readme-updates
Maintain README files with setup instructions, features, tech stack, and usage examples. Use when updating project documentation, adding new features, improving onboarding, or creating READMEs for new packages.
Best use case
readme-updates is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Maintain README files with setup instructions, features, tech stack, and usage examples. Use when updating project documentation, adding new features, improving onboarding, or creating READMEs for new packages.
Teams using readme-updates 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/readme-updates/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How readme-updates Compares
| Feature / Agent | readme-updates | 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?
Maintain README files with setup instructions, features, tech stack, and usage examples. Use when updating project documentation, adding new features, improving onboarding, or creating READMEs for new packages.
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
# README Updates Skill
## Root README Structure
```markdown
# SG Cars Trends
[](LICENSE)
[](https://github.com/sgcarstrends/sgcarstrends/actions)
> Platform for accessing Singapore vehicle registration and COE bidding data
## Features
- 📊 **Comprehensive Data**: Car registration and COE bidding data
- 🔄 **Real-time Updates**: Automated daily updates from LTA DataMall
- 📝 **AI-Generated Blog**: Automated insights using Google Gemini
## Quick Start
\`\`\`bash
git clone https://github.com/sgcarstrends/sgcarstrends.git
cd sgcarstrends
pnpm install
cp .env.example .env
pnpm db:migrate
pnpm dev
\`\`\`
## Tech Stack
- **Frontend**: Next.js 16, HeroUI, Recharts, Tailwind CSS
- **Backend**: Hono, Drizzle ORM, PostgreSQL, Upstash Redis
- **Infrastructure**: SST v3, AWS Lambda, Cloudflare
- **AI**: Google Gemini, QStash workflows
## Project Structure
\`\`\`
sgcarstrends/
├── apps/
│ ├── api/ # Hono API
│ └── web/ # Next.js web app
├── packages/
│ ├── database/ # Drizzle schemas
│ ├── ui/ # UI components
│ └── utils/ # Shared utilities
└── infra/ # SST infrastructure
\`\`\`
## Development
\`\`\`bash
pnpm dev # Start all servers
pnpm test # Run tests
pnpm build # Build for production
\`\`\`
## License
MIT
```
## Package README Template
```markdown
# @sgcarstrends/[package-name]
> Brief description
## Installation
\`\`\`bash
pnpm add @sgcarstrends/[package-name]
\`\`\`
## Usage
\`\`\`typescript
import { functionName } from "@sgcarstrends/[package-name]";
const result = functionName();
\`\`\`
## API
### `functionName(param: string): ReturnType`
Description.
**Parameters:** `param` (string) - Description
**Returns:** `ReturnType` - Description
## Development
\`\`\`bash
pnpm test
pnpm build
\`\`\`
## License
MIT
```
## Common Badges
```markdown
[](LICENSE)
[](actions)
[](npm)
[](typescript)
```
## Environment Variables Section
```markdown
## Environment Variables
Create `.env` from `.env.example`:
\`\`\`env
DATABASE_URL=postgresql://user:pass@localhost:5432/db
UPSTASH_REDIS_REST_URL=https://your-redis.upstash.io
UPSTASH_REDIS_REST_TOKEN=your-token
\`\`\`
```
## Update Checklist
- [ ] Features list current when new features added
- [ ] Tech stack updated when dependencies change
- [ ] Setup instructions accurate when process changes
- [ ] Examples working and up-to-date
- [ ] Links not broken
## Validate README
```bash
# Check for broken links
pnpm dlx markdown-link-check README.md
# Lint markdown
pnpm dlx markdownlint README.md
```
## Best Practices
1. **Clear Description**: Concise project description at top
2. **Quick Start**: Immediate value with copy-paste setup
3. **Working Examples**: Test all code examples
4. **Keep Updated**: Update when features change
5. **Check Links**: Regularly verify links work
## References
- Shields.io: https://shields.io (badges)
- markdownlint: https://github.com/DavidAnson/markdownlintRelated Skills
claude-updates
Fetch and analyze Claude/Anthropic RSS feeds to summarize recent updates and propose improvements to CLAUDE.md, skills, and workflows.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
vercel-deploy-claimable
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as 'Deploy my app', 'Deploy this to production', 'Create a preview deployment', 'Deploy and...
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
vercel-ai-sdk-development
Use when building AI-powered applications with the Vercel AI SDK (V6+). Covers agents (ToolLoopAgent), tool design with execution approval and strict mode, MCP client integration, structured output with tool calling, streaming patterns, DevTools debugging, reranking, provider-specific tools, and UI integration with React/Next.js.
vercel-ai-sdk-best-practices
Best practices for using the Vercel AI SDK in Next.js 15 applications with React Server Components and streaming capabilities.
venice-router
Supreme model router for Venice.ai — the privacy-first, uncensored AI platform. Automatically classifies query complexity and routes to the cheapest adequate model. Supports web search, uncensored mode, private-only mode (zero data retention), conversation-aware routing, cost budgets, function calling, thinking/reasoning mode, and 35+ Venice.ai text models. Use when the user wants to chat via Venice.ai, send prompts through Venice, or needs smart model selection to minimize API costs while keeping data private from Big Tech.
validator-workflow
Phase-level validation workflow for validator agents. Handles loading project rules, reading phase files, running /code-review, conditional verification (unit tests + typecheck + E2E/DB tests based on phase type), determining verdict, and reporting to the orchestrator. Invoke this skill as your first action — not user-invocable.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
uvicorn
ASGI server for Python web applications - Fast, production-ready server for async frameworks
using-superantigravity
Use when starting any conversation — establishes how to find and use skills, requiring skill check before ANY response including clarifying questions