Github Agent Trends

Generate GitHub agent-trending project reports as formatted markdown leaderboards. Fetches agent/LLM-agent/multi-agent related repos by daily, weekly, or mon...

Security Scan

The skill's code and instructions align with its stated purpose (fetching GitHub search results for agent-related repos) and request only an optional GitHub token; nothing in the package appears disproportionate or malicious.

Purpose & Capability

Name/description describe fetching GitHub agent-related repos and producing a markdown leaderboard; the included Python script implements exactly that using the GitHub Search API. No unrelated credentials, binaries, or services are requested.

Instruction Scope

SKILL.md runtime instructions are scoped to running the provided script and optionally using GITHUB_TOKEN; they do not instruct reading unrelated files or exfiltrating data. However, the example CLI path in SKILL.md (scripts/skills/github-agent-trends/scripts/fetch_trends.py) does not match the included file location (scripts/fetch_trends.py), which is a usability/incoherence issue and could confuse installers.

Install Mechanism

No install spec and the script uses only Python stdlib and direct HTTP calls to api.github.com. There are no downloads from third-party URLs or archive extraction steps.

Credentials

No required environment variables are declared. The script accepts an optional GITHUB_TOKEN (recommended for rate limits) which is proportional to calling the GitHub API. No unrelated secrets or broad system credentials are requested.

Persistence & Privilege

The skill does not request persistent/always-on presence, does not modify other skills or system settings, and has no special privileges.

Assessment

This skill appears to do what it says: query the GitHub Search API for agent-related projects and print a markdown leaderboard. Before installing or running it: (1) note the path mismatch in SKILL.md — run the actual script at scripts/fetch_trends.py (or adjust the path as needed); (2) if you provide a GITHUB_TOKEN, use a least-privilege PAT and keep it secret (do not paste it into chat); (3) verify network access to api.github.com in your environment; (4) inspect the script yourself if you require extra assurance—its logic is short and uses only the GitHub API, with no hidden endpoints or arbitrary code downloads.

Generate a formatted leaderboard of agent-related open-source projects on GitHub (keywords + topics such as ai-agent, multi-agent, agent framework), and paste the script output into chat.

Usage

From the repository root:

python3 scripts/skills/github-agent-trends/scripts/fetch_trends.py --period weekly --limit 20

With a token (recommended for rate limits):

export GITHUB_TOKEN=ghp_...
python3 scripts/skills/github-agent-trends/scripts/fetch_trends.py --period weekly --limit 20

Parameters

• --period: daily | weekly | monthly (default: weekly)
• --limit: Number of repos after dedupe/sort (default: 20)
• --token: GitHub PAT (or set GITHUB_TOKEN)
• --json: Raw JSON instead of markdown

How It Works

1. Queries GitHub Search repositories API with agent-focused keywords (e.g. ai-agent, multi-agent, agent framework) and topics (e.g. ai-agent, multi-agent, langchain, autogen), filtered by pushed within the period and minimum stars.
2. Deduplicates by full_name, sorts by stargazers_count, takes top N.
3. Prints a markdown leaderboard (Chinese title: GitHub Agent 趋势榜).

Notes

• Results reflect search relevance + stars, not the official GitHub “Trending” page (which has no public API).
• Unauthenticated: ~10 requests/minute to Search API; with GITHUB_TOKEN: higher quotas (follow GitHub docs).
• Stdlib only — no pip dependencies.

Customization

Edit SEARCH_KEYWORDS and SEARCH_TOPICS in scripts/fetch_trends.py to widen or narrow the agent theme (e.g. add crewai, browser-use).