caveman

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1.30x

Quality

100%

Does it follow best practices?

Impact

95%

1.30x

Average score across 2 eval scenarios

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 lean, highly actionable body that embodies its own compression philosophy while giving concrete rules, intensity levels, examples, and explicit gating/resume checkpoints. Well-organized into clear sections with no unnecessary explanation.

Dimension	Reasoning	Score
Conciseness	The body practices what it preaches — terse, dense rules with no concept-explanation fluff and no padding; every line earns its place and assumes Claude's competence.	3 / 3
Actionability	Provides concrete, executable guidance: exact switch syntax, a per-intensity level table, and before/after example pairs ('Not: Sure! I'd be happy to... Yes: Bug in auth middleware...'). For an instruction-only skill the direction is specific and copy-ready.	3 / 3
Workflow Clarity	The Auto-Clarity section acts as an explicit validation checkpoint: lists conditions to drop the mode (security warnings, irreversible actions, ambiguity) and resumes after the clear part, with clear sequencing for the persistence/switch lifecycle.	3 / 3
Progressive Disclosure	Single self-contained SKILL.md with no bundle files; content is well-organized into clearly labeled sections (Persistence, Rules, Intensity, Auto-Clarity, Boundaries), which suffices for a simple skill per the scoring notes.	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 tight, well-constructed description that states concrete capabilities, gives natural trigger phrases, and explicitly covers both what and when in third person. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names concrete actions and outcomes — 'Cuts output tokens 65% (measured)', 'keeping full technical accuracy' — and enumerates six specific intensity levels, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Ultra-compressed communication mode...cuts output tokens 65%') and when via a clear 'Use when...' clause with explicit triggers, matching the score-3 anchor exactly.	3 / 3
Trigger Term Quality	Lists natural phrases a user would actually say ('caveman mode', 'talk like caveman', 'be brief', 'less tokens', '/caveman', 'token efficiency'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (caveman-style compression) with highly distinctive triggers unlikely to fire for the wrong skill; the broad 'token efficiency' auto-trigger is the only mild overlap.	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: juliusbrussee/caveman
Path: skills/caveman/SKILL.md
Commit: ec83e5b

Reviewed: 5 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.