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".
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 reasonably well-crafted description that excels at trigger term coverage and completeness by explicitly listing when it should be activated. Its main weakness is that the 'what' portion could be more specific about what information the reference card actually displays. The description is concise and uses third person voice appropriately.
Suggestions
Expand the 'what' portion to list specific content shown on the reference card (e.g., 'Displays available caveman modes, syntax examples, and command list').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('caveman modes, skills, and commands') and a specific action ('quick-reference card' / 'one-shot display'), but doesn't list multiple concrete 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 when clause is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger phrases users would actually say: '/caveman-help', 'caveman help', 'what caveman commands', 'how do I use caveman'. These cover common variations of how a user would ask for help. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — it's a help/reference card for 'caveman' commands specifically, with distinct trigger terms that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 help-card skill that exemplifies concise, well-structured reference content. Tables are used effectively to compress information, the content is immediately actionable with concrete triggers and configuration examples, and the organization makes it easy to scan. The skill practices what it preaches—caveman-style terseness applied to its own documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Tables compress mode/skill info perfectly. No unnecessary explanations—every token earns its place. Assumes Claude understands the concepts without hand-holding. | 3 / 3 |
Actionability | Concrete triggers, exact commands, specific config file paths, environment variable names, and JSON examples are all provided. Copy-paste ready configuration examples with clear precedence rules. | 3 / 3 |
Workflow Clarity | This is a single-purpose reference card (one-shot display), so no multi-step workflow is needed. The single action is unambiguous: display this card when triggered. Deactivation and configuration steps are clearly sequenced. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Modes, Skills, Deactivate, Configure, More). Links to full docs externally. Content is appropriately sized for a help card—nothing needs to be split out, and nothing is missing. | 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
8bab5c7
- 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.