Plan, design, and implement A/B tests and experiments with statistical rigor. Covers hypothesis frameworks, sample sizing, metrics, and result analysis.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트
무료GitHub에 공개
create-stories
Break an epic into implementable story files with acceptance criteria, GDD traceability and ADR guidance. Run after /create-epics.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane스타 3(GitHub 3 + cccskills 0)
실행 점수 미검증
설치 방법 보기포함된 파일(1)
- SKILL.md4.0 KB
SKILL.md(원문)
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Create Stories
Break an epic into implementable stories — one behavior per story, ~2-4h each, fully traceable to GDD requirement + ADR decision. Run per epic, Foundation first, then Core, etc.
Output: production/epics/[epic-slug]/story-NNN-[slug].md
1. Parse Argument
Resolve review mode: --review arg → production/review-mode.txt → default full. Accept epic-slug or full path. No arg → list available epics via Glob.
2. Load Everything
Read in full: EPIC.md, its GDD (all 8 sections), all governing ADRs (Decision, Implementation Guidelines, Engine Compatibility, Engine Notes), control-manifest.md (rules + manifest version), tr-registry.yaml.
ADR existence validation: confirm all referenced ADR files exist on disk. Missing → stop immediately, redirect to /architecture-decision.
3. Classify Stories by Type
| Type | Assign when criteria reference... |
|---|---|
| Logic | Formulas, thresholds, state transitions, calculations |
| Integration | Two+ systems interacting, signals crossing boundaries, save/load |
| Visual/Feel | Animation, VFX, timing, audio sync |
| UI | Menus, HUD, buttons, screens, tooltips |
| Config/Data | Balance tuning values, data files only |
Mixed → assign type with highest implementation risk. Type determines test evidence required at /story-done.
4. Decompose GDD into Stories
For each GDD AC: group related criteria → each group = one story. Order: foundational first, edge cases last, UI last. Per story determine: GDD requirement + TR-ID (from registry), governing ADR (Proposed → story Blocked), story type, engine risk.
4b. QA Lead Gate (full mode only)
Solo/lean → skip. Full → spawn qa-director gate QL-STORY-READY with story list + ACs + types + TR-IDs. Revise until ADEQUATE. Then qa-director produces test case specs per story:
- Logic/Integration: Given/When/Then + edge cases per AC
- Visual/UI: Setup/Verify/Pass condition per AC
Specs embed into each story's ## QA Test Cases section.
5. Present Stories for Review
Show full story list (title, type, ADR, TR-IDs covered, test required) before writing. AskUserQuestion: write all / review first.
6. Write Story Files
Each story file includes: header (epic, status, layer, type, manifest version), context (GDD path, TR-ID, ADR + decision summary, engine risk + notes, manifest rules), acceptance criteria (from GDD), implementation notes (from ADR), out of scope, QA test cases (from qa-director), test evidence (required path by type + status), dependencies (depends on / unlocks).
Also update EPIC.md with populated stories table.
4b. Producer Epic Gate (full mode only)
Solo/lean → skip. Full → spawn delivery-manager gate PR-EPIC before writing.
7. After Writing
AskUserQuestion with context-aware next steps: start implementing (/story-readiness), create stories for next epic, plan sprint, or stop.
Protocol
- Read all inputs before presenting
- Present all stories at once, not one at a time
- Warn on blocked stories (Proposed ADR)
- Ask before writing (per-epic approval)
- All content from GDDs, ADRs, manifest — no invention
- Never start implementation — stops at story file level
Checklist
- Every story traces back to its parent epic via epic-slug reference
- Each story has a classified type (Logic, Integration, Visual/Feel, UI, Config/Data)
- Acceptance criteria are defined with Given/When/Then format for every story
- No single story exceeds one sprint of estimated effort (~2-4h target)
- Stories with Proposed ADRs are marked as Blocked
- EPIC.md stories table is updated with all created stories
리뷰
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
댓글
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
같은 저장소의 스킬
Web/mobile accessibility decision guide: WCAG 2.2 AA, ARIA, keyboard nav, focus management, contrast, testing. Use for: a11y, accessibility, wcag, aria, screen reader, keyboard, contrast.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트
Generate, iterate, and scale ad creative for paid advertising across Google, Meta, LinkedIn, and X. Covers platform specs, creative frameworks, and quality validation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트
Musica interactiva para juegos: layering vertical, re-secuenciacion horizontal, stingers, reglas de transicion con sync points, y mapeo de estados de gameplay a musica. Usar para: musica adaptativa, sistema de musica dinamica, transiciones musicales, combat music.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트
Design multi-agent systems, create agent architectures, define communication patterns, and build autonomous agent workflows with structured evaluation frameworks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, response formats, and quality loops.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SebastianLuser/claude-code-arcane32026년 10월 27일 업데이트