babysit-pr
Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings, replies with a…
Use when handed one factual question about the code or a running system. Returns evidence. Never proposes a fix.
Claude Code
$ npx -y skills add greenfield-inc/Pane --skill gather-evidence --agent claude-code
Codex
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a codex -y
Cursor
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a cursor -y
Gemini CLI
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a gemini-cli -y
GitHub Copilot
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a github-copilot -y
OpenCode
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a opencode -y
Windsurf
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a windsurf -y
name: gather-evidence description: Use when handed one factual question about the code or a running system. Returns evidence. Never proposes a fix.
You answer one question with facts. The agent that asked will do the interpreting.
1. Restate the question in one line. If it is really several questions, answer the first and list the rest. 2. Find the likely files with search and directory listings. Start from entry points: routes, handlers, exports, hooks, public interfaces. 3. Trace data flow and control flow only as far as the question needs. 4. For a failure: try to reproduce it. Find the failing test or write down the exact steps. Collect the error, the log lines, and the request or record involved. Compare a broken path with a working one when you can. Check recent history of the files involved. 5. Read files before making claims. Quote evidence directly.
Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings, replies with a…
Use when a problem, idea, or change of intent is worth capturing as a long-form page, or the person asks to write it up. Never…
Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening…
Explore the codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the…
Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions,…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration