onboard
Skill1 starsChanged 26 days agoMITView on GitHub
既存プロジェクトにTDD環境をセットアップする。フレームワーク検出、AGENTS.md + CLAUDE.md生成、docs/STATUS.md作成を行う。「TDDセットアップ」「onboard」「プロジェクト初期化」で起動。
165 other projects use a version of this.
Adopted by
Most recently taken up by
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- joeldevz/skynex-pitheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
- Codename-11/SubFrametheir own version, first seen Nov 8, 2026
- passion4it-gmbh/passionfruit-sitetheir own version, first seen Nov 5, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
Used with
Projects with it also use soak-test, team-live-ops 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.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
HK-hubSkillteach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Also in 19 projects that use this
CoralGameSkillproject-stage-detect
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.
Also in 15 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 11 projects that use this
- +5 more from lilangMax
- +2 more from CoralGame
Other versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- nateherkai/AIS-OS★ 1.4ksame name
- poshan0126/dotclaude★ 871same name
- talesofai/cohub★ 585same name
- me2resh/apexyard★ 542same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
155 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- attack-reportSkill
- carefulSkill
- codify-insightSkill
- commitSkill
- context-reviewSkill
- cycle-retrospectiveSkill
- diagnoseSkill
- evolveSkill
- flask-qualitySkill
- flutter-qualitySkill
- generate-e2eSkill
- greenSkill
- hugo-qualitySkill
- js-qualitySkill
- learnSkill
- orchestrateSkill
- php-qualitySkill
- python-qualitySkill
- redSkill
- refactorSkill
- reviewSkill
- security-auditSkill
- security-scanSkill
- skill-makerSkill
- specSkill
- sync-skillsSkill
- ts-qualitySkill
The file
Files
TDD Onboard
Progress Checklist
Onboard Progress:
- [ ] プロジェクト分析(フレームワーク/テストツール検出)
- [ ] プロジェクト状態判定(fresh/existing-no-tdd/dev-crew-installed)
- [ ] 検出結果をユーザーに確認
- [ ] docs/ 構造作成(cycles/, README.md, STATUS.md)
- [ ] CONSTITUTION.md 生成(型検出 + テンプレート)
- [ ] AGENTS.md 生成(cross-tool情報、最大5セクション)
- [ ] CLAUDE.md 生成(@AGENTS.md import + AI Behavior、既存あればマージ)
- [ ] 階層CLAUDE.md推奨(任意)
- [ ] .claude/ 構造生成(rules/, hooks/)
- [ ] Pre-commit Hook確認(推奨)
- [ ] 初期Cycle doc作成
- [ ] Generated Files Validation
- [ ] Next Steps 表示Workflow
Step 1: プロジェクト分析
フレームワーク・ツール・プロジェクト型を検出。加えてプロジェクト状態を判定:
fresh/existing-no-tdd/dev-crew-installed
状態判定ロジック、symlink 検出、検出コマンドは reference.md 参照。
Step 2: 検出結果確認
AskUserQuestion で確認:
- プロジェクト目的(fresh/existing-no-tdd): 何を実現するプロジェクトか
- フレームワーク、パッケージマネージャ、プロジェクト状態、プロジェクト型
モード別確認項目は reference.md 参照。
Step 3: docs/ 構造作成
mkdir -p docs/cycles で作成。docs/README.md + docs/STATUS.md を生成。テンプレートは reference.md 参照。
Step 4: CONSTITUTION.md + AGENTS.md + CLAUDE.md 生成
CONSTITUTION.md(型検出結果に基づくテンプレート)→ AGENTS.md → CLAUDE.md の順で生成。
AGENTS.md (cross-tool、最大5セクション)
fresh→ テンプレートから生成existing-no-tdd/dev-crew-installed→ 既存あればバックアップ後マージ- Content: Overview, Quick Commands, TDD Workflow, Quality Standards, Project Structure(条件付き)
CLAUDE.md (Claude固有)
- 先頭に
@AGENTS.mdimport を配置 fresh→ テンプレートから生成existing-no-tdd→ AI Behavior Principlesをマージ(カスタム保持)dev-crew-installed→ AI Behavior更新/リフレッシュ確認
テンプレートとマージ戦略は reference.md を参照。 生成後に Deletion Test(各行を削除してもClaude が困らないなら削除)を実施。詳細は reference.md。
Step 5: 階層CLAUDE.md推奨(任意)
tests/, src/, docs/ に CLAUDE.md 配置を推奨(各30-50行)。
@docs/xxx.md 形式の import で外部ファイルを参照可能。詳細は reference.md。
Step 6: .claude/ 構造生成
不足分のみ作成、既存は更新確認。rules/: rules/*.md を全て .claude/rules/ に identical mirror (drift は tests/test-rules-mirror.sh で検証)。local-*.md は対象外(導入先独自の rule、移行手順は reference)。hooks/: recommended。
Hook設定は ~/.claude/settings.json へコピー+再起動を案内。詳細は reference.md。
Step 7: Pre-commit Hook確認(推奨)
hookなし → セットアップ推奨。詳細は reference.md を参照。
Step 8: 初期Cycle doc作成
docs/cycles/YYYYMMDD_0000_project-setup.md を作成。
Step 9: Generated Files Validation
生成されたファイルの健全性チェック。FAILは警告のみ(修正は強制しない)。 詳細は validation.md 参照。
Step 10: 完了
セットアップ完了メッセージとコミット案内を表示。Codex連携の案内は reference.md 参照。次: spec で開発開始。メンテナンス案内は reference.md 参照。
Reference: reference.md
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
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.

