Aha-Skill automates the conversion of MCP Server, REST API, and OpenAPI specifications into Claude Skill packages. Operations teams use it to streamline skill development, reducing manual effort and ensuring compatibility with Claude agents.
git clone https://github.com/melonlee/aha-skill.gitSidonie is an open-source front-end application that integrates chat, notes, study modules, and academic paper management into a single interface. It supports multi-session conversations with file uploads (PDF, Word, CSV, images), structured reasoning through plan and thought extraction, and local persistence using React and localStorage. The application connects to Google Gemini by default and can be extended with DeepSeek, Kimi, and Qwen models via API keys. Designed for students, researchers, and learners who need organized workflows without requiring backend infrastructure, Sidonie runs entirely in the browser with optional AI-powered analysis and curriculum-based learning features.
[{"step":"Provide the input specification. Paste the MCP Server, REST API, or OpenAPI specification (in JSON or YAML format) directly into the prompt. If the specification is large, share a link to the hosted version or a relevant subset.","tip":"For OpenAPI specs, ensure the `servers` field is correctly defined to avoid errors in the generated skill."},{"step":"Specify any custom requirements. Mention if you need additional fields in the output (e.g., `example_output`, `actions`, or `error_handling`). If the skill requires authentication, include the API key or OAuth details in the prompt.","tip":"Use placeholders like [LOCATION] or [USER_INPUT] in the prompt_template to make the skill reusable."},{"step":"Review the generated skill package. Validate the output against the Claude Skill schema (e.g., check for required fields like `name`, `description`, and `prompt_template`). Test the skill in a development environment if possible.","tip":"Use tools like `claude skills validate` (if available) to check the package before deployment."},{"step":"Deploy the skill. Upload the generated package to your Claude agent or skill repository. Monitor performance and iterate based on user feedback.","tip":"Log API calls and errors to debug issues quickly. For REST APIs, consider rate-limiting the skill to avoid hitting API quotas."}]
Multi-model AI chat with file analysis and streaming responses
Curriculum-based study with learning cards, XP tracking, and review scheduling
Academic paper discovery and management with arXiv integration
Local note-taking with tags, themes, and AI assistance
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/melonlee/aha-skillCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Convert the [MCP_SERVER_SPECIFICATION] / [REST_API_SPECIFICATION] / [OPENAPI_SPECIFICATION] into a Claude Skill package. Ensure the output follows the required schema for Claude Skills, including the 'name', 'description', 'prompt_template', and 'example_output' fields. If the specification includes endpoints, prioritize converting them into actionable skill actions. Use [PLACEHOLDER] for any missing details in the specification.
```json
{
"name": "weather_skill_v1",
"description": "A Claude Skill that fetches real-time weather data from the OpenWeatherMap API and provides 5-day forecasts for any location.",
"prompt_template": "Fetch the 5-day weather forecast for [LOCATION] using the OpenWeatherMap API. Include temperature ranges, precipitation chances, and wind speeds. Format the response as a concise table with daily summaries.",
"example_output": "Here’s the 5-day forecast for San Francisco, CA (as of 2024-05-20):\n\n| Day | Temp (°F) | Precip Chance | Wind (mph) |
|-----------|-----------|---------------|------------|
| May 21 | 68-75 | 10% | 8-12 |
| May 22 | 65-72 | 25% | 10-15 |
| May 23 | 63-70 | 5% | 5-10 |
| May 24 | 67-74 | 0% | 7-12 |
| May 25 | 66-73 | 15% | 6-11 |\n\nData sourced from OpenWeatherMap API (last updated: 2024-05-20T14:30:00Z).",
"actions": [
{
"name": "get_weather_forecast",
"description": "Fetches a 5-day weather forecast for a given location.",
"parameters": {
"location": {
"type": "string",
"description": "City and state, e.g., 'San Francisco, CA'"
}
}
}
]
}
```AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan