Clean Code
Enforce human-readable Python with the cleancode analyzer. Use this to check existing files or to generate and validate new code based on instructions.
Install
$ agentstack add skill-lukasb24-clean-code-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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-lukasb24-clean-code-clean-code) 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 Analyzer
Run the clean-code static analyzer on the targeted Python file or directory to enforce formatting, structure, and readability standards.
Workflow
- If
target_pathis provided:
Execute: clean-code check "{{target_path}}"
- If no
target_pathis provided but aninstructionis:
- Generate the requested Python code based on the
instruction. - Save the code to a temporary path (
{{generated_file_path}}). - Execute:
clean-code check "{{generated_file_path}}"
Guidelines
- By default,
info-severity violations (the fuzziest, lowest-signal rules) are hidden to avoid context noise. - If the summary indicates violations hidden below
--min-severity warning, and a deeper pass is required, rerun the command with:clean-code check --min-severity info "{{target_path}}"(or the generated path). - Review the output from the analyzer. If any violations are reported, modify the source code directly using the suggested
fix:patterns. - Do not silence violations using inline comments unless specifically requested by the user.
DP701/SD801/SD802findings are SOLID/DRY smells, not local style nits — thefix:suggestion (extract a shared helper, replace a type-switch with polymorphism/a dispatch table, split a class) usually means introducing a new function/class or changing call sites, not a one-line edit. Apply the refactor, but summarize what you restructured and why when presenting the result, since these findings reshape the code's structure more than the other rules do.DP701compares functions across every file reached in onecheckrun — it still runs (and can still catch within-file duplicates) on a single-filetarget_path, but a single-file check can't see a duplicate living in a sibling file. Prefer checking the containing directory (or the whole project) when hunting for cross-file duplication, not just the one file you touched.- Present the final cleaned code back to the user.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LukasB24
- Source: LukasB24/clean-code
- License: Apache-2.0
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.