本文へ移動
cccskills
無料GitHub で公開

udocument

Use when writing or editing documentation — project docs, CLAUDE.md, READMEs, SKILL.md, docstrings, inline comments. Auto-triggers on `.md` files and docstring edits. Enforces lead-with-why, kill stale content, lists over tables, no aspirational sentences.

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。

btseytlin/ultrapackスター 46(GitHub 46 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.9 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。

Document

Documentation explains how to use and maintain the system. Apply these rules to project docs, agent guidance, skills, docstrings, and comments.

Core rules

  • Lead with the problem or purpose, then describe behavior and usage.
  • Prefer one concrete example over repeated explanation.
  • Remove stale descriptions of behavior that no longer exists. Do not add historical notes to preserve them.
  • Document supported behavior, not aspirations.
  • Use lists instead of tables unless the user requests a table.
  • Write short, grammatical sentences. Remove framing and repeated instructions.
  • State concrete constraints. "Dataset must not import training" is clearer than "respect boundaries".
  • Consolidate duplicated guidance and link to its owner.

Project docs

Answer what the project does, why it exists, how to use it, and where related documentation lives. Include a minimal working example. Keep a README under 200 lines, moving detail into docs/ when needed.

Agent guidance

Put project-wide rules, constraints, style preferences, and pointers in CLAUDE.md or its equivalent. Per-task instructions belong in docs/tasks/<slug>.md.

Skills

  • Preserve name and description frontmatter. The description determines when an agent loads the skill.
  • Cover when to use it, the process, key rules, required output, and terminal state.
  • Use descriptive headings. Aim for a body under about 150 lines without removing required behavior.

Docstrings

For a large class or module, explain its responsibility and boundaries:

class DatasetBuilder:
    """Build dataset shards from raw episodes.

    Validate inputs, transform records, and checkpoint progress.
    Training-time loading belongs in training/loader.py.
    """

For a small utility, one line is enough. Omit docstrings that merely repeat an internal helper's name.

Inline comments

Explain non-obvious reasons: a workaround, required ordering, hidden invariant, or surprising choice. Remove narration such as # increment counter, change-history notes, and placeholder apologies.

Keep a concrete historical cause when it explains a current constraint. "Guard against overflow that corrupted billing totals" explains a guard. "Added in the billing cleanup" does not.

Process

  1. Identify the audience and the question the document must answer.
  2. Choose a list, example, or paragraph that fits the content.
  3. Draft concise instructions grounded in the implementation.
  4. Remove text that adds no instruction or explanation. Do not cut to a percentage target.
  5. Include a concrete example where it helps the reader act.
  6. Check references and remove stale, aspirational, or duplicated claims.

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。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Run a bounded implement-attack-repair loop for a user-specified task. Use when work needs repeated independent criticism: perform the task, dispatch a fresh attacker, verify significant findings, repair them, and stop on a clean attack or the user's round limit.

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。

btseytlin/ultrapack462026年10月15日 更新

e

無料

Explain a file, error, design, diff, or concept like a helpful engineering colleague: grounded in evidence, concise, and with useful follow-up threads. Use when the user asks for a clear explanation of the current work or codebase.

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。

btseytlin/ultrapack462026年10月15日 更新

expand

無料

Turn one user criticism into a principle-level fix: find the violated principle, every similar occurrence, and fix the shared cause. Use only when the user explicitly invokes expand, $expand, /up:expand, or /skill:expand.

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。

btseytlin/ultrapack462026年10月15日 更新

Use when a task needs an isolated checkout. Verify the worktree location, keep mutable environments and build outputs local, and run only authorized setup and checks.

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。

btseytlin/ultrapack462026年10月15日 更新

handsoff

無料

Contract for hands-off mode — the ultrapack workflow variant that minimizes user prompts after Design, takes the safest reversible path, and logs every auto-choice for one end-of-task review. Referenced by the workflow entry point and child skills (udesign, uplan, uexecute, uverify, ureview). Read when the task file's **Mode:** header is `hands-off`.

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。

btseytlin/ultrapack462026年10月15日 更新

Use when the user explicitly asks to launch and supervise a job. Require an authorized launch, monitoring, recovery, and teardown contract. Detect failures without inventing permission to restart or spend money.

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。

btseytlin/ultrapack462026年10月15日 更新

btseytlin のスキルをすべて見る

このスキルの問題を報告する