By rodrigorjsf
AI-powered PRD generator with official-source research validation, self-evolving project skills, CI/CD pipeline generation, and local documentation cache for AI-assisted development
---
Use this agent to generate or update CI/CD pipeline files based on VCS choice (GitHub/GitLab/Bitbucket) and current architecture stack. Generates lean, essential pipelines with path-filtering per service for monorepos. Operates in full (initial) or update (evolution) mode.
---
---
---
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An AI-powered Claude Code plugin that transforms a product idea into a complete, research-backed PRD with modern architecture design, enforcement skills, CI/CD pipeline, documentation cache infrastructure, and self-evolving project documentation — ready for AI-assisted development.
Given a product idea, this plugin:
Install via Claude Code plugin system:
claude plugin install prd-generator-plugin
Or clone and install locally:
git clone https://github.com/rodrigo/prd-generator-plugin
claude plugin install ./prd-generator-plugin
/prd-new
# or with an initial description:
/prd-new "A B2B SaaS platform for managing construction project budgets"
/prd-evolve "Added Pix payment integration and BACEN compliance requirements"
/prd-evolve "Removed mobile app from scope, focusing on web-only MVP"
/prd-evolve "Changed database from MySQL to PostgreSQL for JSONB support"
/prd-newflowchart TD
A(["/prd-new initial description"]) --> B
subgraph PHASE1["Phase 1 — Interactive Interrogation"]
B["Block 1: Identity\nname, vision, users, problem"]
B --> C["Block 2: Business\nmonetization, KPIs, scale"]
C --> D["Block 3: Core Features\nMVP list, real-time, mobile"]
D --> E["Block 4: Regulatory\nGDPR/LGPD, payments, sector"]
E --> F["Block 5: Integrations\nexternal APIs, auth providers"]
F --> G["Block 6: Infrastructure\ncloud, SLA, budget, geo, VCS, branch strategy"]
G --> H["Block 7: Stack Preference\nAI-suggested or user-defined"]
end
subgraph PHASE2["Phase 2 — Official Research (parallel)"]
I["official-researcher × N\nparallel instances\nblocked: forums, blogs, wikis"]
J["research-validator\nFRESH CONTEXT\nverifies accuracy + officiality"]
K{Approved?}
I --> J --> K
K -->|"no (max 3x)"| I
end
subgraph PHASE3["Phase 3 — Analysis"]
L["requirements-analyst\nRF / RNF / domain rules\ncompliance / acceptance criteria"]
end
subgraph PHASE4["Phase 4 — Architecture"]
M["architecture-designer\nmodern stack selection\nMermaid diagrams + ADRs"]
N{User approves\narchitecture?}
M --> N
N -->|"adjust"| M
end
subgraph PHASE5["Phase 5 — Generation (parallel)"]
O["prd-writer\nPRD.md\nARCHITECTURE.md\nER.md"]
P["stack-guide-generator\nbackend/CLAUDE.md\nfrontend/CLAUDE.md\ninfrastructure/CLAUDE.md\ndocs/stack/ + .claude/settings.json"]
Q["skills-generator\nproject-guardian\nproject-architecture\nproject-domain-rules\nproject-compliance\nproject-docs-stack\nproject-cicd"]
R2["cicd-generator\n.github/workflows/ci.yml\n(or .gitlab-ci.yml\nor bitbucket-pipelines.yml)"]
end
R[("git commit\nall artifacts")]
B -->|"tech/domain identified"| I
K -->|yes| L
H --> L
L --> M
N -->|approved| O & P & Q & R2
O & P & Q & R2 --> R
flowchart LR
A["official-researcher\nWebSearch + WebFetch\nbanned: forums/blogs/social"] -->|research_refs| B
B["research-validator\n🔴 FRESH CONTEXT\nno prior session memory"] --> C{Approved?}
C -->|"✅ yes"| D[("research_refs\nvalidated")]
C -->|"❌ issues found\nmax 3 iterations"| E["re-research\nwith correction\nguidance"]
E --> A
C -->|"3rd attempt fails"| F["mark as\npartially_validated\nlog issues for user"]
Evidence-based AGENTS.md and CLAUDE.md initializer and optimizer. Generates minimal, scoped configuration files following progressive disclosure principles — based on the ETH Zurich 'Evaluating AGENTS.md' study and Anthropic's context engineering best practices.
npx claudepluginhub rodrigorjsf/prd-generator-pluginUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
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.
Complete developer toolkit for Claude Code