本文へ移動
cccskills
無料GitHub で公開

my-better

Push a task to a deeper version of itself, not a bigger one: name what a top practitioner would add, the raw material to start from, the methods and tools to use, and an independent check of the result, then rewrite the brief and do the work to it. Use when the user explicitly invokes my-better, says a result is shallow or not good enough (「浅い」「もっと深く」 「物足りない」), or before starting a hard task: open-ended research, analysis, design, or writing whose quality depends on expertise, primary evidence, or verification the request does not mention. Do NOT use for routine edits, single obvious fixes, quick lookups, fully specified tasks with clear acceptance checks, or work covered by a more specific skill such as my-diagnose, my-epic, or my-pr.

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。

Ynakatsuka/dotfiles
インストール方法を見る

含まれるファイル（1）

  • SKILL.md2.8 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。

Adapted from joshp123's /better skill (https://gist.github.com/joshp123/a1443d30fa1b7c577e74882895cea61b).

Better

Ask for a deeper version of the task, not a bigger one.

Choose the mode

  • Prompt rewrite: The user explicitly invoked this skill with a prompt or task that has not started. Answer the questions, give the rewritten prompt, and stop. Do not carry it out.
  • Redo: The user explicitly invoked this skill alone or with feedback on work already done in this conversation. The task is that work, and the feedback is part of it.
  • Automatic: The skill was selected without explicit invocation because the task is hard. Keep the answers and the brief to a few lines so the user can redirect early.

Answer the questions

Answer each for this specific task, in a few lines:

  1. Practice: What would a top practitioner in this field do here that the request does not ask for?
  2. Raw material: What raw source would they start from instead of material already digested for the user, such as code, logs, data, primary documents, or the running system?
  3. Methods: Which specific methods and tools would they use?
  4. Independent check: What, other than the agent's or the user's judgment, would show the result is right, such as a test, measurement, reproduction, or primary source?

Then write the deepened brief: the original request and any feedback, sharpened by these answers.

Decide whether to pause

In Redo and Automatic modes, show the brief and wait for the user's go-ahead when it changes the goal, adds deliverables or affected systems, or needs a decision, money, or access only the user can give. Better sources, methods, and checks for the same deliverable do not need approval; continue without asking.

Do the work

Start from the raw material in answer 2 and use the methods in answer 3. Before reporting, run the check in answer 4 and state what it showed. If the check cannot be run, name what blocked it and what would run it; do not report the result as verified.

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

my-agent

無料

Delegate tasks to an external CLI agent (OpenAI Codex, Google Gemini, or Claude Code) for second opinions or parallel execution. Use when the user explicitly mentions "codex", "gemini", or "claude" or asks to delegate work to one of them (e.g., "codexで実行", "codexに聞いて", "geminiで実行", "Geminiに聞いて", "claudeで実行", "Claudeに聞いて", "run with codex", "ask gemini", "ask claude"). Also use when the user mentions Claude's "fable" model alias for delegation or consultation (e.g., "fableで実行", "fableに相談", "Fableに聞いて", "ask fable"). Do NOT use for general coding tasks that don't mention codex, gemini, claude, or fable.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

my-bulk-read

無料

Delegate reading large or multiple files to the `bulk-read` command, which sends the files to a cheaper reader model and returns only its answer. Use when a question needs the content of a file over about 350 lines or of several files at once, when a PreToolUse guard denied an unbounded read, or when the user says "bulk read", "一括読み込み", or "まとめて読んで". Do NOT use for files you are about to edit, for subtle correctness reasoning such as concurrency bugs, or for short files that fit a bounded read.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

my-ccv

無料

Manage Claude Code Viewer (CCV): preview in-progress CCV changes on ccv-preview, register HTML artifacts, download files, or schedule jobs via CCV local API. Use when user asks for CCV preview, ccv-preview, browser visual QA, UI/UX validation, CCV artifacts, CCV file download, or CCV scheduler jobs. Treat preview/プレビュー as the CCV app preview service first; use artifacts only when the user explicitly asks for artifact/dashboard/report HTML. Do NOT use for generic web app previews outside CCV, production deployment, Cloudflare config, or Anthropic remote triggers.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

my-code-write

無料

Delegate writing predictable code to the `code-write` command, which has a cheaper writer model write the target file directly so the generated code never enters your context. Use for tests, scaffolding, fixtures, boilerplate, or a new file that copies an existing pattern, and when the user says "code write", "生成を委譲", or "雛形を書かせて". Do NOT use for design decisions, changes to public contracts or shared modules, edits inside an existing file that needs judgment, or logic with subtle correctness requirements.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

my-diagnose

無料

Disciplined diagnosis workflow for hard, intermittent, or multi-component bugs and performance regressions: inspect logs and existing evidence, build a feedback loop, test falsifiable hypotheses, instrument gaps, and verify the outcome. Use when the root cause is unclear, reproduction is unreliable, several causes or components are plausible, or performance has regressed. Do NOT use for obvious single-cause errors, straightforward configuration or syntax fixes, planned feature work, or broad architecture review. Diagnosis-only requests stop after reporting the root cause and evidence; apply a fix only when the user requested one.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

my-epic

無料

Manual-only orchestrator for medium-to-large software development. Turns a broad goal into PR-sized and operational nodes with verification gates, then coordinates approved execution across follow-up prompts. Activate only when the user explicitly invokes my-epic; once activated, keep orchestrating that epic for the rest of the session. Do NOT use for an uninvoked planning or implementation request, a single small bug fix, one obvious PR, pure code review, ordinary SDD work that fits in one spec/PR, or implementing an epic during the same first call that created it.

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。

Ynakatsuka/dotfiles42026年10月22日 更新

Ynakatsuka のスキルをすべて見る

このスキルの問題を報告する