claude-forge

전문 에이전트 자동 라우팅. 법률, 재무, 특허, SEO, 마케팅, 기획, 코드리뷰, 아키텍처, 견적, CRM, 리서치, 제1원칙 사고 등 34 도메인

개별 커맨드를 하나씩 호출하는 대신, 전체 파이프라인을 한 번에 자동 실행합니다.

Incrementally fix TypeScript and build errors one at a time

작업 상태 저장/복원 (v6)

방금 작성한 코드를 보안+품질 검사합니다.

```bash

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

Manage eval-driven development workflow (define, check, report, list)

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Comprehensive guide to all benchmarks supported by BigCode Evaluation Harness.

Guide to implementing custom evaluation tasks for code generation models.

Solutions to frequently encountered problems with BigCode Evaluation Harness.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Guide to evaluating OpenAI, Anthropic, and other API-based language models.

Complete guide to all 60+ evaluation tasks in lm-evaluation-harness, what they measure, and how to interpret results.

Complete guide to creating domain-specific evaluation tasks in lm-evaluation-harness.

Guide to running evaluation across multiple GPUs using data parallelism and tensor/pipeline parallelism.

---

Use when adding new error messages to React, or seeing "unknown error code" warnings.

---

처음 사용자를 위한 인터랙티브 가이드. 약 3분이면 끝납니다.

v5의 `/handoff` + `/clear` + `/verify`를 **하나의 커맨드**로 통합.

프로젝트 초기화 체크리스트. 최초 1회 실행하여 CLAUDE.md, spec.md, prompt_plan.md를 대화형으로 생성한다.

---

다음 작업 추천 (v6)

v5의 worktree 기반 병렬 실행을 **Agent Teams API**로 대체.

AI가 구현 계획을 세워줍니다. 확인 후 코딩 시작.

git pull origin main 빠르게 실행

간단한 수정용 빠른 커밋 (v6)

Safely identify and remove dead code with test verification

A comprehensive skill pack for security professionals implementing defense-in-depth security architectures, achieving compliance with industry frameworks, conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

**Incident ID**: INC-2025-XXX

The entity implements logical access security software, infrastructure, and architectures over protected information assets to protect them from security events to meet the entity's objectives.

```

SOC 2 is an auditing standard developed by the American Institute of CPAs (AICPA) for service organizations. It evaluates a company's information systems based on five Trust Service Criteria (TSC).

Zero Trust is a security model based on the principle of "never trust, always verify." It assumes that threats exist both inside and outside the network.

```

STRIDE is a threat modeling framework developed by Microsoft that categorizes threats into six types.

```

현재 Claude Forge 설치 상태와 프로젝트 정보를 보여줍니다.

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

반복 패턴 분석하여 자동화 기회 제안 (주기적 실행 권장)

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

prompt_plan.md, spec.md, CLAUDE.md + rules/ 문서 동기화 (v7)

---

테스트 먼저 만들고 코드 작성. 한 단위 작업에 사용.

Analyze test coverage and generate missing tests:

Analyze the codebase structure and update architecture documentation:

Sync documentation from source-of-truth:

- `--max-retries N`: 최대 재시도 횟수 (기본: 3)

```bash

PR 완료 후 Git Worktree 정리 (v6)

```bash

---

---

---

---

---

---

---

---

---

---

---

프로젝트 빌드 시스템 자동 감지 및 실행 스킬

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

Claude Code 개발 워크플로우 최적화. Context Engineering, Sub-agents, TDD, 개발 후 검증 워크플로우 제공. 트리거: CC 프로젝트 시작, CLAUDE.md/spec.md 작성, /handoff /verify /commit-push-pr, sub-agent/Explore, Agent Teams 병렬 개발 요청 시.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.

세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 프로젝트 CLAUDE.md를 관리합니다.

스킬/프롬프트 탐색 및 검색 통합 스킬. 사용자가 스킬 설치, 프롬프트 검색, 프롬프트 개선을 요청할 때 활성화.

보안 파이프라인 - CWE Top 25 + STRIDE 자동 검증

세션 종료 전 자동 정리 스킬. 4개 병렬 subagent가 문서 업데이트, 반복 패턴, 학습 포인트, 후속 작업을 동시 탐지하고, 1개 검증 subagent가 중복 제거 후 사용자에게 선택지를 제시한다. 트리거: /session-wrap, 세션 마무리, 세션 정리, 작업 마무리

Analyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로", "스킬 만들어", "이거 스킬로", "skill factory", "이 작업 자동화해", "스킬 추출", "make this a skill", "extract skill", "convert to skill", "스킬 팩토리", "자동 스킬 생성". Differs from skill-creator (archived) and manage-skills (drift detection): this skill actively analyzes sessions, checks for duplicates, and creates skills via Agent Teams.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Agent Teams 오케스트레이션 엔진 - 팀 구성, 작업 분배, 의존성 관리, 결과 집계

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

통합 검증 엔진 - 서브에이전트 기반 fresh-context 검증 루프 (v6)

프로젝트의 모든 verify 스킬을 실행하여 통합 패턴 검증 보고서를 생성합니다. 기능 구현 후, PR 전, 코드 리뷰 시 사용.