hamen/compose_skill

컴포즈 스킬 스위트

Jetpack Compose 감사 + 코딩 에이전트 스킬을 Claude Code, Codex, 커서, 그리고 Anthropic 스타일의 스킬로더에 적용합니다.

compose-agent 4.4.0 · 2026-07-07 — 코딩 에이전트 기술이 작성 중 경고 — 단계별 역쓰기 금지 및 아무 효과도 없는 최적화 — 자체 쓰기 모드 수락 평가(감사 규칙을 추적하기 위해 CI로 강제됨)로 뒷받침됨. 4.3.0 감사는 이런 평가를 사후에 포착합니다; compose-agent는 작성을 멈춥니다.

jetpack-compose-audit 4.3.2 · 2026-07-07 — 교차 위상 백라이트 감지(축 3: 레이아웃 콜백, 컴포지션에서 읽기 상태 읽기), 관련 컴포지션 단계 자기 무효화 검사(컴포저블 바디에서 변이된 스냅샷 컬렉션), 그리고 감사자가 노옵션 "재구성 수정"에 대한 크레딧을 더 이상 인정하지 않도록 False Leads 점수 가드. chrisbanes/skills (Apache-2.0)에서 각색됨.

버전 4.2.0 · 2026-06-17 — Compose에서 3번 페이지: 새로운 paging.md 참조(LLM 가드레일, API 투어가 아님), 기존 Performance/State 카테고리 하의 감사 훅, docs/paging-skill-plan.md의 계획 문서. 멀티 에이전트 교차 검토를 통해 검증됨. 두 기술 모두 '4.2로 출시됨.

Compose Skill Suite

Jetpack Compose audit + coding-agent skills for Claude Code, Codex, Cursor, and Anthropic-style skill loaders.

compose-agent 4.4.0 · 2026-07-07 — Authoring guidance so the coding-agent skill warns while you write — Never Back-Write Across Phases and Optimizations That Do Nothing — now backed by its own write-mode acceptance evals (CI-enforced to track the audit’s rules). The 4.3.0 audit catches these after the fact; compose-agent stops you writing them.

jetpack-compose-audit 4.3.2 · 2026-07-07 — Cross-phase back-write detection (axis 3: layout callbacks writing state read in composition), a related composition-phase self-invalidation check (snapshot collections mutated in a composable body), and a False Leads scoring guard so the auditor stops crediting no-op “recomposition fixes.” Adapted from chrisbanes/skills (Apache-2.0).

Version 4.2.0 · 2026-06-17 — Paging 3 in Compose: new paging.md reference (LLM guardrails, not API tour), audit hooks under existing Performance/State categories, planning doc at docs/paging-skill-plan.md. Validated through multi-agent cross-review. Both skills ship as 4.2.0.

Find out where your Compose app is burning frames, by how much, and what to change to win them back — measured against real compiler data, not vibes.

A strict, evidence-based audit for Android Jetpack Compose repositories. Point it at a repo, let it run the build once, and get back a 0-100 score, a 0-10 score per category, an actionable top-three fix list, and a full Markdown report with every deduction cited against an official developer.android.com page.

Built for Claude Code, Codex, Cursor, and any agent that loads the Anthropic skill format.

Authored and cross-reviewed with every frontier model — Claude Opus 4.8, GPT-5.5, and Gemini 3.5 Flash — each used to pressure-test the rubric, prompts, and references so the audit holds up regardless of which model ends up running it.

---

What’s new

4.4.0 — 2026-07-07