generate-instructions
Analyze a directory and generate consolidated Cursor rules.
Best use case
generate-instructions is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Analyze a directory and generate consolidated Cursor rules.
Teams using generate-instructions should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/generate-instructions/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How generate-instructions Compares
| Feature / Agent | generate-instructions | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Analyze a directory and generate consolidated Cursor rules.
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.
SKILL.md Source
# Generate Directory Instructions
Analyze a specific directory in the monorepo and create a consolidated rule file for Cursor.
## Inputs
1. **Target Directory** (required) - The directory path to analyze (e.g., `packages/api`, `apps/web`)
## Output
Create a single file at `.cursor/rules/{DIR_NAME}.mdc` with:
- Frontmatter: `globs: "{DIR_PATH}/**"`
- All 7 sections populated with directory-specific information
## Steps
1. **Analyze the Directory** - Examine code structure, patterns, and conventions
2. **Generate Instructions File** - Create the consolidated file with all sections
3. **Validate Content** - Ensure all mentioned code/patterns actually exist
4. **Review Formatting** - Follow the guidelines below
## Sections to Include
### 1. Overview
- What this directory/package does
- Key concepts and domain terms
- Primary consumers/users of this code
- Integration points with other parts of the monorepo
### 2. Architecture & Patterns
- Folder structure within this directory
- Module boundaries and responsibilities
- Communication patterns (events, APIs, shared state)
- External service integrations
### 3. Stack Best Practices
- Language-specific idioms used here
- Framework patterns and conventions
- Dependency injection approach
- Error handling and validation patterns
### 4. Anti-Patterns
- Patterns to avoid in this directory
- Common mistakes to watch for
- Security pitfalls specific to this code
### 5. Data Models
- Key entities and their relationships
- DTOs and value objects
- Validation rules
- Database/storage patterns
### 6. Security & Configuration
- Environment variables used
- Secrets and sensitive data handling
- Authentication/authorization patterns
- API security considerations
### 7. Commands & Scripts
- Build commands for this directory
- Test commands
- Development scripts
- Deployment commands
## Guidelines
- Each section should be **concise** (aim for 5-10 bullet points per section)
- Use bullet points, not paragraphs
- Include specific file paths and code examples from THIS directory
- Only document patterns that actually exist in the code
- Skip sections that don't apply (but include the header with "N/A" note)
- The `globs` glob should match the target directory (e.g., `packages/api/**`)
## Output Format
```markdown
---
globs: "{DIR_PATH}/**"
---
# {DIR_NAME} Instructions
## Overview
- [specific bullet points]
## Architecture & Patterns
- [specific bullet points]
## Stack Best Practices
- [specific bullet points]
## Anti-Patterns
- [specific bullet points]
## Data Models
- [specific bullet points]
## Security & Configuration
- [specific bullet points]
## Commands & Scripts
- [specific bullet points]
```Related Skills
generate-status-report
Comprehensive system status report with services, infrastructure, performance metrics, and recommendations
generate-qr-code-natively
Generate QR codes locally without external APIs using native CLI and runtime libraries in Bash and Node.js.
generate-knowledge-base
Generate a product knowledge base from a codebase. Analyzes source code to create an Obsidian vault with architecture docs, API references, domain logic, data models, and infrastructure documentation. Use when the user asks to document a codebase, create a knowledge base, or generate product docs.
e2e-generate
Generate end-to-end tests with Playwright browser automation
Dictation Instructions
Instructions for fixing speech-to-text errors and improving text quality in gh-aw documentation and workflows
copilot-instructions-blueprint-generator
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.
config-generate
Generate configuration files for development tools
api-test-generate
Auto-generate comprehensive API tests for REST and GraphQL endpoints with request/response validation
root-level-project-instructions
Root level project guidelines and initial steps to start and implement EEG processor
generate_quiz_batch
Generates batches of high quality quizzes in JSON format for the BlindsidedGames pool, categorised and rated by difficulty.
weekly-email-team-instructions
Generates The Edmund Bogen Team's weekly market intelligence package: email, article page, dashboard, and community listings pages. Guides team through data collection, validates consistency, and produces all HTML assets ready for deployment to Constant Contact and GitHub.
generate-llms
Generate llms.txt and llms-full.txt files for AI agent consumption following the llmstxt.org standard. Use when updating site content that should be reflected in the llms files, or when building/deploying the site.