Loading...
Loading...
Found 236 Skills
Create documentation-first PRDs that guide development through user-facing content
Label taxonomy and triage workflow for GitHub issues. Defines type labels (bug/feature/enhancement/docs/chore), priority levels (critical/high/medium/low), status labels, and triage decision workflow. Use when categorizing and prioritizing issues.
Issue creation expertise and convention enforcement. Auto-invokes when creating issues, writing issue descriptions, asking about issue best practices, or needing help with issue titles. Validates naming conventions, suggests labels, and ensures proper metadata.
Plan and file goals and feature issues through conversation. Use when the user wants to create goals, plan features, file issues, or discuss what to build next.
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).
Use when the user asks to create a GitHub issue from the current conversation context (e.g., "new issue", "create issue", "file an issue", bug/feature request) with a target repo given or auto-detected, and gh CLI is available/authenticated.
Close a PRD that is already implemented or no longer needed
Report a bug in the compound-engineering plugin
Collaboration workflow for GitHub Issue handling. Used when users receive an issue that needs analysis and response. Through the four-step process of "Diagnosis → Qualification → Decision → Response", produce accurate root cause analysis and appropriate user responses from an issue, avoiding misjudgment of problem types or unprofessional responses.
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.
Replicate and validate a GitHub issue by spinning up Archon, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Archon, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /archon or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).