Skill Claude Code
Invoked helper skill for strict red-green-refactor implementation, usually delegated from /execute or bug-fix work shaped by /triage-issue. Use when backend behavior or behavior-heavy frontend logic should be built test-first through public interfaces. Not for shaping, decomposition, vague implementation tasks, or…
Skill Claude CodeCodex
Invoked helper skill for deep bug diagnosis, usually delegated from /qa when a reported issue needs root-cause analysis and a TDD fix plan before implementation. Use when the cause is unclear, the bug is a regression, or the user explicitly wants diagnosis. Not for lightweight QA intake (use /qa) or already-clear…
Skill Claude CodeCodex
Audit TypeScript and React code against expert-level best practices from 9 TypeScript library references. Use when the user wants to review, audit, check, or improve TypeScript code quality — including requests like "audit this file", "review my types", "check my TypeScript", "what's wrong with this code", "improve my…
Skill Claude CodeCodex
Side-route skill for hardening domain vocabulary. Use when terminology is fuzzy, competing terms are causing confusion, or a glossary would improve shaping, QA, and refactor conversations. Produces UBIQUITOUSLANGUAGE.md, then returns to the workflow that needed sharper language.
Skill Claude CodeCodex
Side-route skill that renders a change as a single self-contained interactive HTML artifact — a finished diff, PR, or branch, or a plan's decisions and architecture before any of it is built. Three block sets: a scrolling recap for auditing a change (file-tree + change flags, annotated split diffs with line-anchored…
Skill Claude CodeCodex
Side-route skill for an interactive, commit-by-commit comprehension walkthrough of a finished branch before merge. Use when the person about to merge didn't author the diff — or hasn't internalized it — and needs to understand each commit's intent, riskiest line, deliberate oddities, and what's absent by design, with…
Skill Claude CodeCodex
Primary pipeline shaping step after /research and before /prd-to-issues. Use when the problem is understood well enough to turn into a bounded PRD issue. May invoke /design-an-interface or /api-design-review when interface or contract uncertainty remains. Not for discovery, decomposition, or implementation-ready work.
Skill Claude Code
Invoked helper skill for fixing the /pre-merge findings a human has already chosen, with a fresh sub-agent writing each fix and a second fresh sub-agent trying to break it. User-invoked only — type /fix-findings after picking findings from a review. Not for choosing which findings to act on, not for stamping review…
Skill Claude Code
User-invoked side-route for a proof of concept: short shaping conversation, then AFK to a stamped PR. Auto-sizes a one-off fix to a tiny path. Stops only for a credential, a destructive action, a spend, or a product fork. Not for production features, not for work you intend to keep without a later /pre-merge, not…
Skill Claude Code
User-invoked side-route for onboarding to a legacy repo with no docs/solutions/, research archive, or written decisions. Mines the last 12 months of git history and, when gh is available, PR bodies and review threads, into ranked hotspots, cited recovered decisions, and a who-to-ask map, then offers a PR of…
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: