macos-cleaner
Analyze and reclaim macOS disk space through intelligent cleanup recommendations. This skill should be used when users report disk space issues, need to clean up their Mac, or want to understand what's consuming storage. Focus on safe, interactive analysis with user confirmation before any deletions.
Install with Tessl CLI
npx tessl i github:fernandezbaptiste/claude-code-skills --skill macos-cleaner80
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent completeness and trigger term coverage. It clearly states both what the skill does and when to use it, with natural language triggers. The main weakness is that the specific capabilities could be more concrete - listing actual cleanup actions rather than the general 'intelligent cleanup recommendations'.
Suggestions
Add specific concrete actions like 'identify large files, clear system caches, find duplicate files, analyze application storage' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (macOS disk space) and some actions ('analyze', 'reclaim', 'cleanup recommendations'), but lacks specific concrete actions like 'identify large files', 'clear caches', 'remove duplicates', or 'empty trash'. | 2 / 3 |
Completeness | Clearly answers both what ('Analyze and reclaim macOS disk space through intelligent cleanup recommendations') and when ('when users report disk space issues, need to clean up their Mac, or want to understand what's consuming storage'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'disk space issues', 'clean up their Mac', 'storage', 'macOS'. These are phrases users naturally use when experiencing storage problems. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche targeting macOS disk space specifically, with distinct triggers like 'disk space', 'clean up their Mac', 'storage'. Unlikely to conflict with general file management or other OS-specific skills. | 3 / 3 |
Total | 11 / 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 at actionability and workflow clarity with comprehensive, executable guidance and strong safety protocols. However, it severely violates conciseness principles—the content is 5-10x longer than necessary, with extensive repetition of safety rules and explanations of concepts Claude already understands. The verbosity undermines the skill's effectiveness by consuming excessive context window space.
Suggestions
Reduce content by 60-70% by removing redundant safety warnings (consolidate into single section), eliminating explanations of basic concepts (sparse files, tmux basics, Docker fundamentals), and cutting duplicate workflow descriptions
Move the detailed report templates, anti-patterns table, and multi-layer exploration examples to separate reference files (e.g., references/report_templates.md, references/anti_patterns.md)
Consolidate the 10 core principles and 'ABSOLUTE PROHIBITIONS' into a single concise safety section rather than repeating throughout
Remove verbose explanations like 'PDF (Portable Document Format)' equivalents—trust Claude to understand macOS concepts, Docker basics, and file system operations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~800+ lines, with significant redundancy (Docker safety rules repeated 4+ times, Mole tmux workflow explained multiple times). Many sections explain concepts Claude already knows (what sparse files are, how tmux works, basic Docker commands). | 1 / 3 |
Actionability | Excellent executable guidance with copy-paste ready commands throughout. Includes complete bash scripts, specific file paths, exact tmux commands, and detailed command tables. The multi-layer exploration workflow provides step-by-step executable instructions. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The decision tree, Step 2C verification protocol, and report quality checklist provide strong feedback loops. Destructive operations have mandatory confirmation steps and the 'Double-Check Before Delete' protocol is well-defined. | 3 / 3 |
Progressive Disclosure | References external files appropriately (references/cleanup_targets.md, scripts/*.py) but the main document is monolithic with excessive inline content. The report templates, anti-patterns section, and multi-layer exploration workflow could be separate reference files. Content that should be in references is inline. | 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (1203 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- 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.