clean
Intelligent code cleanup with mainline detection, stale artifact discovery, and safe execution. Supports targeted cleanup and confirmation.
42
28%
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 jargon that doesn't match how users naturally request help, lacks an explicit 'Use when...' clause, and doesn't clearly specify what types of artifacts or code are being cleaned up. While it hints at a specific domain (code cleanup with branch/artifact management), the language is too abstract for reliable skill selection.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'clean up old branches', 'remove stale files', 'delete unused code', or 'tidy up repository'.
Replace jargon like 'mainline detection' and 'stale artifact discovery' with plain language explaining what is detected and cleaned, e.g., 'Identifies and removes unused branches, orphaned build artifacts, and dead code from repositories'.
Specify the scope more clearly—is this for git branches, build artifacts, unused source files, or all of the above? This will help distinguish it from linting or refactoring skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions like 'mainline detection', 'stale artifact discovery', and 'safe execution', but these are somewhat jargon-heavy and not fully concrete. 'Targeted cleanup and confirmation' adds some detail but remains vague about what exactly is being cleaned up. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per the rubric, 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' which are not terms users would naturally say. Missing natural keywords like 'delete unused files', 'remove dead code', 'clean up branches', or 'remove old files'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Code cleanup' is somewhat specific but could overlap with linting, refactoring, or formatting skills. Terms like 'mainline detection' and 'stale artifact discovery' add some distinctiveness but are unclear enough that they don't carve out a precise niche. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates strong workflow design with clear phasing, validation checkpoints, and safety features (staged deletion, path whitelisting, dry-run mode). However, it is severely over-verbose by inlining all implementation code in a single file, mixes languages unnecessarily, and relies on undefined pseudo-APIs that make the code non-executable. The content would benefit greatly from extracting implementation into separate scripts and keeping SKILL.md as a concise orchestration overview.
Suggestions
Extract the implementation code for each phase into separate script files (e.g., scripts/mainline-detect.js, scripts/drift-discover.js) and reference them from SKILL.md with one-line descriptions.
Remove or consolidate the Chinese-language comments — pick one language consistently and eliminate redundant explanations of what the code does.
Define or document the pseudo-API functions (spawn_agent, wait_agent, bash, Write, Read, request_user_input) either inline or in a referenced REFERENCE.md so the code becomes actionable.
Reduce SKILL.md to a concise overview (~50-80 lines) covering the workflow phases, key commands, and pointers to implementation files rather than embedding all code inline.
| 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 utility functions Claude already knows how to write. The full implementation code for every phase is inlined rather than referenced, consuming excessive tokens. | 1 / 3 |
Actionability | The code blocks are detailed and mostly concrete, but they use pseudo-API functions (spawn_agent, wait_agent, followup_task, close_agent, Write, Read, request_user_input) without defining or importing them, making the code not truly executable as-is. The JavaScript mixed with bash invocations via an undefined `bash()` function further reduces copy-paste readiness. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (Detect → Discover → Confirm → Stage → Execute), includes validation checkpoints (path validation, manifest schema validation, user confirmation gate), staged deletion before permanent removal, dry-run mode, and error recovery cascades for agent timeouts. The feedback loops are well-defined. | 3 / 3 |
Progressive Disclosure | All implementation details are inlined in a single monolithic file with no references to supporting files. The full code for every phase is dumped into SKILL.md rather than being split into referenced scripts or documentation files. No bundle files are provided, and the content that could be in separate files (agent prompts, utility functions, manifest schemas) is all inline. | 1 / 3 |
Total | 7 / 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
227244f
- 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.