Install
$ agentstack add skill-viknesh20-20-claude-code-tool-kit-explain-code ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Code Explanation
Instructions
Step 1: Identify the Target
Read the specified file, function, or module completely. Also read:
- Any imports/dependencies it uses
- Any files that import/call it (to understand usage context)
- Recent git history for the file:
git log --oneline -10
Step 2: Provide Multi-Level Explanation
Level 1 — One-Sentence Summary
What does this code do in plain English? A non-technical person should understand this.
Level 2 — High-Level Overview
- Purpose: What problem does it solve?
- Inputs: What goes in? (parameters, config, env vars, external data)
- Outputs: What comes out? (return values, side effects, events emitted)
- Dependencies: What does it rely on?
- Callers: Who uses this? In what context?
Level 3 — Detailed Walkthrough
Walk through the code section by section:
- Explain the logic flow with numbered steps
- Highlight non-obvious decisions ("this uses X instead of Y because...")
- Note any error handling and what triggers each path
- Explain any performance-sensitive sections
Level 4 — Data Flow Diagram
Create an ASCII diagram showing:
[Input] → [Processing Step 1] → [Processing Step 2] → [Output]
↓ ↓
[Side Effect 1] [Side Effect 2]
Step 3: Highlight Key Details
- Tricky Parts: Code that might confuse a new reader
- Assumptions: Implicit assumptions the code makes
- Edge Cases: How are boundary conditions handled?
- History: Why was it written this way? (use
git blamefor context)
Step 4: Related Code
List the most important related files/functions that someone exploring this code should read next.
Output Style
- Use clear section headers
- Include code snippets with line references
- Use analogies where helpful
- Adjust technical depth based on the complexity of the code
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: viknesh20-20
- Source: viknesh20-20/claude-code-tool-kit
- License: MIT
- Homepage: https://viknesh20-20.github.io/claude-code-tool-kit/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.