User Story Writer
deanpeters/Product-Manager-Skills
Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.
作業指示毎の作業計画、タスクリストをドキュメントに記録するためのスキル。ユーザーからの指示をトリガーとした作業計画時、実装時、検証時に読み込む。
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/steering .claude/skills/steering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .claude/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/steering .agents/skills/steering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .agents/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/steering .cursor/skills/steering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .cursor/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GenerativeAgents/claude-code-book-chapter8.git --path .claude/skills/steering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/steering .gemini/skills/steering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .gemini/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/steering .github/skills/steering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .github/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GenerativeAgents/claude-code-book-chapter8 steering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GenerativeAgents/claude-code-book-chapter8.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/steering .opencode/skills/steering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "steering" agent skill from https://github.com/GenerativeAgents/claude-code-book-chapter8/tree/main/.claude/skills/steering into .opencode/skills/steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "steering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
steering作業指示毎の作業計画、タスクリストをドキュメントに記録するためのスキル。ユーザーからの指示をトリガーとした作業計画時、実装時、検証時に読み込む。
Steering is an agent skill from GenerativeAgents/claude-code-book-chapter8. 作業指示毎の作業計画、タスクリストをドキュメントに記録するためのスキル。ユーザーからの指示をトリガーとした作業計画時、実装時、検証時に読み込む。
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `templates/design.md`, `templates/requirements.md` and `templates/tasklist.md`).
It sits in Product & Project Management. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 27c4191. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Steering loads about 1.7k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 250 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from GenerativeAgents/claude-code-book-chapter8 at commit 27c4191, republished under its MIT licence (© GenerativeAgents). 250 words, ~1,696 tokens.
.claude/skills/steering/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.ステアリングファイル(.steering/)に基づいた実装を支援し、tasklist.mdの進捗管理を確実に行うスキルです。
このスキルは以下のタイミングで使用してください:
新しい機能や変更のためのステアリングファイルを作成します。
ステアリングディレクトリの確認
現在の日付を取得し、`.steering/[YYYYMMDD]-[機能名]/` の形式でディレクトリを作成永続ドキュメントの確認
docs/product-requirements.mddocs/functional-design.mddocs/architecture.mddocs/repository-structure.mddocs/development-guidelines.mdこれらを読んで、プロジェクトの方針を理解する
テンプレートからファイル作成
以下のテンプレートを読み込み、プレースホルダーを具体的な内容に置き換えてファイルを作成:
