The definitive guide & configuration system for GitHub Copilot CLI — agents, skills, rules, multi-AI orchestration, and more
Skill Claude CodeCodex
Use when you want to create a new SKILL.md file — describe a workflow and this skill generates a properly structured, frontmatter-complete SKILL.md that follows this repository's conventions.
Skill Claude CodeCodex
Use when implementing framework-specific or library-specific code — verify non-trivial APIs against official documentation before writing them, and record the source in task notes, docs, or the PR.
Skill Claude CodeCodex
Use before starting any non-trivial feature to write a technical spec first — prevents misaligned implementation and scope creep.
Skill Claude CodeCodex
Use when a bug is non-obvious or has resisted quick fixes — applies a 4-phase root cause analysis to find and permanently resolve the issue rather than patching symptoms.
Skill Claude CodeCodex
Use when starting a new feature or function to write failing tests first, then implement the minimal code to pass (Red→Green→Refactor).
Skill Claude CodeCodex
Use when you are lost in local code details — step one abstraction level up, map the owning modules and callers, and restate the system in project vocabulary.
Skill Claude CodeCodex
Use when you've shipped a feature, fix, or breaking change and need to update CHANGELOG.md — follows Keep a Changelog format and syncs version numbers across package manifests.
Skill Claude CodeCodex
Use when source code has changed and API docs are stale, or a new endpoint lacks documentation — generates accurate docs from implementation, not guesswork.
Skill Claude CodeCodex
Use when making significant, hard-to-reverse technical decisions to document context, rationale, and consequences as Architecture Decision Records (ADRs).
Skill Claude CodeCodex
Use when a user asks for a code tour, onboarding walkthrough, architecture tour, or PR tour — creates persona-targeted, step-by-step .tour files with real file and line anchors.
Skill Claude CodeCodex
Use when code has changed and documentation may be out of date — identifies stale docs, finds gaps between implementation and docs, and applies targeted updates.
Skill Claude CodeCodex
Use when a feature, module, or whole project needs missing documentation created from scratch - read the codebase, map the public surface with Diataxis (tutorial/how-to/reference/explanation), and generate the missing docs with cross-links.
Skill Claude CodeCodex
Use when you're ready to define a feature before building it — generates a structured PRD using Jobs-to-be-Done thinking, success metrics, and explicit scope boundaries.
Skill Claude CodeCodex
Use when you have a backlog of features and need to rank them for the next sprint — scores each feature using Impact × Confidence × Effort matrix with SQL tracking for transparent prioritization.
Skill Claude CodeCodex
Use when you're preparing to launch a product or feature publicly — builds a structured checklist covering positioning, distribution, messaging, and success metrics from private beta to GA.
Skill Claude CodeCodex
Use when you need to ensure every feature in the backlog connects to a measurable business outcome — applies Teresa Torres' OST framework to map outcomes → opportunities → solutions → experiments.
Skill Claude CodeCodex
Use when engineering needs testable, implementable technical requirements — not a PRD but a capability spec with acceptance criteria, task breakdown, and traceability from requirement to implementation ticket.
Skill Claude CodeCodex
Use when designing or reviewing an AI agent system that needs policy-based access controls, intent classification, tool-level rate limiting, trust scoring for multi-agent workflows, or append-only audit trails.
Skill Claude CodeCodex
Use when auditing an AI agent system against the OWASP Agentic Security Initiative Top 10 — checks tool access, prompt boundaries, memory handling, and operational safeguards across the agent pipeline.
Skill Claude CodeCodex
Use when auditing an AI agent plugin, skill bundle, or MCP tool package for supply chain integrity — generate deterministic SHA-256 manifests, detect modified or untracked files, flag unpinned dependencies, and gate promotion to production.
Skill Claude CodeCodex
Use when you need a comprehensive health scorecard of a codebase — scores security, code quality, test coverage, documentation, and AI agent governance across 7 dimensions with a prioritized remediation plan.
Skill Claude CodeCodex
Use when reviewing GitHub Actions workflows for exploitable vulnerabilities — finds pwn-request patterns, expression injection, credential escalation, config poisoning, and supply chain risks, and reports only HIGH and MEDIUM confidence findings with concrete attack paths.
Skill Claude CodeCodex
Use when writing or reviewing code that processes user input — validates and sanitizes to prevent SQL injection, XSS, CSRF, and other injection attacks. NOT when the code path doesn't touch user-supplied data.
Skill Claude CodeCodex
Use when reviewing the source code of an MCP server or client implementation — not just its runtime config — for authentication, session, rate-limit, schema-validation, and SDK-usage vulnerabilities, with file/line-cited findings mapped to OWASP Top 10.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: