Loading...
Loading...
Found 1,194 Skills
Use when implementing any code in RLM Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first.
Provides reflective questioning framework to challenge assumptions about work completeness, catching incomplete implementations before they're marked "done". Use before claiming features complete, before moving ADRs to completed status, during self-review, or when declaring work finished. Triggers on "is this really done", "self-review my work", "challenge my assumptions", "verify completeness", or proactively before marking tasks complete. Works with any type of implementation work. Enforces critical thinking about integration, testing, and execution proof.
Guides strict Test-Driven Development (TDD) using the Red-Green-Refactor cycle. Ensures no production code is written without a prior failing test. Use this skill when implementing new features, fixing bugs, or refactoring code to ensure high test coverage and design quality. Triggers on phrases like 'TDD', 'write tests first', 'test-driven', 'red-green-refactor', 'watch it fail', 'test first', or 'behavior driven'.
Autonomous mobile dev subagent that implements a single user story from a PRD for Expo / React Native apps. Use when you need parallel, independent mobile implementation tasks — screens, native components, data fetching, navigation. Designed to run alongside other ralph-mobile instances. Receives a specific task ID and PRD path. Returns a structured completion signal. Does NOT commit or modify the PRD — those are handled by the documenter. Loads expo, building-native-ui, vercel-react-native-skills, native-data-fetching, and expo-dev-client skills automatically.
Generate production-ready REVIEW.md and AGENTS.md files for Devin Review's AI code review system. Use this skill whenever the user mentions Devin Review, REVIEW.md, Devin code review setup, PR review instructions for Devin, AI code review configuration for Devin, or wants to create instruction files that Devin's Bug Catcher uses. Also trigger when someone says "set up Devin review", "configure Devin for our repo", "create review rules for Devin", or asks about REVIEW.md / AGENTS.md — even if they don't say "Devin" explicitly but describe wanting AI-powered PR review instructions that work with Devin's auto-review or Bug Catcher.
AI-powered code review via the OpenAI Codex CLI. This skill should be used when reviewing branch diffs before merging a PR, auditing uncommitted changes during development, inspecting a specific commit, performing custom-scoped reviews, or whenever changes touch security-sensitive paths or exhibit risky patterns.
Diagnoses what makes code complex and why, using the three-symptom two-root-cause framework. Use when code feels harder to work with than it should but the specific problem is unclear. This skill identifies WHETHER complexity exists and WHERE it comes from. Not for scanning a checklist of known design smells (use red-flags) or evaluating a specific module's depth (use deep-modules).
Orchestrates a structured design review by running existing skills in a diagnostic funnel, from complexity triage through structural, interface, and surface checks to a full red-flags sweep. Use when reviewing a file, module or PR for overall design quality and you want a comprehensive, prioritized assessment rather than a single-lens check. Not for applying one specific lens (use that skill directly) or for evolutionary analysis of how code changed over time (use code-evolution).
Refactor overly large code units into smaller, more focused components. Use when code has grown too large or complex.
Copilot agent that assists with bug investigation, root cause analysis, and fix generation for efficient debugging and issue resolution Trigger terms: bug fix, debug, troubleshoot, root cause analysis, error investigation, fix bug, resolve issue, error analysis, stack trace Use when: User requests involve bug hunter tasks.
Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing.
This skill should be used when the user asks to "remove AI slop", "clean up AI code", "remove AI patterns", "fix AI-generated code", "clean up PR", "remove unnecessary comments", "fix defensive checks", or mentions AI slop, AI code cleanup, or code quality issues from AI-assisted development. Identifies and removes unnecessary comments, defensive checks, type casts to any, and style inconsistencies.