菜单
Use when an RFC discusses multiple options but hasn't laid them out side-by-side. Reads the body, extracts the alternatives, proposes comparison axes, and builds a markdown table in chat. The user edits it into the RFC themselves – in their own voice – if they want it there.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when reviewing an RFC that proposes code changes. Reads the RFC, then reads the actual repository at the PR head ref, and flags every factual claim the proposal makes about the codebase that the code contradicts or omits. Output stays in chat – the user types any feedback into GitHub themselves.
Recommend reviewers for an RFC based on file paths in the PR, prior commenters on related RFCs, and the team mapping already visible from listed RFCs. Shows a ranked list with reasons, then requests reviewers on the user's approval.
Use when the user wants to talk through a specific RFC in depth – understanding the proposal, pressure-testing it, comparing it against the actual codebase, and surfacing gaps the author missed. Pulls the RFC + threads via the MCP server, grounds the discussion in the current code, and stays in chat. Never posts back to the RFC.
Use to surface explicit owner+action items buried in long RFC discussions ("@alice will write up the migration", "@bob to check with infra"). Shows the checklist in chat; the user edits it into the RFC themselves, in their own voice.
Use when the user wants to stress-test an RFC's reasoning – strawman and steelman each claim, surface unstated assumptions, list missing alternatives, and find weak links. Pulls the RFC + threads via the MCP server and runs the analysis in chat. Never posts back to GitHub.
Use when an RFC has accumulated enough comments that newcomers can't easily see the shape of the discussion. Reads every comment and review thread, groups concerns by theme, distinguishes settled vs. unresolved, and shows the roll-up in chat. Never posts back to GitHub – the user reworks any of it into the RFC in their own words.
| name | compare-alternatives |
| description | Use when an RFC discusses multiple options but hasn't laid them out side-by-side. Reads the body, extracts the alternatives, proposes comparison axes, and builds a markdown table in chat. The user edits it into the RFC themselves – in their own voice – if they want it there. |
| allowed-tools | ["mcp__rfc123__rfc123_get_rfc"] |
Convert a prose discussion of options into a comparison table the user can scan in 10 seconds. Output stays in chat. If the user wants the table on the RFC, they edit it in themselves – rewriting the cells in their own voice. The chat table is a thinking aid, not source prose.
The user says "compare the options", "build a table", or the RFC contains phrases like "Option A would …, Option B would …" without a structured comparison. Also good when the user is reviewing and is confused about which option does what.
Read the RFC. Call rfc123_get_rfc.
Extract the options. List every distinct alternative the body discusses, in the order they appear. If you can only find one, stop and tell the user – there's nothing to compare.
Pick comparison axes. 4–7 axes typically. Choose axes that actually discriminate between options. Generic axes ("complexity", "cost") often end up with the same value in every cell – prefer specific axes that match the topic (e.g. "supports cross-region", "schema-compat with X", "blast radius if it breaks").
Build the table in chat.
| | Option A | Option B | Option C |
|-----------------------|------------------|------------------|------------------|
| <axis 1> | … | … | … |
Walk the user through your axes and cell values. They may know domain facts you don't. Iterate in chat until the table looks right.
Stop there. Do not commit the table to the RFC. Tell the user: "Here's the table – edit it into the RFC body yourself, rewriting the cells in your own voice as you go."