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".

Quality

95%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

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 help-card skill that exemplifies conciseness and actionability. It uses tables effectively to compress mode and skill references, provides concrete configuration examples, and clearly constrains its own behavior (one-shot, no persistence). The content is well-structured and every section earns its place.

Dimension	Reasoning	Score
Conciseness	Extremely lean and efficient. Uses tables to compress information, avoids explaining what Claude already knows, and every token serves a purpose. The caveman style itself reinforces brevity.	3 / 3
Actionability	Provides concrete triggers, exact commands, configuration examples with executable bash and JSON snippets, and clear resolution order. Everything is copy-paste ready.	3 / 3
Workflow Clarity	This is a simple single-purpose skill (display a reference card). The single action is unambiguous: display the card, don't persist anything. The instruction 'One-shot — do NOT change mode, write flag files, or persist anything' is a clear constraint. No multi-step workflow is needed.	3 / 3
Progressive Disclosure	Well-organized with clear sections (Modes, Skills, Deactivate, Configure, More). Links to full docs externally. For a help card skill with no bundle files, the structure is appropriately flat and navigable.	3 / 3
	Total	12 / 12 Passed

Description

89%

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 well-structured description that clearly communicates its purpose as a help reference card and provides excellent explicit trigger terms. Its main weakness is that the 'what' portion could be slightly more specific about what information the reference card actually displays (e.g., does it list commands, show syntax, provide examples?). Overall it performs well across all dimensions.

Dimension	Reasoning	Score
Specificity	It describes a concrete action ('Quick-reference card' and 'One-shot display') and names the domain (caveman modes, skills, commands), but doesn't list multiple specific actions beyond displaying help information.	2 / 3
Completeness	Clearly answers both 'what' (quick-reference card for all caveman modes, skills, and commands; one-shot display) and 'when' (explicit trigger terms listed after 'Trigger:'). The trigger clause serves as an explicit 'Use when' equivalent.	3 / 3
Trigger Term Quality	Excellent trigger term coverage with natural phrases users would actually say: '/caveman-help', 'caveman help', 'what caveman commands', 'how do I use caveman'. These cover multiple natural variations of how a user would request this.	3 / 3
Distinctiveness Conflict Risk	Very distinct niche — it's specifically a help/reference card for 'caveman' commands. The trigger terms are highly specific and unlikely to conflict with other skills unless there are multiple caveman-related skills, but even then the 'help' focus distinguishes it.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: anthonystepvoy/caveman-opencode
Commit: dcb485a

Reviewed: 15 days 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.