.claude/skills/steering/templates/requirements.md → .steering/[日付]-[機能名]/requirements.md.claude/skills/steering/templates/design.md → .steering/[日付]-[機能名]/design.md.claude/skills/steering/templates/tasklist.md → .steering/[日付]-[機能名]/tasklist.mdtasklist.mdの詳細化
requirements.mdとdesign.mdに基づいて、tasklist.mdを詳細化:
tasklist.mdに従って実装を進め、進捗を確実にドキュメントに記録します。
MUST(必須):
[ ]→[x]に更新NEVER(禁止):
[ ])を残したまま作業を終了する絶対に守るべきルール:
tasklist.mdの全タスクが完了するまで作業を継続すること
[x]になるまで実装を継続タスクスキップは原則禁止
タスクが大きすぎる場合の対処法
技術的な理由でタスクが不要になった場合のみスキップ許可
以下の技術的理由に該当する場合のみスキップ可能:
スキップ手順:
- [x] ~~タスク名~~(実装方針変更により不要: アーキテクチャをXからYに変更したため、このレイヤーが不要になった)未完了タスクが残っている場合のNG例
## 実装後の振り返り
**実装しなかったタスク**:
- テストの実装(時間の都合により別タスクとして実施予定) ❌ 絶対にダメ正しい完了の形
[x]Read('.steering/[日付]-[機能名]/tasklist.md')全体のタスク構造を把握し、次に着手すべきタスクを特定する。
tasklist.mdの内容に基づいてTodoWriteツールでタスクリストを作成:
3-1. 次のタスクを確認
tasklist.mdを読み、次の未完了タスク(`[ ]`)を特定3-2. タスク開始をtasklist.mdに記録(必須)
Editツールを使って、tasklist.mdの該当行を`[ ]`→`[x]`に更新
例:
old_string: "- [ ] StorageServiceを実装"
new_string: "- [x] StorageServiceを実装"重要: Editツールを実行した直後に、更新が成功したことを確認する。
3-3. TodoWriteでもステータス更新
TodoWriteツールで該当タスクを"in_progress"に変更3-4. 実装を実行
開発ガイドライン(docs/development-guidelines.md)に従って実装3-5. タスク完了をtasklist.mdに記録(必須)
実装完了後、必ずEditツールでtasklist.mdを更新して完了を記録
サブタスクがある場合はサブタスクも個別に更新する3-6. TodoWriteでもステータス更新
TodoWriteツールで該当タスクを"completed"に変更3-7. 次のタスクへ
ステップ3-1に戻る各フェーズ(例: フェーズ1、フェーズ2)が完了したら:
tasklist.mdを読み込んで進捗確認
Read('.steering/[日付]-[機能名]/tasklist.md')完了したタスクを確認
[x]になっているかユーザーに報告
「フェーズ1が完了しました。tasklist.mdの進捗を確認してください。」全フェーズの実装完了後、振り返りを書く前に必ず実行:
tasklist.mdを読み込む
Read('.steering/[日付]-[機能名]/tasklist.md')未完了タスク([ ])がないか確認
[x]になっているか?[ ]が残っていないか?未完了タスクが見つかった場合
❌ やってはいけないこと:
✅ 正しい対処法:
パターンA: タスクを実装する
ステップ3(タスクループ)に戻り、未完了タスクを実装するパターンB: タスクが大きすぎる場合
1. タスクを小さなサブタスクに分割
2. tasklist.mdに分割したサブタスクを追加
3. サブタスクを1つずつ完了させるパターンC: 技術的な理由でタスクが不要になった場合のみ
以下の技術的理由に該当する場合のみスキップ可能:
スキップ手順:
1. tasklist.mdに技術的な理由を明記:
「- [x] ~~タスク名~~(実装方針変更により不要: 具体的な技術的理由を詳細に記述)」
2. 振り返りセクションに変更理由を詳細に記録
3. なぜこのタスクが不要になったのか、何に置き換わったのかを明確に記述全タスク完了を確認できた場合のみ次へ
全てのタスクが`[x]`になっていることを確認してからステップ5へ進む最終確認
Read('.steering/[日付]-[機能名]/tasklist.md')すべてのタスクが[x]になっていることを確認
振り返りセクションに記録
Editツールでtasklist.mdの「実装後の振り返り」セクションを更新:
- 実装完了日
- 計画と実績の差分
- 学んだこと
- 次回への改善提案5タスクごとに以下を確認:
実装完了後、tasklist.mdに振り返りを記録します。
tasklist.mdを読み込む
Read('.steering/[日付]-[機能名]/tasklist.md')振り返り内容を作成
Editツールで更新
tasklist.mdの「実装後の振り返り」セクションを更新ユーザーに報告
「振り返りをtasklist.mdに記録しました。内容を確認してください。」もし実装中にtasklist.mdの更新を忘れていることに気づいたら:
即座に更新を実行
Read('.steering/[日付]-[機能名]/tasklist.md')
完了したタスクを特定し、すべてEditツールで`[x]`に更新ユーザーに報告
「tasklist.mdの更新が遅れていたため、現在の進捗を反映しました。」再発防止
計画と実装が大きく異なる場合:
tasklist.mdに注釈を追加
Editツールで該当タスクに注釈を追加:
「- [x] タスク名(実装方法を変更: 理由)」必要に応じて新しいタスクを追加
Editツールで新しいタスクを追加design.mdも更新
設計の変更が大きい場合はdesign.mdも更新実装前に必ず確認:
実装後に必ず確認:
このスキルを正しく使用すると:
🚨 このスキルの最も重要な役割は、tasklist.mdの進捗管理を確実に行うことです。
実装中は常に「ユーザーがtasklist.mdを見たときに進捗が分かるか?」を自問してください。
© GenerativeAgents, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files in .claude/skills/steering of GenerativeAgents/claude-code-book-chapter8.
