Install
$ agentstack add skill-olshansk-agent-skills-cmd-clean-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
Clean Code
Use these rules to improve code readability without altering functionality unless explicitly requested.
Core Principles
- Minimize cognitive load for human readers and agents.
- Apply idiomatic best practices where they fit.
- Preserve all business logic unless told otherwise.
- Clarify comments and structure with bullet points where possible.
Accepted Inputs
- Full source files (
.proto,.go,.py,.md, etc.). - Partial comments: package headers, method docs, inline notes.
- Whole or partial functions.
- Arbitrary code snippets (or any mix of the above).
Response Requirements
- Return the cleaned code wrapped in triple back-ticks.
- Keep all identifiers (fields, params, classes, methods, etc.).
- Add strategic whitespace for readability.
- Convert paragraph-style comments into bullet points when feasible.
- Do not delete or change original content unless asked.
- Favor bullet lists whenever information is list-like.
Team-Specific Edge Cases
- Leave
TODO_???(???)tags untouched. - Preserve callouts like
IMPORTANT,DEV_NOTE, etc. - Maintain references to GitHub issues/PRs (e.g. "As of #XX ...").
- Keep every link and external reference.
- Retain markers such as
CRITICAL,NB,DEV_NOTE,NOTE; just clean up the following text.
Handling Long Snippets
- For grouped code (~5 lines) followed by a blank line, add a brief comment atop the block.
- Keep existing comment hierarchy; just enhance readability.
Nits & Edits
- Don't create a list with only one item -- write it as plain text.
- Never remove existing links while editing.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Olshansk
- Source: Olshansk/agent-skills
- License: MIT
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.