caveman-help

Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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.

The body is an exemplary lean reference card: dense tables, exact triggers and commands, concrete configuration with explicit resolution order, and crisp one-shot behavioral constraints. It contains no padding, no inferred-only steps, and no navigation debt.

Dimension	Reasoning	Score
Conciseness	Tables carry all the content with zero padding ('Mode stick until changed or session end.'), and nothing explains concepts Claude already knows — every token earns its place, matching the lean anchor.	5 / 5
Actionability	Exact slash commands per mode and skill, copy-paste-ready config snippets ('export CAVEMAN_DEFAULT_MODE=ultra', the JSON defaultMode example), and an explicit priority order ('Resolution: env var > config file > full'); for an instruction-only skill the guidance is fully actionable with the card itself as the deliverable.	5 / 5
Workflow Clarity	This is a simple single-task skill whose one action is unambiguous ('Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything'), meeting the simple-skill exception; no destructive or batch operations exist, so no validation cap applies.	5 / 5
Progressive Disclosure	A short, well-organized skill with clear sections (Modes, Skills, Deactivate, Language, Configure, More) that needs no external references — the only link is a single one-level pointer to full docs — satisfying the short-skill exception for well-organized sections.	5 / 5
	Total	20 / 20 Passed

Description

82%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 concise, third-person description with an explicit trigger clause and a clearly distinct niche. Its only weakness is thin capability coverage — it says the skill is a reference card but never enumerates what the card helps with (modes, commands, configuration).

Suggestions

Enumerate concrete capabilities in the description, e.g. 'Lists caveman modes and their triggers, available caveman skills, deactivation commands, default-mode configuration via CAVEMAN_DEFAULT_MODE or config.json.'

Add natural trigger variations users might say, such as 'caveman modes', 'what caveman skills exist', or 'caveman commands', to broaden trigger coverage beyond the two literal invocations.

Dimension	Reasoning	Score
Specificity	Names the domain ('caveman modes, skills and commands') and one action ('Quick-reference card'), matching the 'domain plus 1-2 concrete actions' anchor; it does not list several distinct actions, so it falls short of anchor 4.	3 / 5
Completeness	Clearly answers 'what' (quick-reference card for caveman modes, skills and commands) and 'when' with concrete trigger strings ('Trigger: /caveman-help or "caveman help"'), which is more explicit than anchor 4's example and matches the concrete-trigger-phrases anchor; the missing-'Use when' cap does not apply.	5 / 5
Trigger Term Quality	Includes explicit natural trigger phrases ('caveman help', '/caveman-help') a user would actually say, exceeding the bare-domain-keyword level of anchor 3, but lacks synonyms or variations like 'caveman modes' or 'what does /caveman do' needed for anchor 5.	4 / 5
Distinctiveness Conflict Risk	The 'caveman' niche with distinct literal triggers ('/caveman-help', 'caveman help') is unlikely to fire for any other skill, matching the clear-niche anchor.	5 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: JuliusBrussee/caveman
Path: skills/caveman-help/SKILL.md
Commit: f5d7294

Reviewed: 1 hour 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.