Open the folder on GitHubat commit 27c4191
Steering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Steering this skillGenerativeAgents/claude-code-book-chapter8 | 119 | — | ~1.7k | Automated safety check: Pass | MIT | |
| User Story Writerdeanpeters/Product-Manager-Skills | 7.2k | 2 repos | ~2.9k | Automated safety check: Pass | Custom licence | |
| Game Changing FeaturesopenstatusHQ/data-table-filters | 2.3k | 3 repos | ~2.1k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Convex Create Componentspokvulcan/poker-planning | 114 | 8 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Self Improving Agentfarm-fe/farm | 5.6k | 2 repos | ~3.3k | Automated safety check: Notes | MIT |
deanpeters/Product-Manager-Skills
Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.
openstatusHQ/data-table-filters
Find 10x product opportunities and high-leverage improvements.
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
spokvulcan/poker-planning
Builds reusable Convex components with isolated tables and app-facing APIs.
farm-fe/farm
A universal self-improving agent that learns from ALL skill experiences.
garrytan/gstack
Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.
GenerativeAgents/claude-code-book-chapter8
チーム全体で統一された開発プロセスとコーディング規約を確立するための包括的なガイドとテンプレート。開発ガイドライン作成時、コード実装時に使用する。
GenerativeAgents/claude-code-book-chapter8
プロダクト要求定義書(PRD)を作成するための詳細ガイドとテンプレート。PRD作成時にのみ使用. An agent skill from GenerativeAgents/claude-code-book-chapter8.
GenerativeAgents/claude-code-book-chapter8
アーキテクチャ設計書を作成するための詳細ガイドとテンプレート。アーキテクチャ設計時にのみ使用. An agent skill from GenerativeAgents/claude-code-book-chapter8.
GenerativeAgents/claude-code-book-chapter8
機能設計書を作成するための詳細ガイドとテンプレート。機能設計書作成時にのみ使用. An agent skill from GenerativeAgents/claude-code-book-chapter8.
GenerativeAgents/claude-code-book-chapter8
リポジトリ構造定義書を作成するための詳細ガイドとテンプレート。リポジトリ構造定義時にのみ使用. An agent skill from GenerativeAgents/claude-code-book-chapter8.
GenerativeAgents/claude-code-book-chapter8
用語集を作成するための詳細ガイドとテンプレート。用語集作成時にのみ使用。
Categories
作業指示毎の作業計画、タスクリストをドキュメントに記録するためのスキル。ユーザーからの指示をトリガーとした作業計画時、実装時、検証時に読み込む。. Steering is an agent skill from GenerativeAgents/claude-code-book-chapter8.
Steering fits situations like: product & Project Management work in your project.
Run `npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a claude-code`. Or copy the skill folder (.claude/skills/steering in GenerativeAgents/claude-code-book-chapter8) into .claude/skills/steering in your project. Claude Code loads it when a task matches its description.
Run `npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a codex`. Or copy the skill folder (.claude/skills/steering in GenerativeAgents/claude-code-book-chapter8) into .agents/skills/steering in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GenerativeAgents/claude-code-book-chapter8 --skill steering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/steering, .gemini/skills/steering, .github/skills/steering and .opencode/skills/steering in your project.
SKILL.md names no scripts, command-line tools or credentials: Steering is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Steering is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Steering: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Game Changing Features (openstatusHQ/data-table-filters, 2.3k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Convex Create Component (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
GenerativeAgents (a GitHub organization) maintains it in GenerativeAgents/claude-code-book-chapter8, which has 119 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on February 28, 2026.
Source: GenerativeAgents/claude-code-book-chapter8 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.