CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-compress

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/caveman/skills/caveman-compress/SKILL.md

The canonical home for this skill is caveman-compress in JuliusBrussee/caveman

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 actionable and well-structured with a sound fail-safe workflow for a destructive operation. The main weakness is conciseness, due to repeated explanations of the backup location and code-block preservation rules.

Suggestions

Consolidate the backup-directory explanation into one place and cross-reference it from Boundaries instead of restating it.

Merge the 'CRITICAL RULE' code-block block with the 'Preserve EXACTLY' section to avoid restating the same preservation rules twice.

Make the validation/retry checkpoints explicit steps Claude performs (or clearly states are CLI-internal) so the workflow sequence reads as a checklist.

DimensionReasoningScore

Conciseness

Mostly efficient with well-organized rules, but repeats the backup-directory explanation (Purpose vs Boundaries) and restates code-block preservation across the 'Preserve EXACTLY' section and the 'CRITICAL RULE' block; could be tightened.

3 / 5

Actionability

Provides a concrete executable command ('python3 -m scripts <absolute_filepath>'), specific Remove/Preserve/Compress rules, and before/after examples, with only minor gaps.

4 / 5

Workflow Clarity

Clear numbered sequence with validation and a fail-safe feedback loop ('if errors: cherry-pick fix ... retry up to 2 times ... if still failing ... leave original file untouched'), though the actual validation is delegated to the CLI rather than performed as explicit checkpoints by Claude.

4 / 5

Progressive Disclosure

Well-organized single-file overview with clearly signaled one-level-deep references to the real scripts/ bundle ('The compression scripts live in scripts/'), and no nested reference chains.

4 / 5

Total

15

/

20

Passed

Description

87%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, specific, and third-person, explicitly covering both capabilities and trigger conditions with a distinctive niche. Minor improvements could add a few more natural synonyms, but it broadly meets the top anchors.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Compress natural language memory files ... into caveman format', 'Preserves all technical substance, code, URLs, and structure', 'overwrites the original file', 'backup saved as FILE.original.md'), with only minor gaps in distinguishing actions from described behaviors.

4 / 5

Completeness

Explicitly answers both what (compress into caveman format, preserve substance, overwrite, backup) and when ('Trigger: /caveman-compress FILEPATH or "compress memory file"') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes a natural user phrase ('compress memory file') and a slash trigger ('/caveman-compress FILEPATH') plus concrete file types (CLAUDE.md, todos, preferences), though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche ('caveman format' compression of memory files) with distinct triggers, giving minimal conflict risk with other skills.

5 / 5

Total

18

/

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.