菜单
Take a finished change from working diff to a ready-for-review PR, ending with the PR URL as plain text. Use when the user says "ship it" or wants to go from a working change to an opened PR.
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。
基于 SOC 职业分类
Commit the current change, push a branch, and open a draft PR. Use when the user wants to open a PR for finished work.
How to drive the `ct` CLI to run matches and produce every number and graph a control experiment ships. Covers `ct run eval`, `ct run monitor`, `ct run summarize`, `ct game-metrics metrics / graph roc / graph pareto`, `ct traj`, and the viewers. Load this when you launch a match, compute safety or usefulness, regenerate a graph, or need the exact reproduce command for an output. White loads it always; main and others load it on demand.
The empirical-research method and quality bar for AI-control experiments run through the ct CLI. Reduce uncertainty fast, iterate on qualitative plus quantitative evidence, size for power, keep splits clean, report honestly, and hold P1 observability, P2 affordance discipline, and the per-team B/R/W/M criteria. Loaded by every role.
The public, LessWrong-style writeup of a control experiment. Ruthlessly compressed for a reader with zero context, leading with the surprise, citing public-viewer trajectory URLs only. Load this in the writing phase when producing the shipped post into `outputs/`. It lifts the STRONG-tagged claims from the internal [report-writing]; same evidence base, far less detail. Before shipping it runs the lw-review gate below.
The red (attacker) role for ONE protocol in an automated control-research run. Load this when you are spawned as red_<protocol>. Holds red's self-managed loop, guarded objective, iteration discipline, and validity rules. Every shared fact (folder layout, iteration mechanics, the stop gate, the game, safety formula, the quality bar, ct commands) lives in a general skill and is referenced here by name, never copied.
The white (referee) role for ONE protocol in an automated control-research run. Load this when you are spawned as white_<protocol>. Holds white's self-managed loop, guarded objective, task-set ownership, validity disciplines, and per-protocol stopping judgment. Every shared fact (folder layout, iteration mechanics, the stop gate, the game, safety formula, the quality bar, ct commands) lives in a general skill and is referenced here by name, never copied.
| name | ship |
| description | Take a finished change from working diff to a ready-for-review PR, ending with the PR URL as plain text. Use when the user says "ship it" or wants to go from a working change to an opened PR. |
Run in order, skipping any step already done; if a step surfaces a real problem, fix it before continuing.
/simplify — code quality pass on the diff./verify — edge-case sweep, reliability checklist, drive the change end-to-end. Tests passing ≠ feature working./code-review — review the diff for bugs before the PR exists; fix every real finding (re-run /verify if a fix changes runtime behavior)./pr — commit, push, open a draft PR./babysit — watch CI, fix failing checks, address review feedback, mark ready when green.When done, share the full PR URL with the user, verbatim as plain text on its own line.