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

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

100%Weight 40%Scale 1-3

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

A concise, actionable skill body with an executable command, a clearly sequenced workflow containing validation and retry feedback loops, and appropriate offloading of implementation to the scripts/ bundle. It avoids teaching known concepts and stays lean.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse rule lists ('Articles: a, an, the'), fragments, and minimal prose — without padding or explaining concepts Claude already knows.	3 / 3
Actionability	Provides a concrete executable command ('cd caveman-compress && python3 -m scripts <absolute_filepath>'), explicit before/after compression examples, and concrete rules that are directly applicable.	3 / 3
Workflow Clarity	The Process section is a clear numbered sequence with explicit validation ('validate output', 'cherry-pick fix', 'retry up to 2 times', 'leave original file untouched') forming a feedback loop for a destructive overwrite operation.	3 / 3
Progressive Disclosure	The SKILL.md is an overview with well-organized sections, and the actual implementation is correctly split into the adjacent scripts/ bundle (cli.py, compress.py, detect.py, validate.py) referenced by real paths, keeping references one level deep.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, third-person description that names concrete actions, natural trigger terms, and an explicit trigger clause answering both what and when. It is distinct from other skills and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Compress natural language memory files', 'Preserves all technical substance, code, URLs, and structure', and the backup behavior — rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (compress memory files into caveman format) and 'when' via an explicit 'Trigger:' clause, satisfying both halves.	3 / 3
Trigger Term Quality	Includes natural user-facing terms ('CLAUDE.md', 'todos', 'preferences', 'memory files') plus explicit trigger phrases ('compress memory file'), matching how a user would phrase the request.	3 / 3
Distinctiveness Conflict Risk	The caveman-format compression niche and explicit trigger make it unlikely to fire for unrelated skills; it is 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthonystepvoy/caveman-opencode
Path: .opencode/skills/caveman-compress/SKILL.md
Commit: 89d14c7

Reviewed: 10 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.