CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

caveman-help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A tight, well-organized reference card: every token is non-derivable fact, the single action is unambiguous with explicit negative constraints, and the section structure is clean for a small single-file skill. The only minor gap is that the exact output format of the displayed card is left implicit.

DimensionReasoningScore

Conciseness

The body is lean and table-driven ('Drop filler. Keep sentence structure.'), with zero space given to concepts Claude already knows; every line carries non-derivable facts such as the mode list, triggers, and the config resolution order 'env var > config file > full'. Matches the anchor for lean and efficient content where every token earns its place.

5 / 5

Actionability

Concrete user commands ('/caveman lite', '/caveman-commit'), copy-paste config snippets ('export CAVEMAN_DEFAULT_MODE=ultra' and the JSON config example), and exact deactivation phrases ('stop caveman', 'normal mode') make the guidance mostly executable. It is not 5 because 'Display this reference card... Output in caveman style' leaves the exact output form (verbatim tables vs. reformatted card) implicit.

4 / 5

Workflow Clarity

This is a simple single-task skill, so the simple-skill exception applies: the single action is unambiguous — 'Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything.' The explicit negative constraints remove ambiguity, and there are no destructive or batch operations, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The bundle contains no references/, scripts/, or assets/ directories — this is a small single-file skill, and the under-50-lines exception applies: the content is organized into clear sections (Modes, Skills, Deactivate, Configure Default Mode, More) with a clearly signaled external docs link (https://github.com/JuliusBrussee/caveman).

5 / 5

Total

19

/

20

Passed

Description

78%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.

The description clearly states what the skill does and when to use it, with explicit natural-language trigger phrases in third person voice. The weaknesses are mild: the capability statement is thin beyond 'quick-reference card', a few natural trigger synonyms are missing, and one trigger overlaps the core caveman mode skill.

Suggestions

Enumerate one or two more concrete capabilities in the description (e.g., 'Lists all modes, triggers, config options, and deactivation commands') to lift specificity beyond the single 'quick-reference card' action.

Add natural trigger synonyms such as 'caveman modes', 'list caveman commands', or 'caveman options' to broaden keyword coverage.

Narrow the 'how do I use caveman' trigger (e.g., 'how do I use caveman commands') to reduce overlap with the core /caveman mode skill.

DimensionReasoningScore

Specificity

Names the domain ('Quick-reference card for all caveman modes, skills, and commands') and one concrete behavior ('One-shot display, not a persistent mode'), matching the anchor for domain plus 1-2 concrete actions that are not comprehensive. It is not 4 because no several specific actions are listed, and not 2 because the scope and display behavior go beyond minimal or generic.

3 / 5

Completeness

Both questions are answered explicitly: the 'what' is 'Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode', and the 'when' is an explicit 'Trigger:' clause with concrete phrases. This matches the anchor for clearly and explicitly answering both what and when with concrete trigger phrases, and the explicit trigger guidance means the missing-'Use when' cap does not apply.

5 / 5

Trigger Term Quality

Explicit triggers '/caveman-help', 'caveman help', 'what caveman commands', and 'how do I use caveman' are natural user phrasings with good coverage. It falls short of 5 because common variants like 'caveman modes', 'list caveman commands', or 'caveman options' are missing.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche within the caveman skill family with distinct triggers ('caveman help', 'what caveman commands'). It is not 5 because 'how do I use caveman' could plausibly match the core /caveman mode skill rather than this help card — minor overlap risk with a closely related skill.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

masweb/waxp-vuebo

Path

.agents/skills/caveman-help/SKILL.md

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.