Clean Code
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill is mostly coherent as a coding-style guide, but it also mandates running local Python validation scripts from other skills that are not included or declared.
This skill is generally a clean-code instruction set, but install it only if you are comfortable with its instruction to run local validation scripts from other skill folders. Review those scripts separately and keep changes under version control.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If followed, the agent may execute local code that was not included in this skill review, potentially affecting the project environment beyond simple code-style edits.
The skill is presented as instruction-only and declares only Read, Write, and Edit tools, but it mandates running local Python scripts from other skill directories over the project.
## Verification Scripts (MANDATORY) ... `python .agent/skills/frontend-design/scripts/ux_audit.py .` ... `python .agent/skills/lint-and-validate/scripts/lint_runner.py .`
Only allow script execution after reviewing the referenced scripts and confirming they exist, are trusted, and are appropriate for the current project.
The agent may change multiple related files, not just the file you explicitly named.
The skill can read and modify files and instructs the agent to update dependent files too; this is purpose-aligned for coding work but can broaden the set of changed files.
allowed-tools: Read, Write, Edit ... Rule: Edit the file + all dependent files in the SAME task.
Use version control, review diffs before accepting changes, and give clear limits if only specific files should be edited.