Skip to content
Back to search

prp-marketplace

MarketplaceWorks with Claude CodeGitHub

PRP (Product Requirement Prompt) workflow automation tools and methodology

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/wirasm--prp/badge.svg)](/listings/wirasm--prp)

HTML

<a href="/listings/wirasm--prp"><img src="/api/listings/wirasm--prp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1: Install the plugin (recommended)

/plugin marketplace add Wirasm/PRPs-agentic-eng
/plugin install prp-core@prp-marketplace

Every skill is then available across all your projects as `/prp-core:<name>`, updated centrally.

Option 2: Copy the skills you want

# From your project root — copy individual skills (or the whole folder)
cp -r /path/to/PRPs-agentic-eng/.claude/skills/prp-plan .claude/skills/

Option 3: Clone the repository

git clone https://github.com/Wirasm/PRPs-agentic-eng.git
cd PRPs-agentic-eng

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "prp-marketplace",
  3. "description": "PRP (Product Requirement Prompt) workflow automation tools and methodology",
  4. "owner": {
  5. "name": "Wirasm",
  6. "email": "contact@wirasm.com"
  7. },
  8. "plugins": [
  9. {
  10. "name": "prp-core",
  11. "source": "./plugins/prp-core",
  12. "description": "Complete PRP workflow automation as agent skills - prd, plan, implement, review, commit, PR, an autonomous build loop, and specialized agents"
  13. }
  14. ]
  15. }
README.md · README · 333 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # PRP (Product Requirement Prompts)
  2. A collection of prompts for AI-assisted development with Claude Code.
  3. ## Video Walkthrough
  4. https://www.youtube.com/watch?v=KVOZ9s1S9Gk&lc=UgzfwxvFjo6pKEyPo1R4AaABAg
  5. ### Support This Work
  6. **Found value in these resources?**
  7. **Buy me a coffee:** https://coff.ee/wirasm
  8. I spent a considerable amount of time creating these resources and prompts. If you find value in this project, please consider buying me a coffee to support my work.
  9. ---
  10. ### Transform Your Team with AI Engineering Workshops
  11. **Ready to move beyond toy demos to production-ready AI systems?**
  12. **Book a workshop:** https://www.rasmuswiding.com/
  13. **What you'll get:**
  14. - Put your team on a path to become AI power users
  15. - Learn the exact PRP methodology used by top engineering teams
  16. - Hands-on training with Claude Code, PRPs, and real codebases
  17. - From beginner to advanced AI engineering workshops for teams and individuals
  18. **Perfect for:** Engineering teams, Product teams, and developers who want AI that actually works in production
  19. Contact me directly at hello@rasmuswiding.com
  20. ---
  21. ## What is PRP?
  22. **Product Requirement Prompt (PRP)** = PRD + curated codebase intelligence + agent/runbook
  23. The minimum viable packet an AI needs to ship production-ready code on the first pass.
  24. A PRP supplies an AI coding agent with everything it needs to deliver a vertical slice of working software—no more, no less.
  25. ### How PRP Differs from Traditional PRD
  26. A traditional PRD clarifies _what_ the product must do and _why_ customers need it, but deliberately avoids _how_ it will be built.
  27. A PRP keeps the goal and justification sections of a PRD yet adds AI-critical layers:
  28. - **Context**: Precise file paths, library versions, code snippet examples
  29. - **Patterns**: Existing codebase conventions to follow
  30. - **Validation**: Executable commands the AI can run to verify its work
  31. ---
  32. ## Quick Start
  33. ### Option 1: Install the plugin (recommended)
  34. ```bash
  35. /plugin marketplace add Wirasm/PRPs-agentic-eng
  36. /plugin install prp-core@prp-marketplace
  37. ```
  38. Every skill is then available across all your projects as `/prp-core:<name>`, updated centrally.
  39. ### Option 2: Copy the skills you want
  40. ```bash
  41. # From your project root — copy individual skills (or the whole folder)
  42. cp -r /path/to/PRPs-agentic-eng/.claude/skills/prp-plan .claude/skills/
  43. ```
  44. ### Option 3: Clone the repository
  45. ```bash
  46. git clone https://github.com/Wirasm/PRPs-agentic-eng.git
  47. cd PRPs-agentic-eng
  48. ```
  49. ---
  50. ## Skills
  51. The `.claude/skills/` directory contains the core PRP workflow as Agent Skills — also distributed as the `prp-core` plugin (invoke as `/prp-core:<name>`):
  52. ### Core Workflow
  53. | Command | Description |
  54. | ---------------- | -------------------------------------------------------- |
  55. | `/prp-prd` | Interactive PRD generator with implementation phases |
