvements

Validate code quality using certainty-graded rules. Detect AI artifacts, anti-patterns, and b00t violations. Reports auto-fixable vs review-required findings.

Review code changes with parallel detection agents and smart fixing

Generic code review that auto-detects tech stack and delegates to appropriate framework-specific orchestrator

Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing

Use when test coverage has dropped and you need to find which changes caused it and what tests to add. Traces coverage regressions to specific commits and files.

Guidelines for handling long lines in Dart code to adhere to the 80-column rule. The `lines_longer_than_80_chars` lint.

Structured debugging session — reproduce, isolate, diagnose, and fix

Debug errors, test failures, or unexpected behavior. Auto-detects project type.

Diagnose ClaudeMemory installation and configuration issues. Use when memory tools fail or setup seems broken.

Read open review comments and resolve them by making code fixes

Automatically discover testing skills when working with unit testing, integration testing, e2e testing, TDD, test coverage, mocking, pytest, Jest, or test automation. Activates for testing development tasks.

Adding test infrastructure to a .NET project. Scaffolds xUnit project, coverlet, layout.

Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses needing legal review. Use when creating confidentiality agreements or preparing an NDA for a partnership.

This skill should be used when the user asks to "add a database table", "create a new context", "query the database", "add a field to a schema", "validate form input", "fix N+1 queries", "preload this association", "separate these concerns", or mentions Repo, changesets, migrations, Ecto.Multi, has_many, belongs_to, transactions, query composition, or how contexts should talk to each other.

This skill should be used when the user asks to "add a database table", "create a new context", "query the database", "add a field to a schema", "validate form input", "fix N+1 queries", "preload this association", "separate these concerns", or mentions Repo, changesets, migrations, Ecto.Multi, has_many, belongs_to, transactions, query composition, or how contexts should talk to each other.

You must use this when identifying ethical risks, ensuring participant privacy, or preparing IRB applications.

Apply feedback and implement review suggestions. Incorporates reviewer comments into code changes systematically.

QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.

Post-documentation decision menu for fix-reporter. Routes to critical patterns, skill updates, cross-references, or discovery enablement.

Systematically fix all failing tests after business logic changes or refactoring

Knowledge about Flutter/Dart code formatting, analysis tools (flutter analyze, dart fix, dart format), and when to apply them. Use when formatting code, fixing lint issues, running code cleanup, or when user mentions format, analyze, lint, or cleanup in Flutter context.

Generate integration tests for multi-DocType workflows in Frappe. Use when testing end-to-end workflows, state transitions, or complex business processes.

Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).

Validate GenLayer intelligent contracts with the GenVM linter.

Create a pull request from the current branch. Use when the user wants to open a PR, create a pull request, or push their branch up for review.

GitHub patterns using gh CLI for pull requests, stacked PRs, code review, branching strategies, and repository automation. Use when working with GitHub PRs, merging strategies, or repository management tasks.

Automate Pull Request creation with proper titles, descriptions, labels, and quality checks using the GitHub CLI. Use when preparing code for review and merge.

Corriger une issue GitHub avec workflow simplifié et efficace

Review monitoring, filtering, and automated responses for Google Play. Use when managing user reviews and feedback.

Systematic debugging with persistent state across context resets

Phase 6: Serve via python3 -m http.server 8899, screenshot light mode (fullPage), screenshot dark mode via browser_screenshot colorScheme:dark, compare 3 declared elements [expected vs present], fix gaps with modify_frontend (max 2 cycles), report.

Use when performing a holistic code review of an implementation - routes to codex:rescue or falls back to a direct subagent

Probe IoT/embedded targets for exposed SWD/JTAG debug interfaces using a SEGGER J-Link. Detects whether debug is OPEN, LOCKED (readout-protected), or DEAD (fused off). Use when assessing whether a target's on-chip debug port can be reached, identifying the silicon vendor from DPIDR/IDCODE, and confirming halt+memory access for full debugger control.

Update fx-cc plugin skills based on conversation learnings. Use when the user says "use /learn to...", "learn to...", "remember to...", "don't do X again", or when a skill misbehaved and needs correction. This skill modifies plugin source files but does NOT commit changes - they require manual review before committing.

Save a reusable pattern from this session to the knowledge base. Use for /learn, "remember this", "save this pattern". NOT for session state (/save-session) or full session review (/introspect).

Test understanding of recently written or accepted code

You must use this when synthesizing existing knowledge, identifying research gaps, or tracing the evolution of scientific ideas.

Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI. Use when creating or maintaining LSUIElement menubar utilities, defining Tuist targets/manifests, implementing model-client-store-view architecture, adding script-based launch flows, or validating reliable local build/run behavior without Xcode-first workflows.

Identify underserved market gaps and unmet customer needs in e-commerce. Analyzes competitor blind spots, review pain points, search demand without adequate supply, and emerging customer segments.

You must use this when critiquing academic manuscripts, evaluating methodological rigor, or providing structured reviewer feedback.

Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks

PolicyEngine code review patterns - validation checklist, common issues, review standards

Polish code changes by recovering context, checking against codebase guidelines, removing AI slop, and running review. Use when finalizing work on a branch before PR.

Creates comprehensive post-incident documents with timeline, root cause analysis, contributing factors, action items, and ownership. Follows SRE best practices for blameless postmortems. Use for "postmortem", "incident review", "RCA", or "post-incident".

Create a GitHub pull request — pushes the current branch and opens a PR with auto-generated title and description. Use for any PR creation, branch submission, or code review request.

Load PR comments and feedback for code review. Use when the user wants to see reviewer feedback, check for unresolved comments, understand what changes are requested, or review discussion on a PR.

Create a new pull request. Use when the user wants to open a PR, submit code for review, create a draft PR, or push changes for merge.

Use when the user asks to review a PR description, check if a PR description matches the implementation, verify PR accuracy, or says things like "review PR description", "does my PR description match the code", "check PR accuracy", "is my PR description correct", or "description review".

List pull requests from the repository. Use when the user wants to see open PRs, find PRs to review, check their own PRs, or browse PR history.

Push a branch, create a PR, iterate on reviews until clean, then squash-merge. Runs /pr-review-fixer in a loop until no blockers/critical/major issues remain, rebases onto latest origin/main, and squash-merges. Works with or without Transit tickets. Use when you want to shepherd a PR from push to merge, e.g. "push and merge this", "get this PR merged", "review-fix-merge loop".

Review PRs against the Intent Layer. Use for reviewing AI-generated PRs or having AI review human PRs. Provides risk scoring, checklists, and contract verification.

Bulk resolve unresolved PR review threads. Useful after manually addressing threads or after using /pr-threads-address.

Test pricing strategies with synthetic data. Use when: simulating willingness to pay, price sensitivity, or optimal price points.

Review PII handling, encryption, and GDPR/CCPA compliance in Rails applications.