Deep analysis of a GitHub repository for tool spotlight inclusion in news digests. Evaluates the project's purpose, quality, popularity trajectory, and usefulness for AI practitioners.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Deep analysis of a GitHub repository for tool spotlight inclusion in news digests. Evaluates the project's purpose, quality, popularity trajectory, and usefulness for AI practitioners.
license
MIT
compatibility
Requires OpenAI-compatible LLM API access and GitHub API access
[{"name":"repo","type":"GithubRepo","description":"Repository metadata from fetch-github-trending"},{"name":"include_readme","type":"bool","default":true,"description":"Whether to fetch and analyze the README for deeper insights"}]
output
[{"name":"analysis","type":"RepoAnalysis","description":"Comprehensive repository analysis with summary and recommendations"},{"name":"spotlight_worthy","type":"bool","description":"Whether repo deserves a featured tool spotlight"},{"name":"spotlight_summary","type":"str","description":"Ready-to-use summary for digest if spotlight-worthy"}]
Analyze GitHub Repo
Evaluate a GitHub repository for potential inclusion as a tool spotlight in the news digest.
When to Use
Evaluating trending repos for digest tool spotlight section
Framework: Full framework for building applications (e.g., LangChain)
Library: Focused library for specific task (e.g., sentence-transformers)
Tool: Standalone tool or CLI (e.g., ollama)
Model: Model weights or implementation (e.g., Llama)
Dataset: Dataset or data processing
Application: Complete application (e.g., chat UI)
Tutorial/Demo: Educational content
Step 2: Evaluate Quality Signals
Assess quality based on:
Documentation: Is there a README? Is it comprehensive?
Activity: Recent commits? Active maintenance?
Community: Issues being addressed? PRs reviewed?
Code Quality: Based on language, structure visible from description
Dependencies: Are dependencies reasonable and maintained?
Step 3: Analyze Popularity Trajectory
Calculate growth indicators:
Star velocity: Stars gained recently (estimate from trending status)
Fork ratio: Forks/Stars indicates adoption
Issue health: Open issues vs total activity
Maturity: Age vs popularity
Step 4: Determine Use Cases
Identify who would benefit:
Researchers: Academic use cases
Practitioners: Production deployment
Hobbyists: Personal projects
Enterprise: Business applications
Step 5: Identify Differentiators
What makes this repo special:
Novel approach: Does something new
Better performance: Faster/cheaper than alternatives
Ease of use: Lower barrier than alternatives
Integration: Works well with popular tools
Active community: Good support and updates
Step 6: Fetch and Analyze README (if enabled)
If include_readme is true:
Fetch README.md from GitHub
Extract:
Installation instructions
Quick start example
Feature list
Comparison with alternatives (if mentioned)
Step 7: Generate Spotlight Summary
If spotlight-worthy, create a 2-3 sentence summary:
What the tool does
Why it's noteworthy now
Who should check it out
Step 8: Determine Spotlight Worthiness
A repo is spotlight-worthy if:
Stars >= 1000 OR growing rapidly (>500 in last week)
Active maintenance (pushed within 7 days)
Clear, useful purpose for AI practitioners
Good documentation
NOT primarily educational/tutorial content
Output Schema
{"analysis":{"full_name":"owner/repo-name","category":"library","quality_scores":{"documentation":8,"activity":9,"community":7,"overall":8},"popularity_metrics":{"star_count":5000,"fork_count":300,"fork_ratio":0.06,"estimated_weekly_stars":500,"growth_status":"rapid"},"use_cases":["practitioners","enterprise"],"differentiators":["2x faster than alternative X","Simple API with good defaults","Active Discord community"],"target_audience":"ML engineers building LLM applications","maturity":"stable","risk_factors":["Single maintainer","No enterprise support"]},"spotlight_worthy":true,"spotlight_summary":"**repo-name** is a new Python library that makes LLM inference 2x faster with a simple API. It's gained 500 stars this week as developers discover its drop-in compatibility with popular frameworks. Worth checking out if you're running inference workloads."}
Success Criteria
Category correctly identified
Quality assessment reasonable
Spotlight decision justified by metrics
Summary is concise and informative
Target audience identified
Failure Handling
Error Type
Handling Strategy
README fetch fails
Continue without README analysis
Minimal description
Use topics and repo name for analysis
Private/deleted repo
Return error with explanation
Examples
Example 1: High-Quality New Library
Input:
{"repo":{"full_name":"example/llm-accelerator","name":"llm-accelerator","description":"Fast LLM inference with automatic batching and caching","url":"https://github.com/example/llm-accelerator","stars":3500,"forks":180,"language":"Python","topics":["llm","inference","optimization"],"created_at":"2025-11-01","pushed_at":"2026-01-26","open_issues":25},"include_readme":true}
Output:
{"analysis":{"full_name":"example/llm-accelerator","category":"library","quality_scores":{"documentation":9,"activity":10,"community":8,"overall":9},"popularity_metrics":{"star_count":3500,"fork_count":180,"fork_ratio":0.05,"estimated_weekly_stars":400,"growth_status":"rapid"},"use_cases":["practitioners","enterprise"],"differentiators":["Automatic request batching","Built-in caching layer","Drop-in replacement for common APIs"],"target_audience":"ML engineers and backend developers","maturity":"growing","risk_factors":[]},"spotlight_worthy":true,"spotlight_summary":"**llm-accelerator** automatically batches and caches LLM requests, cutting inference costs without code changes. With 3,500 stars and 400 gained this week, it's becoming a go-to for teams looking to optimize their LLM deployments. Check it out if you're serving LLM requests at scale."}
Example 2: Tutorial Repository (Not Spotlight Worthy)
Input:
{"repo":{"full_name":"someone/llm-tutorial","name":"llm-tutorial","description":"Learn how to build with LLMs - step by step tutorials","url":"https://github.com/someone/llm-tutorial","stars":800,"forks":150,"language":"Jupyter Notebook","topics":["tutorial","llm","learning"],"created_at":"2025-08-01","pushed_at":"2026-01-20","open_issues":5},"include_readme":false}
Output:
{"analysis":{"full_name":"someone/llm-tutorial","category":"tutorial","quality_scores":{"documentation":7,"activity":6,"community":5,"overall":6},"popularity_metrics":{"star_count":800,"fork_count":150,"fork_ratio":0.19,"estimated_weekly_stars":20,"growth_status":"steady"},"use_cases":["hobbyists","researchers"],"differentiators":["Comprehensive tutorial collection"],"target_audience":"Beginners learning LLM development","maturity":"stable","risk_factors":["Educational content, not production tool"]},"spotlight_worthy":false,"spotlight_summary":""}
Example 3: Popular But Stale Repository
Input:
{"repo":{"full_name":"old/legacy-tool","name":"legacy-tool","description":"ML toolkit from 2023","url":"https://github.com/old/legacy-tool","stars":15000,"forks":2000,"language":"Python","topics":["machine-learning"],"created_at":"2022-01-01","pushed_at":"2025-06-01","open_issues":500},"include_readme":false}
Output:
{"analysis":{"full_name":"old/legacy-tool","category":"framework","quality_scores":{"documentation":7,"activity":2,"community":3,"overall":4},"popularity_metrics":{"star_count":15000,"fork_count":2000,"fork_ratio":0.13,"estimated_weekly_stars":5,"growth_status":"declining"},"use_cases":["practitioners"],"differentiators":[],"target_audience":"Legacy users","maturity":"legacy","risk_factors":["No recent updates","High open issue count","Likely abandoned"]},"spotlight_worthy":false,"spotlight_summary":""}