  56. | `/prp-plan` | Create implementation plan (from PRD or free-form input) |
  57. | `/prp-implement` | Execute a plan through validated commit and PR |
  58. | `/prp-issue` | Own an issue, plan, document, or idea through reviewed PR and green CI |
  59. | `/prp-issue-contract` | Create an issue or check its preconditions before agent automation |
  60. | `/prp-prd-update` | Maintain PRD phase status and delivery links |
  61. | `/prp-companion` | Visual HTML companion of a plan or review, beside its markdown |
  62. ### Debug Workflow
  63. | Command | Description |
  64. | ------------------------ | ------------------------------------------------ |
  65. | `/prp-debug` | Diagnose a root cause and publish the evidence to the matching GitHub issue |
  66. ### Maintainer Triage
  67. This skill requires explicit invocation because it can comment, label, or close another person's contribution.
  68. | Command | Description |
  69. | ------- | ----------- |
  70. | `/prp-maintainer-triage` | Route a contributor PR or reported issue through its lightweight maintainer triage workflow |
  71. ### Git & Review
  72. | Command | Description |
  73. | ------------- | ------------------------------------------------- |
  74. | `/prp-commit` | Smart commit with natural language file targeting |
  75. | `/prp-pr` | Create PR with template support |
  76. | `/prp-review` | Comprehensive PR code review |
  77. ### Autonomous Loop
  78. | Command | Description |
  79. | ----------- | --------------------------------------------------------------------- |
  80. | `/prp-loop` | Autonomous pipeline: plan → implement with PR → review (review→fix loops until clean) |
  81. | `/prp-orchestrate` | Coordinate parallel workstreams running PRP skills in git worktrees, with review gates and merge sequencing |
  82. ### In Process
  83. | Command | Description |
  84. | ------- | ----------- |
  85. | `/prp-deliver` | Manual-only, top-level multi-context delivery experiment; excluded from distribution and orchestration |
  86. ### Research & Authoring
  87. | Command | Description |
  88. | ------------------------ | ------------------------------------------------------------------------ |
  89. | `/prp-codebase-question` | Research how the codebase works using parallel agents |
  90. | `/prp-research-team` | Design a multi-agent research team and executable research plan |
  91. | `/prp-meta-skill` | Author new skills, or refactor fat skills into lean SKILL.md + references |
  92. | `/prp-technical-writing` | Write and edit developer documentation that is clear, concrete, and verified |
  93. ---
  94. ## PRP Loop (Autonomous Execution)
  95. `/prp-loop` drives the full pipeline (`plan → implement with commit and PR → review`) headlessly, running one `claude -p` session per stage and looping `review → fix` until the PR review comes back clean. Progress is tracked in the project's PRP store at `~/.prp/<project-key>/state/prp-loop.state.json`.
  96. ### How It Works
  97. ```
  98. /prp-loop "add user authentication with JWT"
  99. ```
  100. 1. **plan** — writes `~/.prp/<project-key>/plans/<feature>.plan.md`
  101. 2. **implement** — executes and validates the plan, commits the work, and opens the PR
  102. 3. **pr compatibility** — opens the PR only if an older implementation run did not
  103. 4. **review** — publishes the complete canonical review report to the PR
  104. 5. **cycle** — if fixes are needed, the full report feeds a correction pass → push → re-review, until ready or `--max-cycles` is reached
  105. ### Usage
  106. ```bash
  107. # Run the full pipeline from a feature description
  108. /prp-loop "add user authentication with JWT"
  109. # Run through implementation and PR, then stop before review
  110. /prp-loop "add user authentication with JWT" --until implement
  111. # Resume a halted or in-progress loop
  112. /prp-loop --resume
  113. ```
  114. ### Tips
  115. - `--until <stage>` (`plan` | `implement` | `pr` | `review` | `fix`) halts once that stage completes; `--until implement` stops after the implementation is green, committed, and opened as a PR
  116. - Defaults: `--max-cycles 3`, `--max-implement-iterations 10`; base branch is auto-detected
  117. - Pass `--validate "<cmd>"` to give the loop an authoritative green check (exit 0 = pass)
  118. - Works best with plans that have clear, testable validation commands
  119. - State is tracked in `~/.prp/<project-key>/state/prp-loop.state.json`; inspect or resume from there
  120. ---
  121. ## Workflow Overview
  122. ### Large Features: PRD → Plan → Implement
  123. ```
  124. /prp-prd "user authentication system"
  125. ↓
