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"

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

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

This is a well-structured, actionable skill with clear workflow steps, good error handling, and concrete examples. Its main weakness is moderate verbosity in the compression rules section, where some rules are repeated (code block preservation appears in multiple places) and the lists could be more compact. The progressive disclosure is adequate but the skill is approaching the length where splitting reference material would help.

Suggestions

Consolidate the code block preservation rules—currently stated in 'Preserve EXACTLY', 'CRITICAL RULE', and 'Boundaries' sections. Merge into one authoritative statement.

Consider moving the detailed compression rules (Remove/Preserve/Compress lists) into a separate RULES.md reference file to keep SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The compression rules section is fairly detailed and well-organized, but some content is somewhat verbose for Claude—e.g., listing every filler word and explaining what 'preserve exactly' means with extensive bullet lists. The boundaries and critical rule sections repeat some concepts (e.g., code block preservation is stated multiple times). Could be tightened.	2 / 3
Actionability	Provides a concrete CLI command (`python3 -m scripts <absolute_filepath>`), clear before/after compression examples, explicit lists of what to remove/preserve/compress, and specific file type boundaries. The guidance is directly executable and copy-paste ready.	3 / 3
Workflow Clarity	The process section has a clear numbered sequence with explicit validation, error recovery (cherry-pick fix, retry up to 2 times), and a failure fallback (leave original untouched). The backup step is clearly stated in boundaries. This is a well-defined workflow with appropriate checkpoints.	3 / 3
Progressive Disclosure	The content is all inline in a single file, which is borderline acceptable for this skill's complexity. However, the compression rules section is quite long and could benefit from being split into a reference file. The reference to `scripts/__main__.py` is appropriate but no bundle files were provided to verify. For a skill of this length (~100 lines of substantive content), some separation would improve scannability.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 an excellent skill description that clearly communicates what the skill does (compresses memory files into a token-saving caveman format while preserving technical content and creating backups) and when to use it (via explicit command or natural language trigger). It uses third person voice, includes specific concrete actions, and occupies a highly distinctive niche that minimizes conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: compress natural language memory files, preserve technical substance/code/URLs/structure, overwrite original file, save human-readable backup as FILE.original.md. Very concrete and actionable.	3 / 3
Completeness	Clearly answers both 'what' (compress natural language memory files into caveman format, preserving technical substance, creating backups) and 'when' (explicit trigger clause: '/caveman-compress FILEPATH or "compress memory file"').	3 / 3
Trigger Term Quality	Includes natural trigger terms users would say: '/caveman-compress', 'compress memory file', 'CLAUDE.md', 'todos', 'preferences', 'memory files', 'caveman format', 'input tokens'. Good coverage of both command-style and natural language triggers.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: 'caveman format' compression of memory files is a very specific concept unlikely to conflict with other skills. The specific file types (CLAUDE.md, todos, preferences) and the unique 'caveman' terminology make this clearly distinguishable.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: JuliusBrussee/caveman
Commit: 25d22f8

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.