Generate GitHub AI trending project reports as formatted text leaderboards. Fetches top-starred AI/ML/LLM repos by daily, weekly, or monthly period and renders a styled leaderboard. Use when the user asks for AI project trends, GitHub trending, AI leaderboard, or wants to see popular AI repos.
Security Analysis
high confidenceThe skill's code and instructions match its description: it queries the GitHub API for AI-related repos and formats a leaderboard; it requests no unrelated credentials or installs.
Name/description (GitHub AI trends) align with the included script and SKILL.md: the script queries the GitHub Search API for AI/LLM/ML keywords/topics and sorts by stars to build a leaderboard. No unrelated services, binaries, or config paths are requested.
SKILL.md instructs the agent to run the provided Python script and return stdout; the script only calls the GitHub API, formats results, and prints markdown/JSON. The instructions do not ask the agent to read arbitrary files, access unrelated env vars, or send data to endpoints other than api.github.com.
No install spec is present (instruction-only + single script). The Python script uses only the standard library (urllib, json, datetime), so nothing is downloaded or written to disk beyond running the script.
No required environment variables; an optional GITHUB_TOKEN is supported for higher API rate limits, which is appropriate for GitHub API usage. The token is optional and only used in an Authorization header to api.github.com. No unrelated secrets are requested.
always is false and the skill does not request persistent installation or modify other skills or system-wide config. It does not write credentials or alter agent settings.
Guidance
This skill appears to do exactly what it says: run the included Python script which queries the GitHub Search API and prints a formatted leaderboard. Before installing or running: (1) be aware the script makes outbound HTTPS requests to api.github.com and will respect GitHub rate limits; supply a GITHUB_TOKEN only if you understand the token's scope (prefer a limited, read-only token). (2) Review the code yourself if you have concerns — the repository owner/homepage are unknown. (3) Running the script prints results to stdout/stderr; it does not write files or contact any third-party endpoints beyond GitHub. Overall this is internally consistent and proportionate.
Latest Release
v1.1.0
Changed output from HTML to formatted text for direct chat display
More by @toller892
Published by @toller892 on ClawHub
