CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

92

1.35x
Quality

90%

Does it follow best practices?

Impact

95%

1.35x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is caveman in JuliusBrussee/caveman

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

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

An exceptionally lean, actionable style guide that practices what it preaches and provides concrete rules and examples with clear guardrails. Structure is good and self-contained, with only minor room to split the dense Intensity reference.

DimensionReasoningScore

Conciseness

Deliberately compressed throughout, assumes Claude's competence, and explains no background concepts — every line earns its place; a model of token efficiency.

5 / 5

Actionability

Concrete executable rules: exact switch syntax, an explicit banned-word list, exact before/after examples per intensity level, and a fixed response pattern — fully actionable despite being instruction-only.

5 / 5

Workflow Clarity

A single-purpose style/mode skill where the action is unambiguous; the level switch, persistence rules, and Auto-Clarity guardrails serve as clear checkpoints, and the destructive-operation validation cap does not apply.

5 / 5

Progressive Disclosure

Single self-contained file with clear, well-labeled sections and no external references needed; the Intensity table and per-level examples are somewhat dense inline, keeping it just short of a 5.

4 / 5

Total

19

/

20

Passed

Description

83%Weight 40%Scale 1-5

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 strong, well-formed description that clearly states the skill's purpose and gives concrete, natural trigger phrases. It fully satisfies the what-and-when requirement and is largely distinct from other skills.

DimensionReasoningScore

Specificity

Names the domain and lists concrete capabilities (the lite/full/ultra and wenyan levels) plus the core compression action, but the levels are variants of one action rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what (ultra-compressed communication mode cutting tokens while keeping technical accuracy) and when (concrete trigger phrases including the slash command).

5 / 5

Trigger Term Quality

Covers natural trigger phrases a user would actually say — /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens" — with strong but not fully exhaustive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche with distinctive triggers; minor overlap risk only from the generic phrases "be brief" / "less tokens" that adjacent skills could also match.

4 / 5

Total

17

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
JuliusBrussee/caveman
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.