Coff0xc

Coff0xc / coffee-skill

Public

Comprehensive Codex skills pack for engineering, AI agents, docs, and defensive security, with multilingual triggers, validation checklists, and a router fallback

ai-agents codex defensive-security devsecops rag
10
0
100% credibility
Found May 13, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A set of domain-specific AI skills with keyword-based triggering to route user prompts to the right expert, including evaluation tools and an example for generating editable research diagrams.

How It Works

1
🔍 Discover smart helpers

You stumble upon a collection of specialized helpers that make AI assistants experts in tech areas like research diagrams and security.

2
📋 Explore the skills

Browse through helpers for drawing diagrams, fixing code, checking security, and many other topics.

3
💡 Test with your question

Type in a question about your topic, and it automatically picks the best helper to wake up and assist.

4
🎨 Create a research diagram

Describe your idea, like a workflow or model, and the diagram helper builds an editable drawing you can tweak.

5
✅ Check how well it works

Run a quick test to see if questions reliably call the right helpers without mistakes.

🚀 Helpers are ready to shine

Now your AI knows exactly when to use each expert, making tough tech tasks feel easy and fun.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is coffee-skill?

Coffee-skill is a Python pack of specialized prompts for Codex AI agents, covering engineering, AI agents, docs, and defensive security tasks like code audits, RAG debugging, and drawio diagrams. It solves the hassle of crafting domain-specific prompts by using multilingual triggers to auto-route queries to the right skill, with checklists for validation and a fallback router. Users get plug-and-play expertise for agents, plus scripts to eval trigger accuracy and validate releases.

Why is it gaining traction?

It stands out with comprehensive coverage across 18 domains, from github comprehensive rust debugging to blockchain security and purple team exercises, plus bilingual English-Chinese triggers that catch phrases like "代码审计" or "科研绘图". Devs dig the self-eval tools for trigger precision and release hygiene checks, beating generic prompt libraries. The router fallback ensures no query falls through, making it reliable for production agents.

Who should use this?

Security engineers running defensive audits or threat modeling, AI devs building RAG agents with latency tweaks, and researchers needing editable drawio pipeline diagrams. Backend teams fixing API pagination bugs or CI/CD secrets scanning will save hours over manual prompting.

Verdict

Worth forking for niche Codex workflows if you're in defensive security or agent engineering—docs are thorough with multilingual guides and evals—but at 10 stars and 1.0% credibility, it's early alpha; test triggers locally before prod. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.