skill-grep
Health Pass
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 19 GitHub stars
Code Pass
- Code scan — Scanned 1 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
This tool is a search engine designed for AI agents, helping them discover and rank reusable skills and workflows across multiple sources based on a user's intent.
Security Assessment
The automated code scan reviewed the primary files and found no dangerous patterns, hardcoded secrets, or requests for excessive local permissions. However, as a search tool, its core function involves making external network requests to an API (skills.megatechai.com) to retrieve data. Additionally, it features a "Feedback Telemetry" component that sends data back to the developers to improve ranking algorithms. While no sensitive local data is explicitly targeted, the outbound network traffic keeps the risk at a Low to Moderate level depending on what telemetry is collected.
Quality Assessment
The project appears to be actively maintained, with its last code push occurring today. It uses the standard and highly permissive Apache-2.0 license, which is excellent for open-source adoption. Community trust is currently in the early stages, indicated by 19 GitHub stars, but the project provides clear documentation, installation instructions, and straightforward use cases.
Verdict
Safe to use, but remain aware that it makes external network requests to fetch search results and transmit basic telemetry.
A smart skill search engine for agents with multi-field retrieval and quality signals.
Skill Grep
Navigate the skill universe — Stop reinventing the wheel, start discovering.
A smart skill search engine for agents — discover reusable skills and workflows instantly.
🌐 Try the Web Version: skills.megatechai.com. Search skills directly in your browser!
🌟 Why Skill Grep?
Finding the right skill shouldn't be harder than building it yourself.
When you need a capability, you shouldn't have to:
- Wonder if a solution already exists
- Manually browse multiple marketplaces
- Guess which skills are actually high-quality
Skill Grep searches across sources using multi-field retrieval and returns ranked recommendations with quality signals (e.g., GitHub stars), so you can quickly find the best option.
🛠️ How It Works
1. You: "I need a skill for CI/CD automation"
2. Skill Grep:
├── Builds structured query from your intent
├── Calls search API with query fields
├── (Optional) Asks one clarification question if needed
└── Returns 1-3 ranked recommendations
3. You: Select the best match
└── Skill Grep learns from your feedback
✨ Key Features
| Feature | Description |
|---|---|
| Smart Retrieval | Jointly searches over name, description, and usage context for better relevance |
| Quality Signals | Shows relevance + GitHub stars |
| Clarification Loop | Asks one targeted question if results are ambiguous |
| Feedback Telemetry | Continuously improves ranking |
🚀 Installation
For Claude Code
You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code:
/plugin marketplace add LittleDinoC/skill-grep
/plugin install skill-grep@skill-grep
Option 1: Via skill manager
npx skills add https://github.com/LittleDinoC/skill-grep --skill skill-grep
Option 2: Manual install
You can download the specific skill folder and place it in your skills directory.
# Navigate to your skills directory (e.g., for OpenClaw)
cd ~/.openclaw/skills
# Extract only the specific skill folder
npx degit LittleDinoC/skill-grep/skills/skill-grep skill-grep
Note: This installs only the skill-grep package without cloning the entire repository history.
🔍 Usage
The skill activates automatically when you ask your agent to discover, find, or search for skills.
Example Sessions
Simple search:
You: "Find me a skill for git commit conventions"
Skill Grep:
> Searching for skills...
Recommendations:
1. conventional-commits (github/awesome-copilot, 26.8k repo stars ⭐)
Best for: Structured commit message generation following Conventional Commits specification.
This skill guides you through creating standardized, descriptive commit messages with a structured XML format. It includes instructions, examples, and validation to ensure your commits follow the Conventional Commits specification.
2. git-commit (github/awesome-copilot, 26.8k repo stars ⭐)
Best for: Complete commit workflow with intelligent staging
A more comprehensive option that handles the full git commit workflow: auto-detecting type and scope from changes, generating conventional commit messages from diff, interactive commits with overrides, and intelligent file staging for logical grouping.
Search with clarification:
You: "I need a skill for testing"
Skill Grep:
> I found several testing skills, but they serve different purposes. What type of testing do you need?
1. Test-Driven Development (TDD) — Write tests first, then implement code to make them pass
2. Test Generation — Generate comprehensive tests for existing code (multi-language)
3. Language-Specific Testing — Focused testing for specific languages (Python, C++, etc.)
You: "End-to-end testing"
Skill Grep:
> Refined search...
Recommendations:
1. e2e-testing-patterns (wshobson/agents, 32.3k repo stars ⭐)
- Fit: Master E2E testing with Playwright and Cypress, flaky test debugging, CI/CD integration.
🎯 Search Behavior
| Scenario | Behavior |
|---|---|
| Clear intent | Returns top recommendations immediately |
| Ambiguous results | Asks exactly one clarification question |
| No results | Prompts for refined intent |
| User verdict | Sends feedback for ranking improvement |
📚 Research & Citation
Skill Grep is the practical extension of our paper Multi-Field Tool Retrieval. While the paper proposes a framework for retrieving tools across multiple metadata fields, this project brings those insights into a functional search engine for AI agents.
If you find this work helpful for your research or projects, please cite our paper:
@misc{tang2026multifieldtoolretrieval,
title={Multi-Field Tool Retrieval},
author={Yichen Tang and Weihang Su and Yiqun Liu and Qingyao Ai},
year={2026},
eprint={2602.05366},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2602.05366},
}
⚖️ License
Released under the Apache License 2.0.
📋 User Agreement
By using Skill Grep, you agree to our User Agreement.
Data Collection Notice: We collect search interaction data (without involving personal privacy information) to construct public research datasets. This helps advance research in skill retrieval and agent capabilities. See the User Agreement for full details.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found