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.
99
100%
Does it follow best practices?
Impact
99%
1.39xAverage score across 3 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 what the skill does (compressed communication with reduced token usage), how it works (multiple intensity levels), and when to use it (comprehensive list of trigger phrases). The description is concise yet thorough, with excellent trigger term coverage and a very distinctive niche that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete capabilities: cuts token usage ~75%, maintains technical accuracy, supports specific intensity levels (lite, full, ultra, wenyan-lite, wenyan-full, wenyan-ultra). These are specific, actionable details. | 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 multiple 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. | 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 demonstrates strong self-awareness by embodying its own principles — it's concise, actionable, and well-structured. The intensity level table with parallel examples across all levels is particularly effective for disambiguation. The Auto-Clarity section showing when to break out of caveman mode for safety-critical situations demonstrates thoughtful boundary design.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill practices what it preaches — it's lean, uses tables and examples efficiently, and never explains concepts Claude already knows. Every section earns its place with no filler or redundant explanation. | 3 / 3 |
Actionability | Concrete examples at every intensity level, clear pattern templates ('thing action reason'), specific before/after comparisons, and explicit trigger phrases and exit commands. Claude knows exactly what to do and when. | 3 / 3 |
Workflow Clarity | For a behavioral/communication skill, the workflow is exceptionally clear: activation triggers, persistence rules, intensity switching via /caveman command, auto-clarity exceptions with explicit examples, and clean exit conditions. The destructive-op example demonstrates the safety feedback loop (drop caveman → warn clearly → resume). | 3 / 3 |
Progressive Disclosure | For a self-contained skill under ~80 lines with no need for external references, the content is well-organized into logical sections (Persistence, Rules, Intensity, Auto-Clarity, Boundaries) with a clear hierarchy. The intensity table provides scannable reference without bloat. | 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
655b7d9
- 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.