blueprint
Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.
About this skill
The Blueprint skill empowers AI agents to transform a high-level, single-line objective into a detailed, executable construction plan for software development. Each step in the generated plan is meticulously crafted to be self-contained, including a comprehensive context brief. This design ensures that any fresh coding agent, even one starting a new session without prior conversation history, can seamlessly pick up and execute any specific step independently. This capability is crucial for managing intricate, separate-session, or multi-agent engineering projects where continuity and context independence are paramount. Install it once and invoke it with `/blueprint <project> <objective>`.
Best use case
Streamlining complex software development by breaking down a high-level project goal into atomic, independently actionable stages. It is ideal for orchestrating development across different AI agent sessions or a team of specialized agents, ensuring each can contribute effectively without requiring full historical context.
Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.
A comprehensive, ordered list of development steps, each accompanied by a clear, self-contained context brief. This plan enables a coding agent to understand, execute, and verify each step in isolation, contributing to the overall project objective efficiently.
Practical example
Example input
/blueprint my-project "Implement a user authentication system with OAuth2 and JWT"
Example output
Project: my-project Objective: Implement a user authentication system with OAuth2 and JWT Step 1: Set up basic project structure and dependencies. Context: This step involves initializing a new project (e.g., Node.js with Express, Python with Flask/Django) and installing core dependencies for web server, routing, and environment management. Ensure a .env file is configured for sensitive variables. Expected outcome: Project initialized, basic server running, core dependencies installed. Step 2: Integrate OAuth2 provider (e.g., Google, GitHub). Context: This step focuses on configuring and integrating a chosen OAuth2 provider. This includes setting up developer credentials, defining callback URLs, and implementing the initial redirection to the OAuth provider and handling the callback to exchange authorization code for tokens. Expected outcome: Users can initiate OAuth flow and return to application with an authorization code. Step 3: Implement JWT token generation and storage. Context: After successful OAuth authentication, this step involves generating a JSON Web Token (JWT) for the authenticated user. The JWT should contain necessary user information and be signed with a secure secret. Implement mechanisms to securely store this token (e.g., http-only cookies, local storage with caution). Expected outcome: Upon successful authentication, a JWT is generated and returned to the client for subsequent requests. Step 4: Create authentication middleware for protected routes. Context: Develop middleware that intercepts incoming requests to protected API endpoints. This middleware will verify the JWT's validity (signature, expiration) and extract user information, making it available in the request object for subsequent handlers. Expected outcome: Protected routes enforce JWT authentication, denying access to unauthenticated requests and providing user context for authenticated ones. Step 5: Implement user profile management endpoints. Context: Create API endpoints for authenticated users to view and potentially update their profile information. These endpoints must be protected by the JWT authentication middleware implemented in the previous step. Expected outcome: Authenticated users can access and manage their profile data through secure API endpoints.
When to use this skill
- When a development task is large or complex enough to require several pull requests (PRs) or iterations.
- When collaborating with a team of AI agents, each potentially specialized, where independent execution of tasks is beneficial.
- When resuming work on a project after a break, allowing a new agent instance to pick up from any point in the plan without needing past session data.
- For projects requiring robust, restartable, and fault-tolerant execution across different agent sessions.
When not to use this skill
- For simple, single-step tasks that do not benefit from detailed planning or contextual independence.
- When the entire task can be completed by a single agent in a single, continuous session without interruptions.
- For tasks that are not related to code construction or project planning.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/blueprint/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How blueprint Compares
| Feature / Agent | blueprint | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Blueprint — Construction Plan Generator Turn a one-line objective into a step-by-step plan any coding agent can execute cold. ## Overview Blueprint is for multi-session, multi-agent engineering projects where each step must be independently executable by a fresh agent that has never seen the conversation history. Install it once, invoke it with `/blueprint <project> <objective>`. ## When to Use This Skill - Use when the task requires multiple PRs or sessions - Use when multiple agents or team members need to share execution - Use when you want adversarial review of the plan before execution - Use when parallel step detection and dependency graphs matter ## How It Works 1. **Research** — Scans the codebase, reads project memory, runs pre-flight checks 2. **Design** — Breaks the objective into one-PR-sized steps, identifies parallelism, assigns model tiers 3. **Draft** — Generates the plan from a structured template with branch workflow rules, CI policy, and rollback strategies inline 4. **Review** — Delegates adversarial review to a strongest-model sub-agent (falls back to default model if unavailable) 5. **Register** — Saves the plan and updates project memory ## Examples ### Example 1: Database migration ``` /blueprint myapp "migrate database to PostgreSQL" ``` ### Example 2: Plugin extraction ``` /blueprint antbot "extract providers into plugins" ``` ## Best Practices - ✅ Use for tasks requiring 3+ PRs or multiple sessions - ✅ Let Blueprint auto-detect git/gh availability — it degrades gracefully - ❌ Don't invoke for tasks completable in a single PR - ❌ Don't invoke when the user says "just do it" ## Key Differentiators - **Cold-start execution**: Every step has a self-contained context brief - **Adversarial review gate**: Strongest-model review before execution - **Zero runtime risk**: Pure markdown — no hooks, no scripts, no executable code - **Plan mutation protocol**: Steps can be split, inserted, skipped with audit trail ## Installation ```bash mkdir -p ~/.claude/skills git clone https://github.com/antbotlab/blueprint.git ~/.claude/skills/blueprint ``` ## Additional Resources - [GitHub Repository](https://github.com/antbotlab/blueprint) - [Examples: small plan](https://github.com/antbotlab/blueprint/blob/main/examples/small-plan.md) - [Examples: large plan](https://github.com/antbotlab/blueprint/blob/main/examples/large-plan.md)
Related Skills
nft-standards
Master ERC-721 and ERC-1155 NFT standards, metadata best practices, and advanced NFT features.
nextjs-app-router-patterns
Comprehensive patterns for Next.js 14+ App Router architecture, Server Components, and modern full-stack React development.
new-rails-project
Create a new Rails project
networkx
NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.
network-engineer
Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization.
nestjs-expert
You are an expert in Nest.js with deep knowledge of enterprise-grade Node.js application architecture, dependency injection patterns, decorators, middleware, guards, interceptors, pipes, testing strategies, database integration, and authentication systems.
nerdzao-elite
Senior Elite Software Engineer (15+) and Senior Product Designer. Full workflow with planning, architecture, TDD, clean code, and pixel-perfect UX validation.
nerdzao-elite-gemini-high
Modo Elite Coder + UX Pixel-Perfect otimizado especificamente para Gemini 3.1 Pro High. Workflow completo com foco em qualidade máxima e eficiência de tokens.
native-data-fetching
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).
n8n-workflow-patterns
Proven architectural patterns for building n8n workflows.
n8n-validation-expert
Expert guide for interpreting and fixing n8n validation errors.
n8n-node-configuration
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type.