メニュー
Draft or update a personal mode skill from repeated working preferences, corrections, and current-workspace evidence. Use when the user says "automate me," wants agents to work in their style, or asks to create, refresh, or update a personal mode skill.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create a researched, durable, approval-gated goal contract whose verification tools, repository-vault authentication, exact proof steps, rollout safety, and evidence lifecycle are ready before execution. Use when the user asks to set, create, refine, save, or verify a goal; asks whether an agent has everything needed to prove completion; wants a proof-driven alternative to a raw `/goal`; or explicitly invokes `$verify-goal`.
Relentlessly interview the user in dependency-aware batches to sharpen a plan, decision, design, idea, codebase change, or bug fix. Use when the user wants to get grilled, investigate a bug from a ticket or screenshots, pass unfinished grilling to a teammate, or pick it up from a PR. Begin each session by choosing native dialogs or one full text batch, then Sideshow or experimental Grill Visuals for live diagrams. In repositories, inspect current behavior, run a mandatory gap and blast-radius pass, and maintain durable decision docs as answers settle.
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents. Loads the rubric from the `thermo-nuclear-code-quality-review` skill in the cursor-team-kit plugin.
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
| name | automate-me |
| description | Draft or update a personal mode skill from repeated working preferences, corrections, and current-workspace evidence. Use when the user says "automate me," wants agents to work in their style, or asks to create, refresh, or update a personal mode skill. |
Turn the user's recurring working conventions into one concise <handle>-mode skill. Use skill-creator for authoring and stop-slop for prose. Capture durable preferences, not a biography or one conversation's mood.
Search the active project and normal personal skill locations for <handle>-mode/SKILL.md, including .agents/skills/, .claude/skills/, .cursor/skills/, and the configured Codex skills directory.
If one exists, update it unless the user explicitly asks to start over. Preserve rules not contradicted by stronger evidence. Use the file's last modification or commit time to focus on newer evidence.
Use only evidence already in the current conversation or explicitly exposed for the active workspace:
If the host exposes a workspace-scoped transcript directory, inspect only that directory. Never glob across unrelated projects or broad home-directory history. If transcripts are unavailable, use current conversation context, repo instructions, .context/CONTINUITY.md, handoff files, and durable project notes. Do not pretend one session proves a recurring preference.
For a large history, use parallel read-only subagents on non-overlapping time slices. Require evidence pointers. Treat patterns seen in multiple slices as strong; treat lone examples as weak.
Mining shows behavior, not every preference. Ask at most two short structured questions about the areas that materially affect the skill, then one optional free-form question. Skip questions already answered by strong evidence.
Useful areas:
Use only sections supported by evidence:
Drop generic advice such as "communicate clearly." Keep specific rules that would change agent behavior. Do not force symmetrical sections.
Invoke skill-creator and create or update <handle>-mode in the location the user selected. If they gave no preference, choose the project's normal local skill directory; use the personal Codex skills directory only for cross-project preferences.
Requirements:
name match <handle>-modename and description in frontmatter unless the host requires moreApply stop-slop to every line. Show the draft and incorporate feedback. A mode skill is subjective; user recognition matters more than a synthetic benchmark.
Run the available skill validator. Re-read the final skill cold and confirm each rule has evidence or explicit user approval. Report the path and key behaviors captured. Commit, push, or open a PR only when the user's requested workflow authorizes it.