ReddRadar
Agent skill
dig
Look up documentation and source code for libraries and packages. Use when the user asks a question about a library, needs to understand a library's API, or when you need information about a library that you don't know about. Triggers on questions like "How do I use X library?", "What's the API for Y?", "Show me how Z library handles this", or when encountering unfamiliar library usage.
Install this agent skill to your Project
npx add-skill https://github.com/udecode/dotai/tree/main/.claude-plugin/plugins/dig/skills/dig
SKILL.md
Dig
Look up library documentation by finding and exploring the library's source code repository.
Workflow
1. Check for Local Availability
First, check if the library source code already exists locally:
# Check common locations
ls /tmp/cc-repos/{library-name} 2>/dev/null
If the library exists locally, skip to step 3.
2. Clone the Repository
If not available locally, find and clone the repository:
- Search for the library's GitHub repository (most libraries are on GitHub)
- Clone into the standard location:
mkdir -p /tmp/cc-repos
git clone https://github.com/{owner}/{repo}.git /tmp/cc-repos/{repo-name}
Common repository patterns:
- npm packages: Check
package.jsonhomepage or repository field, or searchhttps://github.com/{package-name} - Python packages: Check PyPI page for "Homepage" or "Source" links
- Go packages: The import path often is the repository URL
- Rust crates: Check crates.io for repository link
3. Research the Repository
Launch a Research agent (using the Task tool with subagent_type="Explore") to traverse the repository and answer the question.
Example prompt for the agent:
Explore the repository at /tmp/cc-repos/{repo-name} to answer: {user's question}
Focus on:
- README and documentation files
- Source code structure
- API exports and public interfaces
- Examples and tests for usage patterns
4. Synthesize and Answer
Use the research findings to provide a clear, accurate answer to the user's question about the library.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
udecode/dotai
changelog
Use when updating CHANGELOG.md. Enforces consistent formatting with bolded item names, dash separators, and specific section ordering.
udecode/dotai
debug
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework with built-in backward tracing for deep-stack failures, ensuring root-cause understanding before implementation
udecode/dotai
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?