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.
96
100%
Does it follow best practices?
Impact
96%
1.00xAverage score across 38 eval scenarios
Passed
No known issues
Quality
Discovery
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, quantified benefits and comprehensive trigger terms. It answers both what the skill does and when to use it, with natural language triggers that users would actually say. The description is concise yet thorough, and the skill occupies a distinct niche unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete capabilities: cuts token usage ~75%, maintains technical accuracy, supports specific intensity levels (lite, full, ultra, wenyan variants). Describes a clear, specific communication mode with quantified impact. | 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 |
Implementation
100%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 skill that is both self-demonstrating and highly functional. It provides concrete examples across all intensity levels, clear activation/deactivation rules, and thoughtful safety exceptions (Auto-Clarity section). The content is lean, well-structured, and every token contributes to Claude's ability to execute the skill correctly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill practices what it preaches — it's written in a terse, efficient style with no unnecessary explanation. Every section earns its place, and there's no padding or explanation of concepts Claude already knows. | 3 / 3 |
Actionability | Highly actionable with concrete before/after examples for each intensity level, specific rules for what to drop and keep, exact patterns to follow, and clear trigger/exit conditions. The examples are copy-paste ready behavioral templates. | 3 / 3 |
Workflow Clarity | For a behavioral/communication skill (not a multi-step destructive process), the workflow is crystal clear: activation triggers, persistence rules, intensity switching via /caveman command, auto-clarity exceptions for safety-critical situations, and explicit exit conditions. The Auto-Clarity section serves as a validation checkpoint for when to break the pattern. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Persistence, Rules, Intensity, Auto-Clarity, Boundaries). The intensity table provides a scannable overview, and the skill is appropriately self-contained at under 100 lines with no need for external references. | 3 / 3 |
Total | 12 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- juliusbrussee/caveman
- Commit
84cc3c1
- 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.