Install
$ agentstack add skill-davila7-claude-with-skills-01-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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Instructions
- Identify the code to explain. In order of priority:
- Code the user just pasted or attached in this conversation
- The last file that was opened or discussed
- If it is unclear, ask the user to paste or point to the specific code before proceeding
- Identify the programming language. Do not assume from the file extension alone — check the syntax if the extension is missing or ambiguous.
- Explain the code in plain language covering these three areas:
Overall purpose — What does this code do? What problem does it solve or what action does it perform? State this in one or two sentences without using the function or variable names as a substitute for explanation.
Main data flow — How does data move through the code? What comes in, what happens to it, and what comes out? For a function: inputs, transformations, output. For a class: how instances are created and how their state changes. For a script: what it reads, what it produces.
Non-obvious logic — Is there any behavior that would surprise a competent programmer reading this for the first time? Flag things like: side effects, error suppression, hardcoded assumptions, subtle timing dependencies, or clever bitwise operations.
- Use an analogy if it genuinely makes the concept clearer. Do not force one if the code is self-explanatory once described directly.
- Limit the explanation to what was asked. If the user pointed to one function, explain that function. Do not expand to the surrounding architecture unless asked.
- Do not restate the obvious. If a function is named
calculateTaxand it calculates tax, skip the sentence saying "this function calculates tax" and go directly to how it does it.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: davila7
- Source: davila7/claude-with-skills
- License: MIT
- Homepage: https://claude-with-skills.vercel.app
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.