By shwoo03
Reusable AI agent harness skeleton with canonical skills, rules, ledgers, and verification gates.
Use for read-only codebase, documentation, or repository research where the output should be bounded findings with file references.
Use for bounded implementation after the plan, write scope, and validation command are explicit.
Use after implementation to independently verify behavior, run checks, inspect evidence, and classify outcomes against the project spec.
Use for architecture, tradeoff analysis, implementation planning, and final review when a task needs coherent decisions before execution.
새 프로젝트 부트스트랩 시 사용자와 대화하며 골격을 프로젝트에 맞게 채우는 메타 스킬. 처음 시작할 때 가장 먼저 트리거.
references.yaml의 추적 repo를 갱신하고 변경사항을 우리 패턴에 반영할지 검토.
구현 중 막혔을 때 재계획하는 표준 절차. 같은 task에서 3회 초과 시 자동 정지.
외부 라이브러리·오픈소스를 도입할 때 10개 후보 → 필터 → 정밀 검토 → 사용자 컨펌 절차를 따르는 스킬.
새 skill을 표준 형식으로 생성하는 절차. 골든 케이스 동시 작성 권장.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
공개 HTTP/HTTPS 웹 페이지를 Playwright로 수집하고, 자산·스타일·스크립트·API 단서를 보존해 backend-ready frontend clone 산출물과 replay 검증 결과를 만드는 프로젝트입니다.
npm install
npm test
node bin/cli.js https://example.com --screenshot
주요 진입점:
node bin/cli.js <url>node bin/cli.js harness <url>node bin/cli.js harness queuenode bin/cli.js uinpm test기본 clone 결과는 output/ 아래에 생성됩니다. 임시 수집물과 재생성 가능한 캐시는 .front-clone-tmp/, .page-artifacts/, playwright-report/, test-results/, coverage/ 등에 남을 수 있으며 git 추적 대상이 아닙니다.
이 repo에는 AI_architecture 운영 스켈레톤이 preserve-first 방식으로 이식되어 있습니다. Codex는 AGENTS.md, Claude는 CLAUDE.md를 진입 문서로 사용합니다.
운영 원칙:
skills/, agents/, rules/, mcp/servers.yaml, references.yaml이 canonical source입니다..codex/, .claude/, .mcp.json, CLAUDE.md는 generated surface이며 직접 편집하지 않습니다.python3 scripts/convert.py와 python3 scripts/verify-parity.py로 동기화합니다.runtime/state/session-handoff.md, 활동 로그, completion evidence를 갱신합니다.기본 운영 검증:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/verify-skeleton.py
PYTHONDONTWRITEBYTECODE=1 python3 scripts/verify-parity.py
PYTHONDONTWRITEBYTECODE=1 python3 scripts/resume-readiness.py --strict
프로젝트 목표와 제약은 docs/PROJECT_PROFILE.md를 기준으로 봅니다.
npx claudepluginhub shwoo03/frontend_clone_codingReusable AI agent harness skeleton with canonical skills, rules, ledgers, and verification gates.
Reusable AI agent harness skeleton with canonical skills, rules, ledgers, and verification gates.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns