Loading...
Loading...
Found 99 Skills
Decomposes a PRD into well-formed, engineer-ready tickets — Jira issues or GitHub issues. Use after a PRD exists, to turn its phases and user stories into a structured backlog. Works for a new codebase (MVP scope) or an existing one (epic scope).
Close a PRD that is already implemented or no longer needed
Report a bug in the compound-engineering plugin
Diagnose GitHub bug reports in openai/codex. Use when given a GitHub issue URL from openai/codex and asked to decide next steps such as verifying against the repo, requesting more info, or explaining why it is not a bug; follow any additional user-provided instructions.
Conversational bug discovery → issue draft. Light listening, background exploration, scope assessment. Asks before gh issue create — never auto-files. Use when conducting a QA session, triaging user-reported issues, or filing bugs.
Create a feature branch in a git worktree from a GitHub issue
Configure a Stop hook that surfaces unfinished todos before a session ends and suggests creating GitHub issues for deferred work. Use when you want unfinished Claude Code session tasks automatically flagged for GitHub issue creation at session end.
Use when a user has finished using one installed skill and wants to preserve actionable feedback about that skill while the session context is still fresh
Use this skill to triage a single newly opened, reopened, or `status/needs-triage`-labelled issue in microsoft/apm. Emit one synthesized comment with a triage decision, label set, milestone, and suggested next action.
Use when creating a PRD, writing requirements, or transforming a feature request into an implementation-ready GitHub issue.
Turn vague intent into a precise, executable spec in five phases. (gstack)
Propose improvements to a skill in its canonical repository. Defines how to proceed when work does not follow the skill, when information obtained through Web searches differs from or is newer than the skill's content, or when strictly following the skill's conditions is judged to prevent the best possible result. Includes guidance on not directly editing skills installed in the home directory, routing proposals to the appropriate repository, and Issue title and body templates. Use this when you have questions about a skill's content or want to propose an improvement to it.