
cooneycw/claude-power-pack
Deployment & DevOps이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
Claude Code best practices and MCP second opinion server
개요
- A productivity toolkit for Claude Code that adds workflow automation, MCP servers, security scanning, secrets management, and CI/CD integration - with a verification discipline (from 8.0) enforced at the merge boundary (9.0), and in 10.0 a sweep of the helpers that read a non-answer as an answer, plus a merge helper that no longer escalates to --admin unless it is asked to. - (/flow:auto, /flow:start, /flow:eli5, /flow:finish) - Issue-driven development with worktrees, a pre-implementation ELI5 plan/necessity approval gate that cannot be bypassed (#775), quality gates, automated PR lifecycle, and CI verification.
README
원문 README의 일부입니다. 원문 보기.
Claude Power Pack
v10.1.0 - A productivity toolkit for Claude Code and Codex: explicit test/review evidence contracts, host preflight, clearer init permissions and consent, and guarded framework Makefile generation.
What It Does
- Workflow commands (
/flow:auto,/flow:start,/flow:eli5,/flow:finish) - Issue-driven development with worktrees, a pre-implementation ELI5 plan/necessity approval gate that cannot be bypassed (#775), quality gates, automated PR lifecycle, and CI verification. The necessity gate also ships standalone as eli5-gate - installable without CPP via/plugin marketplace add cooneycw/eli5-gateornpx skills add cooneycw/eli5-gate; CPP vendors its canonical core (file gate improvements there) - Wave orchestration (
/flow:wave,/flow:register,/flow:sync) - dependency-ordered issue waves fanned out across worker sessions, coordinated through a durable mailbox with an armed/stale/dead watch status visible on the roster (#778, #801), and per-driver capability declarations (scope, web access) so an orchestrator can check whether a driver can do the work before assigning it, not after a worker refuses (#783) - MCP servers extending Claude Code’s capabilities:
- Second Opinion - Multi-model code review via external LLMs (Gemini, OpenAI, Anthropic), served by the external
cooneycw/mcp-second-opinionrepo and registered at user scope by/cpp:init(streamable-http) - Browser automation - upstream
@playwright/mcpserver (npx/stdio, no container), registered by/cpp:init - Tavily - web search, content extraction, site crawling, and URL mapping via the upstream
tavily-mcpserver (npx/stdio), registered by/cpp:init; API key stored in AWS Secrets Manager (claude-power-pack/mcp-keys)
- Second Opinion - Multi-model code review via external LLMs (Gemini, OpenAI, Anthropic), served by the external
- PowerPoint generation - Slide decks via the native Anthropic
pptxskill (npx skills add anthropics/skills@pptx) - Security scanning (
/security:scan) - Native vulnerability detection with git history analysis - Secrets management (
/secrets:*) - Tiered credential storage (dotenv, env-file, AWS Secrets Manager) with audit logging and a web UI - CI/CD integration (
/cicd:*) - Framework detection, Makefile generation, health checks, and IaC scaffolding - Woodpecker CI - Self-hosted pipeline (secret-scan, lint, test, typecheck) with programmatic status polling
- Project scaffolding (
/project:init) - Zero-to-GitHub-repo setup with Makefile, CI pipeline, and Docker config - Skills ecosystem - Discover, install, and manage agent skills from skills.sh via native
npx skillsand the/pluginmarketplace (the CPP/skills:*wrapper was retired in issue #437)
추천 도구
다른 키워드를 입력하거나 필터를 제거해 보세요.
설치
npx skillfish add cooneycw/claude-power-pack