Explain
Collection of reusable skills and extensions for AI coding agents - prompts, Pi extensions, and other bits and pieces.
npx -y skills add eddmann/agent-toolkit --skill explainAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Explain how code works — architecture, patterns, and design decisions (read-only)
SKILL.md
1.7 KB, as published. Nobody here has run it
ultrathink: Provide a thorough explanation by first exploring extensively, then synthesizing a clear answer.
Your Task
Explain: $ARGUMENTS
Context
- Current directory: !
pwd - Git branch: !
git branch --show-current 2>/dev/null || echo "not a git repo"
Instructions
Phase 1: Explore Extensively
Before explaining anything:
- Use Explore agents to find all relevant code
- Read the actual files - don't guess from names
- Trace the flow - how do components connect?
- Check tests for behavioral documentation
- Look at git history for evolution and decisions
Phase 2: Synthesize Understanding
Think deeply about:
- What is the architecture? - components, layers, boundaries
- What patterns are used? - and why were they chosen?
- How does data flow? - inputs to outputs
- What are the key abstractions? - and what do they hide?
- What tradeoffs were made? - and what are the implications?
Phase 3: Explain Clearly
Provide an explanation that:
- Starts with the big picture - high-level architecture first
- Zooms into specifics - key files and functions
- Explains the "why" - not just "what" the code does
- Uses file:line references - so the user can navigate
- Connects to patterns - name the design patterns where applicable
Critical Rules
- DO NOT make changes - this is explanation only
- DO NOT skip exploration - read before explaining
- DO include concrete references - file paths and line numbers
- DO explain rationale - why things are structured this way