caveman

Ultra-compressed communication mode. Cuts token usage ~75% 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.

1.02x

Quality

96%

Does it follow best practices?

Impact

80%

1.02x

Average score across 2 eval scenarios

Securityby

Risky

Do not use without reviewing

Quality

Content

92%

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

This is an excellent behavioral skill that is itself a demonstration of concise, actionable writing. It provides clear rules, concrete examples across all intensity levels, smart safety escape hatches (Auto-Clarity), and unambiguous activation/deactivation triggers. The only minor weakness is that all content lives in one file, which is acceptable given no bundle exists, but the six intensity levels with multiple examples each make it slightly longer than ideal for a single SKILL.md.

Dimension	Reasoning	Score
Conciseness	The skill practices what it preaches — it's lean, uses fragments, and avoids explaining concepts Claude already knows. Every section earns its place with no filler or unnecessary context. The intensity table and examples are dense but necessary for disambiguation.	3 / 3
Actionability	Highly actionable with concrete before/after examples at each intensity level, explicit pattern templates ('thing action reason. next step.'), specific words to drop, and clear trigger/exit commands. Claude knows exactly what to do in every scenario.	3 / 3
Workflow Clarity	For a behavioral/communication skill (not a multi-step destructive operation), the workflow is exceptionally clear: activation triggers, persistence rules, intensity switching, auto-clarity escape conditions with examples, and explicit exit conditions. The destructive-op example even demonstrates the clarity escape hatch with a feedback loop.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections (Rules, Intensity, Auto-Clarity, Boundaries), but everything is in a single file. The intensity table and multiple examples for 6 levels make the file moderately long. The wenyan variants could potentially be split into a separate reference, though for a standalone skill without bundle files this is reasonable.	2 / 3
	Total	11 / 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 a strong skill description that clearly communicates a unique capability with specific actions, well-defined intensity levels, and comprehensive trigger terms. It follows the 'Use when...' pattern effectively and covers both natural language triggers and command-based invocation. The description is concise yet thorough, making it easy for Claude to distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities: cuts token usage ~75%, maintains technical accuracy, supports specific intensity levels (lite, full, ultra, wenyan variants). These are specific, actionable details about what the skill does.	3 / 3
Completeness	Clearly answers both 'what' (ultra-compressed communication that cuts tokens ~75% while keeping technical accuracy, with multiple intensity levels) and 'when' (explicit 'Use when' clause with specific trigger phrases plus auto-trigger condition).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms: 'caveman mode', 'talk like caveman', 'use caveman', 'less tokens', 'be brief', '/caveman', and 'token efficiency'. These are phrases users would naturally say when wanting this behavior.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche — 'caveman mode' communication style with specific intensity levels is unlikely to conflict with any other skill. The trigger terms are unique and specific to this particular behavior.	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: 9 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.