AI coding completion framework. Built-in Ralph Loop + DoD/SPEC/TDD/Fresh Context Verification to ensure AI finishes the job
npx claudepluginhub vp-k/auto-complete-loopAdd E2E tests to existing projects. Auto-generate scenarios from docs or code analysis
Doc consistency check. Verify doc↔doc and doc↔code alignment with scripts + AI auto-fix
Iterative code review (3-way: codex + gemini). codex-cli(SEC/ERR/DATA) + gemini-cli(PERF/CODE) independent review
Iterative code review (solo multi-perspective). Claude reviews from SEC/ERR → DATA/PERF → IMPL perspectives without external AI
Iterative code review (2-way: codex). codex-cli reviews all categories (SEC/ERR/DATA/PERF/CODE) independently
End-to-end project automation (solo). No external AI dependency, Claude multi-perspective review
End-to-end project automation with Agent Teams. 3-way parallel code review + Live Testing
End-to-end project automation. One-line requirement to planning → implementation → code review → verification
Implement planning docs (fully automated). Claude implements directly, codex handles review/debugging only
User interview preparation. Auto-generate persona-based interview scripts using The Mom Test principles
Interview transcript analysis. Extract patterns and derive requirements from user interview records
Planning doc refinement (3-way auto-discussion). codex-cli, Gemini, and Claude Code debate to optimal result
Planning doc refinement (solo multi-perspective). Claude debates as writer vs. critical reviewer without external AI
Planning doc refinement (2-way auto-discussion). codex-cli and Claude Code debate to optimal result
프로젝트를 프로덕션 릴리즈 준비 상태로 만듭니다.
프로젝트를 프로덕션 릴리즈 준비 상태로 만듭니다.
프로젝트를 프로덕션 릴리즈 준비 상태로 만듭니다.
Post-project analysis. Run Metrics/Retrospective/Launch/Competitive analysis sequentially
Use this agent during Phase 1 for architecture review. Validates tech stack fitness, dependency analysis, API design consistency, data model integrity, and non-functional requirement coverage. Produces Architecture Review Report with ARCHITECTURE_SCORE.
Use this agent for independent code review during Phase 3. Reviews code across 5 categories (SEC/ERR/DATA/PERF/CODE) with severity-based finding format. Designed for Agent Teams parallel review.
Use this agent at every phase transition gate. Validates Pre-mortem Tiger resolution, DoD evidence validity, scope change impact, and technical debt accumulation. Delivers GO / NO-GO / CONDITIONAL GO decisions before phase advancement.
Use this agent for Phase 0 PM planning review. Independently validates persona quality, priority consistency (MoSCoW→ICE→Kano), user story INVEST criteria, and goal-feature alignment. Runs in parallel with Codex review at Step 0-7.
Use this agent between Phase 1 and Phase 2. Designs test strategy including pyramid allocation, edge case identification, failure path scenarios, test data design, and contract test needs. Produces Test Plan that guides Phase 2 implementation and Phase 4 verification.
Use this agent during Phase 3 code review, in parallel with code-reviewer. Conditional: only invoked when projectScope.hasFrontend=true. Reviews information architecture, interaction patterns, WCAG 2.1 AA accessibility, responsive design, and visual consistency. Produces UX Review Report with UX_SCORE.
Use this agent for Phase 4 verification. Independently validates that all quality gates pass, DoD items have evidence, and the project is ready for release. Does not modify code — only audits and reports.
Loaded by the full-auto-solo orchestrator at Phase 3 entry via Read.
Loaded by the full-auto orchestrator at Phase 3 entry via Read.
Loaded by the full-auto-solo orchestrator at Phase 1 entry via Read.
Loaded by the full-auto orchestrator at Phase 1 entry via Read.
Loaded by full-auto Phase 2 or add-e2e orchestrator via Read.
Loaded by the full-auto orchestrator at Phase 2 entry via Read.
Runs the actual app and validates user flows from the user perspective.
Loaded by the full-auto orchestrator at Phase 0 entry via Read.
Loaded by the full-auto-teams orchestrator at Phase 3 entry via Read.
Loaded by the full-auto orchestrator at Phase 4 entry via Read.
Generates a competitive analysis frame based on source code and planning docs.
Generates a launch strategy draft based on planning docs and code.
Analyzes source code to recommend KPIs and analytics events to track.
Generates a data-driven retrospective report from progress JSON and git log.
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.