本文へ移動
cccskills
無料GitHub で公開

grill-and-record

Run an explicitly requested decision interview and record each settled decision in durable project documentation.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.6 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Grill and Record

Use this skill only when the user explicitly asks for grilling plus durable documentation or directly invokes this skill. Complexity, ambiguity, or a possible need for docs alone never activates it. This skill carries its own interview and documentation contract. Do not load or invoke grill or domain-modeling at runtime.

Interview Contract

  1. Research discoverable facts in the repository, issue, docs, and code before asking the user. Ask only for judgments or facts that cannot be discovered.
  2. Ask one decision-forcing question at a time. State the recommended answer and the reason briefly, then wait for the answer.
  3. Prefer the host's structured input surface for bounded decisions:
    • Use request_user_input when it is exposed and the decision fits 2-3 short, mutually exclusive choices. Put the recommended answer first. Send one question per call with id, header, question, and options; omit Other and None because the client provides a free-form escape. Never set the top-level auto_resolution_ms in a grilling interview: a grilling decision always waits for the human answer, because auto-resolving to the recommended default is never safe when the whole point of the interview is the user's judgment.
    • On Claude Code, use AskUserQuestion for the same bounded choice.
    • Use plain chat only when the structured surface is unavailable or the answer needs free-form discussion. Never pose a bounded checkpoint as plain assistant text or as a free-form question before offering structured choices.
  4. Use comparison tables only when the user explicitly requested one or the question concerns agent-product behavior, such as Claude Code versus Codex.
  5. Follow dependent decisions until the skill decides the decision tree is exhausted. Never ask a final "are we done?" meta-question.
  6. Summarize the settled contract: goals, non-goals, decisions, constraints, risks, validation, and unresolved items.

Ending the interview never authorizes implementation. Implement only after a separate explicit user request.

Documentation Contract

  1. Before the first question, resolve the target document from the user's named target and the repository's existing documentation conventions. Inspect local instructions, indexes, specs, ADRs, glossaries, and nearby docs. If the target is undeterminable, ask one question. Never invent a universal docs/grilling/<date>.md location.
  2. Create or update the target as Draft. Write each settled decision immediately as Draft instead of waiting for the interview to end. Keep unresolved questions visibly marked.
  3. If interrupted or cancelled, preserve the Draft and all file edits, mark unresolved questions, and never auto-revert documentation changes.
  4. Read detailed CONTEXT.md, ADR, glossary, or other format references only when that document type is actually being written.
  5. Normal Write/Edit tool events are the live proof of documentation work. Do not emit duplicate Updated <path> status lines.
  6. An explicit docs request is a hard completion condition: the session cannot finish successfully without a useful documentation creation or update. "No docs needed" with zero file changes never satisfies it.
  7. Only explicit user acceptance may change a document from Draft to Final. Exhausting the decision tree does not imply acceptance.
  8. In the final response, list every changed documentation path and whether it stayed Draft or became Final.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

3d-object

無料

three.js model, downloadable as OBJ or GLB

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

Manage your private to-do list for the user. Use to add or update tasks, record what they are waiting on, track blockers, mark tasks complete or canceled, and clean up the list. Not for Dreamers or external task trackers.

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

agents

無料

Run a goal as a project: you coordinate. Use for "agents <task>", "take this to done", "work on this in parallel", "what are my threads doing", "pick up <slug>", "resume <slug>", "keep going until it is merged". Under `/agents` you do the work yourself unless it needs several lanes or a long wait — you judge; the plan line says why. No target you could verify (a file, API, number or measure) → the grill interview first, not threads. Read this skill before proposing anything for `/agents`: without it a proposal is in-session subagents.

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

Timeline-based motion design

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

The user's synced Apple Health (HealthKit) data: daily metrics (steps, distance, calories, heart rate, HRV, VO2max), sleep sessions (stages, quality, efficiency), and workouts.

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

Create, read, edit, or manipulate Word documents (.docx) and Word templates (.dotx). Use whenever a build task's artifact kind is document with the default docx output, or the task mentions a Word doc, .docx, or .dotx, extracts or reorganizes content from one, inserts or replaces images, does find-and-replace in one, or works with tracked changes (redlines) or comments. Covers python-docx generation, raw OOXML editing of existing files, document structure and formatting, and render verification. Not for PDFs, spreadsheets, or Google Docs.

日本語の概要は準備中です。原文の説明を表示しています。

asgeirtj/system_prompts_leaks7万2026年10月12日 更新

asgeirtj のスキルをすべて見る

このスキルの問題を報告する