CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-compress

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/caveman-compress/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-organized, actionable, and notably strong on workflow clarity with validation and retry loops around a destructive operation. Conciseness and progressive disclosure are solid with only minor redundancy and navigation gaps.

DimensionReasoningScore

Conciseness

The body is mostly lean and list-driven without explaining concepts Claude already knows, but the "Preserve EXACTLY" section and the later "CRITICAL RULE" block重复 the same code-block preservation rules, a minor instance of over-explanation that could be trimmed.

4 / 5

Actionability

It provides a concrete, copy-pasteable command ("python3 -m scripts <absolute_filepath>"), explicit remove/preserve/compress rule lists, and before/after Pattern examples; it stops short of anchor 5 only because the compression itself relies on Claude's judgment rather than fully deterministic steps.

4 / 5

Workflow Clarity

The Process section lays out a clear sequence with explicit validation ("validate output"), a feedback loop ("if errors: cherry-pick fix ... retry up to 2 times"), and a safe fallback ("leave original file untouched"), matching the anchor for explicit validation steps with error-recovery loops; the destructive overwrite is properly guarded so no cap applies.

5 / 5

Progressive Disclosure

SKILL.md is a well-sectioned overview and points one level deep to the real scripts/ bundle (e.g., "scripts/__main__.py"), with implementation deferred to scripts; it falls short of anchor 5 because references are signaled as a directory rather than per-concern files, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

70%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 clear, third-person, and covers both what the skill does and its trigger, with a distinct niche. Its main limitation is that it conveys essentially one core action and relies on a slash-command trigger rather than natural user phrasing.

Suggestions

Add a 'Use when...' clause naming natural user phrasing (e.g., 'Use when the user asks to compress CLAUDE.md or a todo list to save tokens') rather than only the slash-command trigger, to make the 'when' guidance more explicit.

Enumerate a couple more concrete actions/outcomes (e.g., 'overwrites the original in place and restores from the out-of-tree backup on failure') to lift specificity beyond the single compress action.

DimensionReasoningScore

Specificity

The description names the domain ("memory file such as CLAUDE.md or a todo list") and the core action ("Compress ... into caveman format to save input tokens, keeping a readable backup"), but really describes one core action with its outcomes rather than multiple distinct concrete actions, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

It answers both 'what' (compress memory files into caveman format, keep a backup) and 'when' ("Trigger: /caveman-compress"), satisfying the explicit-trigger requirement so it is not capped at 3; the 'when' is only a slash command and lacks natural phrasing, matching the 'when could be more explicit' anchor.

4 / 5

Trigger Term Quality

Natural keywords are present ("CLAUDE.md", "todo list", "memory file", "compress", "save input tokens") plus an explicit slash trigger, giving good coverage a user would plausibly say; it falls just short of anchor 5 because synonyms and file extensions are not enumerated.

4 / 5

Distinctiveness Conflict Risk

The "caveman format" niche and /caveman-compress trigger are distinct with low conflict risk, but "compress a memory file to save tokens" has minor overlap with general token-reduction or compression skills, fitting the 'mostly distinct; minor overlap risk' anchor rather than a clean 5.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
JuliusBrussee/caveman
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.