create-blueprint
$
npx mdskill add TheBushidoCollective/han/create-blueprintResearch systems and generate accurate blueprint documentation.
- Creates technical design documents for any specified system.
- Uses glob and grep to locate relevant implementation files.
- Prioritizes repository root location for all blueprint files.
- Outputs markdown files directly to the blueprints directory.
SKILL.md
.github/skills/create-blueprintView on GitHub ↗
---
name: create-blueprint
description: Research a specific system and create or update its blueprints/ documentation
---
## Name
blueprints:create-blueprint - Generate or update blueprint documentation for a specific system
## Synopsis
```text
/blueprint <system-name>
```
## Description
Research a specific system in the codebase and create or update its technical blueprint documentation in the `blueprints/` directory at the **repository root**.
## Important: Blueprint Location
**CRITICAL:** Blueprints MUST be created at the repository root, never in subdirectories or packages.
- `{repo-root}/blueprints/{system-name}.md`
- `{repo-root}/packages/foo/blueprints/{system-name}.md`
- `{repo-root}/src/blueprints/{system-name}.md`
Blueprints are repository-wide system design documents. A single system may span multiple packages or directories, but there should be ONE blueprint at the repo root describing the entire system.
## Implementation
You are tasked with creating or updating technical blueprint documentation for a specific system.
## Process
### 1. Identify the Target System
The user will specify which system to document. This could be:
- A feature name (e.g., "authentication", "caching")
- A directory path (e.g., "lib/commands/mcp")
- A component name (e.g., "MCP server", "hook dispatcher")
### 2. Deep Research Phase
Thoroughly investigate the system:
1. **Find all relevant files** using Glob and Grep
2. **Read the implementation** to understand:
- Entry points and public APIs
- Internal architecture and data flow
- Dependencies and integrations
- Configuration options
- Error handling and edge cases
3. **Check for existing documentation**:
- README files in the directory
- Inline code comments
- Existing blueprints/ files
- Test files (they document expected behavior)
### 3. Check for Duplicates
Before creating a new blueprint, check what already exists:
1. **List all blueprints**: Use `Glob("blueprints/*.md")` to see all existing blueprint files
2. **Search by keyword**: Use `Grep` to search frontmatter in `blueprints/` for related topics
3. **Read related blueprints**: Use `Read("blueprints/{related-name}.md")` to check for overlap
4. **Identify overlapping systems** that should be documented together
### 4. Write the Blueprint
Use the `Write` tool to create or update the blueprint file at `blueprints/{system-name}.md`.
The file MUST include YAML frontmatter:
```markdown
---
name: system-name
summary: Brief one-line description
---
# {System Name}
...
```
The blueprint content should follow this structure:
```markdown
---
name: system-name
summary: Brief one-line description
---
# {System Name}
{Brief one-line description}
## Overview
{2-3 paragraphs explaining the system's purpose, why it exists, and its role in the larger system}
## Architecture
{Describe the system structure}
### Components
- **{Component A}** - {description}
- **{Component B}** - {description}
### Data Flow
{How data moves through the system}
### Dependencies
- {Dependency 1} - {why it's needed}
- {Dependency 2} - {why it's needed}
## API / Interface
### Public Functions/Methods
#### `functionName(params)`
{Description}
**Parameters:**
- `param1` (type) - {description}
**Returns:** {description}
### Commands
{If applicable, document CLI commands}
### Configuration
{Document configuration options}
## Behavior
### Normal Operation
{How the system behaves under normal conditions}
### Error Handling
{How errors are handled}
### Edge Cases
{Notable edge cases and how they're handled}
## Files
Key implementation files:
- `path/to/main.ts` - {brief description}
- `path/to/helper.ts` - {brief description}
## Related Systems
- [{Related System}](./related-system.md) - {relationship description}
```
## Output
After completing the research and documentation:
1. Create/update the blueprint using `Write("blueprints/{system-name}.md", content)`
2. Report what was documented and any related systems that may need documentation
**Note:** The blueprint index at `.claude/rules/blueprints/blueprints-index.md` is automatically regenerated by the SessionStart hook - you don't need to manually update it.
More from TheBushidoCollective/han
- absinthe-resolversUse when implementing GraphQL resolvers with Absinthe. Covers resolver patterns, dataloader integration, batching, and error handling.
- absinthe-schemaUse when designing GraphQL schemas with Absinthe. Covers type definitions, interfaces, unions, enums, and schema organization patterns.
- absinthe-subscriptionsUse when implementing real-time GraphQL subscriptions with Absinthe. Covers Phoenix channels, PubSub, and subscription patterns.
- act-docker-setupUse when configuring Docker environments for act, selecting runner images, managing container resources, or troubleshooting Docker-related issues with local GitHub Actions testing.
- act-local-testingUse when testing GitHub Actions workflows locally with act. Covers act CLI usage, Docker configuration, debugging workflows, and troubleshooting common issues when running workflows on your local machine.
- act-workflow-syntaxUse when creating or modifying GitHub Actions workflow files. Provides guidance on workflow syntax, triggers, jobs, steps, and expressions for creating valid GitHub Actions workflows that can be tested locally with act.
- ameba-configurationUse when configuring Ameba rules and settings for Crystal projects including .ameba.yml setup, rule management, severity levels, and code quality enforcement.
- ameba-custom-rulesUse when creating custom Ameba rules for Crystal code analysis including rule development, AST traversal, issue reporting, and rule testing.
- ameba-integrationUse when integrating Ameba into development workflows including CI/CD pipelines, pre-commit hooks, GitHub Actions, and automated code review processes.
- analyze-performanceAnalyze performance metrics and identify slow transactions in Sentry