Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ezagent42
PRD-to-Implementation pipeline: 14-skill workflow from requirement analysis to task execution, progress tracking, and milestone verification. Per-scope plans_dir isolation for parallel milestones. design-spec → prd-structure.yaml ingest bridge for superpowers integration.
npx claudepluginhub ezagent42/prd2impl --plugin prd2implHeterogeneous document ingestion — parse multiple human-authored Markdown files (gap analyses, design specs, plans, PRDs) into the same YAML artifacts as skill-1/skill-2, plus a task-hints.yaml that preserves human design decisions. Use when the user says 'ingest docs', 'read my markdown files', 'import gap analysis', or provides multiple MD files as starting point instead of a formal PRD.
Structured PRD extraction — parse a Product Requirements Document into modules, user stories, NFRs, and constraints. Use when starting a new project from a PRD, or when the user says 'analyze PRD', 'parse requirements', 'read the PRD'.
Milestone gate verification — run automated checks and produce a structured pass/fail report for a milestone. Use when the user says 'smoke test', 'verify milestone', 'M1 gate check', or runs /smoke-test.
Milestone retrospective analysis — analyze cycle times, blockers, failure patterns, and generate improvement suggestions. Use when the user says 'retrospective', 'retro for M1', 'what went wrong', or runs /retro.
Contract drift detection — analyze changes in contract/interface files and assess impact on dependent tasks. Use when the user says 'check contracts', 'contract drift', 'schema changed', 'interface changed', or runs /contract-check.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Connect a Feishu bot to Claude Code
PRD-to-Implementation pipeline for Claude Code. A 14-skill plugin that takes you from a Product Requirements Document (or existing hand-written docs) through gap analysis, task generation, execution planning, parallel batch dispatch, full-autopilot execution, and all the way to milestone verification.
🇨🇳 中文用户: 完整的中文使用手册(含新项目接入 / 多人协同分工 / 典型工作流 / FAQ)见 docs/guide-zh.md。
# 1. Add the ezagent42 marketplace (one-time)
/plugin marketplace add ezagent42/ezagent42
# 2. Install prd2impl
/plugin install prd2impl@ezagent42
If you've cloned this repo locally, add to your project's .claude/settings.json:
{
"plugins": [
"/path/to/prd2impl"
]
}
prd2impl delegates testing and methodology to two optional companions (both available on the same marketplace). Install them for the full pipeline; without them, prd2impl degrades gracefully to simpler paths.
/plugin install dev-loop-skills@ezagent42 # test pipeline (eval / plan / code / run / registry)
/plugin install superpowers # brainstorming, TDD, debugging, code review
references/mock-policy.md — Mock policy
consumed by task-gen, start-task, continue-task, and batch-dispatch.
Defines what may / must-not be mocked and the contract-test pattern
that catches the cdcfdb2 bug class. Project-specific overrides can
live at {plans_dir}/mock-policy.local.md.After installing, the following skills should appear in /help:
prd2impl:ingest-docs — Ingest human-authored MDs (Entry B)
prd2impl:prd-analyze — Structured PRD extraction (Entry A)
prd2impl:gap-scan — Codebase vs PRD gap analysis
prd2impl:task-gen — Task generation with dependencies
prd2impl:plan-schedule — Execution plan & batch scheduling
prd2impl:start-task — Launch a task into dev-loop
prd2impl:continue-task — Resume task at next checkpoint
prd2impl:next-task — Recommend next executable task
prd2impl:batch-dispatch — Parallel agent dispatch for a batch
prd2impl:task-status — Progress dashboard
prd2impl:smoke-test — Milestone gate verification
prd2impl:retro — Milestone retrospective
prd2impl:contract-check — Contract drift detection
prd2impl:autorun — Full-autopilot orchestrator
/prd-analyze docs/prd/my-prd.md # Step 1: Parse PRD → structured YAML
/gap-scan # Step 2: Scan code vs requirements
/task-gen # Step 3: Generate task breakdown
/plan-schedule # Step 4: Create execution plan
Use this when you already have gap analyses, design specs, or plans in Markdown. Entry A and Entry B are mutually exclusive — pick one per project.
/ingest-docs gap.md design-spec.md plan.md
# Step 1: Classify + extract → 3 YAMLs
# prd-structure.yaml
# gap-analysis.yaml
# task-hints.yaml (preserves file-change granularity)
/task-gen # Step 2: Generate tasks (reads task-hints.yaml automatically)
/plan-schedule # Step 3: Create execution plan
Force a role when auto-detection is uncertain:
/ingest-docs a.md b.md --tag design-spec=a.md --tag gap=b.md
Each step has a human review checkpoint — the pipeline pauses and waits for your approval before advancing.
/next-task # What should I work on?
/start-task T1A.1 # Start a specific task
/continue-task T1A.1 # Resume after review
/task-status # Overall progress dashboard
/batch-dispatch batch-3 # Launch batch in parallel
/batch-dispatch T1A.3,T1A.6,T1A.7 # Launch specific tasks
/smoke-test M1 # Verify milestone
/retro M1 # Retrospective analysis
/contract-check # Check interface drift