CtrlK
BlogDocsLog inGet started
Tessl Logo

mac-disk-cleanup

Free disk space on macOS by cleaning dev caches (npm, pip, uv, Homebrew), removing stale node_modules from old projects, and optionally removing LM Studio or Ollama models after confirmation. Use this skill whenever the user mentions disk space, storage full, Mac running out of space, cleaning up node_modules, LM Studio models, Ollama models, or wants to free space on their Mac — even if they don't say "cleanup" explicitly.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, actionable, and well-structured with appropriate references to real scripts and clear safety/confirmation checkpoints for its destructive operations. The main defect is an organizational one: two separate sections are both numbered 'Part 3' (node_modules audit and Disk summary), which should be renumbered to Parts 3 and 4.

Suggestions

Renumber the second '## Part 3 — Disk summary' to '## Part 4 — Disk summary' so the four-step sequence reads correctly.

Provide an exact rm command for LM Studio model removal (e.g. `rm -rf "~/.lmstudio/models/publisher/model-name/"`) instead of describing the deletion only in prose.

Collapse the redundant confirmation guidance: state the 'show summary + ask before deleting' rule once in the Confirmation rule subsection rather than also previewing it in the Part 2 intro.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explanation of what npm/pip/Homebrew are), but the confirmation requirement is restated across the Part 2 intro and the dedicated 'Confirmation rule' subsection, a minor redundancy that could be trimmed.

4 / 5

Actionability

Mostly executable guidance with copy-paste commands (the LM Studio find one-liner, 'ollama list', 'ollama rm <model-name>', the df/awk summary), but LM Studio deletion is described in prose with a path pattern rather than an exact rm command, and node_modules cleanup uses a placeholder path.

4 / 5

Workflow Clarity

A clear sequence with validation checkpoints is present (confirmation before model deletion, show-before-delete for node_modules, before/after df reporting, plus a staleness classification table), but two sections are both labeled 'Part 3' (node_modules audit and Disk summary), a sequencing defect, and there is no error-recovery feedback loop.

4 / 5

Progressive Disclosure

Well-organized into Parts with one-level-deep references to real bundle scripts (scripts/clean_caches.sh and scripts/find_node_modules.sh, both present), but the duplicate 'Part 3' header is a minor navigation/organization gap that keeps it from a clean 5.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 is exemplary: it states concrete capabilities, lists natural trigger terms with synonyms, and explicitly covers both what the skill does and when to use it. It is appropriately concise without fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'cleaning dev caches (npm, pip, uv, Homebrew)', 'removing stale node_modules from old projects', 'optionally removing LM Studio or Ollama models after confirmation' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (free disk space via the three named cleanup actions) and 'when' ('Use this skill whenever the user mentions disk space, storage full...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user phrasings comprehensively, including synonyms: 'disk space', 'storage full', 'Mac running out of space', 'cleaning up node_modules', 'LM Studio models', 'Ollama models', and 'free space on their Mac'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — macOS disk cleanup targeting specific dev caches, node_modules, and local AI model stores — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gitstua/stu-skills
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.