  126. Creates PRD with Implementation Phases table
  127. ↓
  128. /prp-plan ~/.prp/<project-key>/prds/user-auth.prd.md
  129. ↓
  130. Auto-selects next pending phase, creates plan
  131. ↓
  132. /prp-implement ~/.prp/<project-key>/plans/user-auth-phase-1.plan.md
  133. ↓
  134. Implements and validates, then commits and opens a PR
  135. ↓
  136. Links the plan, report, and PR back to the source PRD
  137. ↓
  138. /prp-review
  139. ```
  140. ### Medium Features: Direct to Plan
  141. ```
  142. /prp-plan "add pagination to the API"
  143. ↓
  144. Creates implementation plan from description
  145. ↓
  146. /prp-implement ~/.prp/<project-key>/plans/add-pagination.plan.md
  147. ```
  148. ### Any Work: Input to Reviewed PR and Green CI
  149. ```
  150. /prp-issue 123
  151. ↓
  152. Creates or resolves the plan, implements it, commits, and opens the PR
  153. ↓
  154. Publishes the complete agent review on the PR
  155. ↓
  156. Fixes or disproves review findings, re-reviews, and waits for green CI
  157. ```
  158. ---
  159. ## Artifacts Structure
  160. Artifacts and runtime state are stored outside the repository in a per-project directory:
  161. ```
  162. ~/.prp/<project-key>/
  163. ├── project.json # Canonical project path and name
  164. ├── prds/ # Product requirement documents
  165. ├── plans/ # Implementation plans
  166. ├── research/ # Codebase research
  167. ├── research-plans/ # Multi-agent research plans
  168. ├── reports/ # Implementation reports
  169. ├── reviews/ # Human-readable PR reviews
  170. ├── debug/ # Root-cause analysis reports
  171. ├── orchestration/ # Parallel-workstream run files
  172. └── state/ # Loop state, logs, and hook sentinels
  173. ```
  174. The project key is derived from the canonical main-checkout path, so all linked worktrees share the same store. Set `PRP_HOME` to override the default `~/.prp` root.
  175. ---
  176. ## PRD Phases
  177. PRDs include an Implementation Phases table for tracking progress:
  178. ```markdown
  179. | # | Phase | Description | Status | Parallel | Depends | Plan | Report | PR |
  180. | --- | ----- | ----------- | ----------- | -------- | ------- | ------ | ------ | ------ |
  181. | 1 | Auth | User login | complete | - | - | [link] | [link] | [link] |
  182. | 2 | API | Endpoints | in-progress | - | 1 | [link] | [link] | [link] |
  183. | 3 | UI | Frontend | pending | with 4 | 2 | - | - | - |
  184. | 4 | Tests | Test suite | pending | with 3 | 2 | - | - | - |
  185. ```
  186. - **Status**: `pending` → `in-progress` → `complete`
  187. - **Parallel**: Phases that can run concurrently (in separate worktrees)
  188. - **Depends**: Phases that must complete first
  189. ---
  190. ## PRP Best Practices
  191. 1. **Context is King**: Include ALL necessary documentation, examples, and caveats
  192. 2. **Validation Loops**: Provide executable tests/lints the AI can run and fix
  193. 3. **Information Dense**: Use keywords and patterns from the codebase
  194. 4. **Bounded Scope**: Each plan should be completable by an AI in one loop
  195. ---
  196. ## Project Structure
  197. ```
  198. your-project/
  199. ├── .claude/
  200. │ ├── skills/ # PRP skills (or install the prp-core plugin)
  201. │ └── agents/ # Custom subagents
  202. ├── CLAUDE.md # Project-specific guidelines
  203. └── src/ # Your source code
  204. ```
  205. ---
  206. ## Parallel Development with Worktrees
  207. When PRD phases can run in parallel:
  208. ```bash
  209. # Phase 3 and 4 can run concurrently
  210. git worktree add -b phase-3-ui ../project-phase-3
  211. git worktree add -b phase-4-tests ../project-phase-4
  212. # Run Claude in each
  213. cd ../project-phase-3 && claude
  214. cd ../project-phase-4 && claude
  215. ```
  216. ---
  217. ## Resources
  218. ### Legacy Commands, Templates & Docs
  219. The previous slash-command generation is preserved in `old-prp-commands/` for reference only. That includes its PRP templates (`old-prp-commands/PRPs/templates/` — `prp_base.md`, `prp_story_task.md`, `prp_planning.md`) and curated AI documentation (`old-prp-commands/PRPs/ai_docs/`). The current skills carry their templates inline or in their own `templates/` directories.
  220. ---
  221. ## License
  222. MIT — see [LICENSE](LICENSE).
  223. ---
  224. ## Support
  225. I spent a considerable amount of time creating these resources and prompts. If you find value in this project, please consider buying me a coffee to support my work.
  226. **Buy me a coffee:** https://coff.ee/wirasm
  227. ---
  228. **The goal is one-pass implementation success through comprehensive context.**

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.