clean
Intelligent code cleanup with mainline detection, stale artifact discovery, and safe execution. Supports targeted cleanup and confirmation.
51
40%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/clean/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description uses technical-sounding but vague terminology that fails to communicate what specifically the skill does or when it should be used. It lacks natural trigger terms users would employ and has no explicit 'Use when...' clause. The core domain (what kind of code cleanup, what artifacts) remains ambiguous, making it difficult for Claude to reliably select this skill.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'clean up code', 'remove dead code', 'unused files', 'stale branches', or whatever the specific domain is.
Replace abstract jargon like 'mainline detection' and 'stale artifact discovery' with concrete, plain-language descriptions of what is being detected and cleaned up (e.g., 'Identifies and removes unused source files, orphaned build artifacts, and dead code branches').
Clarify the specific domain—is this about git branch cleanup, build artifact removal, dead code elimination, or something else? Specificity will reduce conflict risk with other cleanup-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions like 'mainline detection', 'stale artifact discovery', and 'safe execution', but these are somewhat abstract. 'Targeted cleanup and confirmation' adds some detail but the overall capabilities remain unclear—what exactly is being cleaned up (files, branches, dependencies)? | 2 / 3 |
Completeness | Describes a vague 'what' but completely lacks a 'when' clause. There is no 'Use when...' or equivalent guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Uses technical jargon like 'mainline detection', 'stale artifact discovery', and 'safe execution' that users would rarely say naturally. Missing common trigger terms users might use like 'clean up code', 'remove unused files', 'dead code', 'unused imports', or specific file types. | 1 / 3 |
Distinctiveness Conflict Risk | 'Code cleanup' is a broad term that could overlap with linting, formatting, refactoring, or dependency management skills. 'Mainline detection' and 'stale artifact discovery' add some specificity but it's unclear what domain this targets (git branches? build artifacts? dead code?). | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels in actionability and workflow clarity with fully executable code, clear phase sequencing, and robust validation/safety mechanisms including staged deletion and path whitelisting. However, it is significantly over-verbose for a skill file — the full implementation of every phase is inlined, mixed-language comments add noise, and there's no progressive disclosure to separate the overview from detailed implementation. The content would benefit greatly from being split into an overview SKILL.md with references to implementation detail files.
Suggestions
Reduce inline code significantly — move full phase implementations to separate reference files (e.g., PHASES.md or individual phase files) and keep only the workflow overview, key commands, and critical validation steps in SKILL.md.
Remove mixed-language comments (Chinese text) or standardize to one language for consistency and reduced token usage.
Eliminate redundant descriptions — the session folder structure appears twice, and the iteration flow section largely repeats information already covered in the phases.
Add progressive disclosure by creating referenced files for implementation details (e.g., 'See [IMPLEMENTATION.md](IMPLEMENTATION.md) for full phase code') and keep SKILL.md focused on the workflow overview, key decisions, and safety constraints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines with extensive inline code that could be significantly condensed. It includes mixed-language comments (Chinese and English), redundant explanations, and the full implementation code for every phase when much of this is standard programming logic Claude already knows. The session folder structure is described twice. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript and bash code for every phase, with concrete commands, specific data structures, and copy-paste ready implementations. The manifest JSON schema, agent spawn parameters, and user input structures are all explicitly defined. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 phases (0-4) with explicit validation checkpoints: path validation before deletion, staged deletion before permanent removal, manifest schema validation, dry-run exit point, and user confirmation gate. Error recovery is addressed with agent timeout retry and the error handling table covers edge cases. | 3 / 3 |
Progressive Disclosure | The content is essentially monolithic — all implementation details are inline in a single file with no references to external documentation. The overview and phase diagram at the top provide good structure, but the massive code blocks that follow could be split into separate reference files, with SKILL.md serving as a concise overview. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.