From blueprint-plugin
Creates PRP (Product Requirement Prompt) combining PRD, codebase pattern research, external documentation, implementation blueprint, and validation gates for AI agent feature implementation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/blueprint-plugin:blueprint-prp-createsonnetThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create a comprehensive PRP (Product Requirement Prompt) - a self-contained packet with all context an AI agent needs to deliver production code on first attempt.
Create a comprehensive PRP (Product Requirement Prompt) - a self-contained packet with all context an AI agent needs to deliver production code on first attempt.
What is a PRP? PRD + Curated Codebase Intelligence + Implementation Blueprint + Validation Gates = everything needed for reliable implementation.
Usage: /blueprint:prp-create [feature-name]
Prerequisites:
docs/blueprint/ exists)| Use this skill when... | Use alternative when... |
|---|---|
| Creating new feature implementation packet | Executing an existing PRP (use /blueprint:prp-execute) |
| Want comprehensive research and documentation | Quick prototyping without formal requirements |
| Planning for AI agent or subagent execution | Solo developer implementing without research |
| Need to document implementation approach | Implementing based on existing codebase patterns |
find docs/blueprint -maxdepth 1 -name 'manifest.json' -type fjq -r '.id_registry.last_prp // 0' docs/blueprint/manifest.jsonfind docs/blueprint/ai_docs -type f -name "*.md"find docs/prds -name "*.md" -type fParse $ARGUMENTS:
feature-name (required): Kebab-case name for PRP (e.g., auth-oauth2, api-rate-limiting)
Execute the complete PRP creation workflow:
/blueprint:init first"Use Explore agent to find existing patterns:
Store findings with specific file paths and line numbers.
For relevant libraries/frameworks, gather:
Use WebSearch/WebFetch as needed. Create or update ai_docs entries if needed (see REFERENCE.md).
Generate next PRP ID from manifest:
id_registry.last_prp from manifest.jsonPRP-NNN)Create docs/prps/[feature-name].md with frontmatter and sections (see REFERENCE.md).
Fill all required sections (see REFERENCE.md):
Critical: All tasks must be explicitly categorized (see REFERENCE.md).
Rate each dimension 1-10:
| Dimension | Criteria |
|---|---|
| Context Completeness | Are all file paths, code snippets, and references explicit? |
| Implementation Clarity | Is pseudocode clear enough for AI to follow? |
| Gotchas Documented | Are all known pitfalls documented with mitigations? |
| Validation Coverage | Are all validation gates with executable commands? |
Calculate overall score as average of dimensions. Target: 7+ for execution, 9+ for subagent delegation.
If score < 7 → Return to Steps 2-3 to fill gaps.
Verify checklist (see REFERENCE.md):
Update docs/blueprint/manifest.json ID registry with new PRP entry.
Display summary showing:
If confidence >= 7, offer user choices:
/blueprint:prp-execute [feature-name]/blueprint:work-orderIf confidence < 7, offer user choices:
/blueprint:curate-docs| Context | Command |
|---|---|
| Check blueprint init | test -f docs/blueprint/manifest.json && echo "YES" || echo "NO" |
| Next PRP ID | jq -r '.id_registry.last_prp // 0' docs/blueprint/manifest.json | awk '{print $1+1}' |
| List existing PRPs | ls -1 docs/prps/ 2>/dev/null | wc -l |
| Search for patterns | Use Explore agent instead of manual grep |
| Fast research | Use existing ai_docs rather than fetching docs again |
For PRP document structure, task categorization, review checklists, and ai_docs creation guidance, see REFERENCE.md.
npx claudepluginhub laurigates/claude-plugins --plugin blueprint-pluginGenerates Product Requirement Plans (PRPs) for feature implementation via systematic codebase analysis and external research. Use when requesting PRP, PRD, or detailed implementation plans.
Generates Product Requirements Documents (PRDs) for new features via phased approach: discovery, codebase exploration with agents, clarifying questions. Useful for feature planning or project starts.
Generates a structured Product Requirements Document (PRD) from feature descriptions. Analyzes codebase (package.json, configs, README), processes references, asks clarifying questions, saves to .plans/. Use for new feature planning.