blueprint-generate-rules

Generate project-specific rules from Product Requirements Documents.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "blueprint-generate-rules" with this command: npx skills add laurigates/claude-plugins/laurigates-claude-plugins-blueprint-generate-rules

Generate project-specific rules from Product Requirements Documents.

When to Use This Skill

Use this skill when... Use alternative when...

Need to generate rules from existing PRDs Use /blueprint:rules to manually create/edit rules

Want path-scoped rules for specific file types Use /blueprint:claude-md for general project instructions

Automating rule creation from requirements Writing custom rules without PRD reference

Extracting architecture/testing patterns from PRDs Need to create one-off rules for specific contexts

Rules are generated to .claude/rules/ directory. Rules with paths frontmatter are loaded conditionally when working on matching files.

Prerequisites:

  • docs/prds/ directory exists

  • At least one PRD file in docs/prds/

Steps:

Find and read all PRDs:

  • Use Glob to find all .md files in docs/prds/

  • Read each PRD file

  • If no PRDs found, report error and suggest writing PRDs first

Check for existing generated rules:

ls .claude/rules/ 2>/dev/null

  • If rules exist, check manifest for content hashes

  • Compare current content hash vs stored hash

  • If modified, offer options: overwrite, skip, or backup

Analyze PRDs and extract (aggregated from all PRDs):

Architecture Patterns:

  • Project structure and organization

  • Architectural style (MVC, layered, hexagonal, etc.)

  • Design patterns

  • Dependency injection approach

  • Error handling strategy

  • Code organization conventions

  • Integration patterns

Testing Strategies:

  • TDD workflow requirements

  • Test types (unit, integration, e2e)

  • Mocking patterns

  • Coverage requirements

  • Test structure and organization

  • Test commands

Implementation Guides:

  • How to implement APIs/endpoints

  • How to implement UI components (if applicable)

  • Database operation patterns

  • External service integration patterns

  • Background job patterns (if applicable)

Quality Standards:

  • Code review checklist

  • Performance baselines

  • Security requirements (OWASP, validation, auth)

  • Code style and formatting

  • Documentation requirements

  • Dependency management

Generate four aggregated domain rules:

Create in .claude/rules/ :

architecture-patterns.md :

  • Aggregated patterns from all PRDs

  • Fill in project-specific patterns extracted from PRDs

  • Include code examples where possible

  • Reference specific files/directories

testing-strategies.md :

  • Aggregated testing requirements from all PRDs

  • Fill in TDD requirements from PRDs

  • Include coverage requirements

  • Include test commands for the project

  • Add paths frontmatter if tests live in specific directories:


paths:

  • "tests/**/*"
  • "**/.{test,spec}."

implementation-guides.md :

  • Aggregated implementation patterns from all PRDs

  • Fill in step-by-step patterns for feature types

  • Include code examples

  • Scope to source paths if applicable:


paths:

  • "src/**/*"
  • "lib/**/*"

quality-standards.md :

  • Aggregated quality requirements from all PRDs

  • Fill in performance baselines from PRDs

  • Fill in security requirements from PRDs

  • Create project-specific checklist

Path-scoping guidance: Add paths frontmatter when a rule only applies to specific file types or directories. This reduces context noise — Claude only loads the rule when working on matching files. Use brace expansion for concise patterns: .{ts,tsx} , src/{api,routes}/**/ .

Update manifest with generation tracking:

{ "generated": { "rules": { "architecture-patterns": { "source": "docs/prds/*", "source_hash": "sha256:...", "generated_at": "[ISO timestamp]", "plugin_version": "3.0.0", "content_hash": "sha256:...", "status": "current" }, "testing-strategies": { ... }, "implementation-guides": { ... }, "quality-standards": { ... } } } }

Update task registry:

Update the task registry entry in docs/blueprint/manifest.json :

jq --arg now "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
--argjson processed "${PRDS_READ:-0}"
--argjson created "${RULES_GENERATED:-0}"
'.task_registry["generate-rules"].last_completed_at = $now | .task_registry["generate-rules"].last_result = "success" | .task_registry["generate-rules"].context.source_prd_hashes = ($source_prd_hashes // {}) | .task_registry["generate-rules"].stats.runs_total = ((.task_registry["generate-rules"].stats.runs_total // 0) + 1) | .task_registry["generate-rules"].stats.items_processed = $processed | .task_registry["generate-rules"].stats.items_created = $created'
docs/blueprint/manifest.json > tmp.json && mv tmp.json docs/blueprint/manifest.json

For source_prd_hashes , compute sha256sum of each PRD file and pass as a JSON object via --argjson .

Report:

Rules generated from PRDs!

Created in .claude/rules/:

  • architecture-patterns.md
  • testing-strategies.md
  • implementation-guides.md
  • quality-standards.md

PRDs analyzed:

  • docs/prds/[List PRD files]

Key patterns extracted:

  • Architecture: [Brief summary]
  • Testing: [Brief summary]
  • Implementation: [Brief summary]
  • Quality: [Brief summary]

Rules are immediately available - Claude auto-discovers them based on context!

Prompt for next action (use AskUserQuestion):

question: "Rules generated. What would you like to do next?" options:

  • label: "Generate workflow commands (Recommended)" description: "Create /project:continue and /project:test-loop commands"
  • label: "Update CLAUDE.md" description: "Regenerate project overview document with new rules"
  • label: "Review generated rules" description: "I'll examine and refine the rules manually"
  • label: "I'm done for now" description: "Exit - rules are already available"

Based on selection:

  • "Generate workflow commands" -> Run /blueprint:generate-commands

  • "Update CLAUDE.md" -> Run /blueprint:claude-md

  • "Review generated rules" -> Show rule file locations and exit

  • "I'm done for now" -> Exit

Important:

  • Rules should be markdown files with clear headings

  • Keep rule content specific and focused

  • Include code examples to make patterns concrete

  • Reference PRD sections for traceability

  • Rules should be actionable, not just documentation

Error Handling:

  • If no PRDs found -> Guide user to derive PRDs first (/blueprint:derive-prd )

  • If PRDs incomplete -> Generate rules with TODO markers for missing sections

  • If rules already exist and modified -> Offer to backup before overwriting

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

ruff linting

No summary provided by upstream source.

Repository SourceNeeds Review
General

imagemagick-conversion

No summary provided by upstream source.

Repository SourceNeeds Review
General

jq json processing

No summary provided by upstream source.

Repository SourceNeeds Review
General

uv-project-management

No summary provided by upstream source.

Repository SourceNeeds Review