agentleFS
morodomimorodomi/dev-crew/skills/spec/SKILL.md

spec

Skill1 starsChanged 26 days agoMITView on GitHub

TDDサイクルのコンテキストをplan mode内で設定する(plan mode専用)。Triggers on "spec", "new feature", "start TDD", "add feature", "機能追加", "TDDを始めたい", "新しい機能", "開発を始める", "新規開発". Do NOT use for continuing an existing cycle (check docs/cycles/ first).

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, ios-clean and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 7 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 6 projects that use this

  • +2 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No implementation planning(plan modeの探索・設計で行う)/ No test/implementation code

    line 29
  2. Distinctive:

    Ask "What feature do you want to implement?" e.g., login, CSV export.

    line 52
  3. Very specific:

    Use AskUserQuestion to confirm scope (Backend/Frontend/Both).

    line 70

“Common” is measured: kept by at least 6 in 10 of the 145 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Current State

!ls -t docs/cycles/*.md 2>/dev/null | head -3 || echo "(none)"

TDD INIT Phase (Plan Mode)

plan mode内でTDDコンテキストを設定し、planファイルに記録する。

Plan Mode Check

plan modeでない場合: 「plan modeで開始してください。EnterPlanMode → /spec」と案内して終了。

Progress Checklist

- [ ] STATUS確認 → 環境収集 → 既存cycle確認
- [ ] 実装内容確認 → リスク評価 → スコープ確認
- [ ] planファイルにTDDコンテキスト記録

Restrictions

  • planファイルへの記録のみ(Cycle docはsync-planで作成)
  • No implementation planning(plan modeの探索・設計で行う)/ No test/implementation code

Workflow

Step 1: Check Project Status

cat docs/STATUS.md 2>/dev/null — If not found, recommend onboard. Also check hooks: reference.md

Version Gate

  1. .claude/dev-crew.json を読む。missing なら警告して停止。
  2. installed_plugins.json のdev-crewバージョンと比較。不一致なら警告して停止。

Step 2: Collect Environment Info

Collect language versions and key packages. Details: reference.md

Step 3: Check Existing Cycles

ls -t docs/cycles/*.md 2>/dev/null | head -1 — If an active cycle exists, recommend continuing it.

Step 4: Ask What to Implement

Ask "What feature do you want to implement?" e.g., login, CSV export.

Step 4.5: Risk Score Assessment

Calculate risk score (0-100). Keyword scores: reference.md

ScoreResultAction
0-29PASSAuto-proceed
30-59WARNQuick questions (reference.md)
60-100BLOCKBrainstorm (reference.md)

Step 4.8: Ambiguity Detection (reference.md)

ユーザーの回答から仕様の曖昧さを検出し、Questioning Protocolで解消。カテゴリ: Data, API, UI/UX, Scope, Edge cases

Step 5: Scope (Layer) Confirmation

Use AskUserQuestion to confirm scope (Backend/Frontend/Both). Layer/Plugin mapping table: reference.md

Step 5.5: Plan Discipline

Step 6 の前に .claude/rules/plan-discipline.md(local-plan-discipline.md があれば併せて)を Read する。

Step 6: Record to Plan File

planファイルにTDDコンテキストを記録。テンプレート: reference.md

必須: planファイル末尾に ## Post-Approve Action セクションを含めること。これがcompact後のauto-orchestrateトリガーになる。

Step 7: Continue in Plan Mode

Step 7.1: Upstream & Constitution Check — 上流ドキュメント (ROADMAP.md 等) と憲法ドキュメントを読み、設計方針との整合性を確認。差異があれば plan の ## Upstream References に記録。詳細: reference.md

specの記録後、plan mode内で続行(specスキル範囲外): 探索(最低5ファイル)→ 設計 → Test List(Given/When/Then)→ QAチェック(カバレッジ・粒度・セキュリティ・独立性)

Step 7.2: Forced Recall — 設計で Files to Change が確定した直後(Step 8 の前)に bash scripts/recall-candidates.sh . <変更予定ファイル...> を実行し、上位候補を助言者形式で plan の ## Recall に記録(0 件時は「関連する過去サイクルなし」)。詳細: reference.md

→ review --plan → Step 8(承認前 Codex plan review)→ approve(ExitPlanMode)→ 自動orchestrate(sync-plan→RED→GREEN→...)

Step 8: Pre-Approval Plan Review (Codex)

Step 7 後・ExitPlanMode(承認)前: codex exec --sandbox read-only "review plan <plan path>" < /dev/null → findings を draft plan へ直接反映 → 最終版を1回だけ再レビュー(resume、フラグ前置。詳細は reference)→ ## Plan Review Record を plan に記録。未解消 BLOCK は人間の明示 override が承認提示文で必須。Codex 不在時は skip し Record に codex_unavailable を記録。plan_presented 記入後・ExitPlanMode 前に bash "<spec の Base directory>/../../scripts/gates/pre-approve-gate.sh" <plan path> を実行し、BLOCK なら直してから承認へ。詳細: reference.md

Reference

Details: reference.md | Japanese: reference.ja.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.