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".
76
95%
Does it follow best practices?
Impact
—
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 well-structured skill description with excellent trigger terms and clear completeness. Its main weakness is that the specificity of capabilities could be slightly more detailed (e.g., what modes/skills/commands are covered), but the description is concise and functional for skill selection purposes.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It describes a concrete action ('Quick-reference card for all caveman modes, skills, and commands' and 'One-shot display, not a persistent mode') but doesn't list multiple specific capabilities beyond displaying a reference card. | 2 / 3 |
Completeness | Clearly answers both 'what' (displays a quick-reference card for caveman modes, skills, and commands as a one-shot display) and 'when' (explicit trigger terms listed after 'Trigger:'). The trigger guidance is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Excellent trigger terms that match natural user language: '/caveman-help', 'caveman help', 'what caveman commands', 'how do I use caveman'. These cover multiple natural phrasings a user would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — it's specifically a help/reference card for 'caveman' functionality with unique 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 reference card skill that exemplifies concise, actionable documentation. It uses tables effectively to compress mode and skill information, provides concrete configuration examples, and clearly bounds its own behavior (one-shot, no side effects). The structure is clean and navigable with no wasted tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables to compress information, avoids explaining what caveman mode is conceptually, and every line serves a purpose. No unnecessary filler or explanation of obvious concepts. | 3 / 3 |
Actionability | Provides concrete triggers, exact commands, specific config file paths, environment variable names, and JSON examples. Everything is copy-paste ready — from the export command to the config file content. | 3 / 3 |
Workflow Clarity | This is a single-purpose reference card skill with no multi-step or destructive operations. The single action (display reference card) is unambiguous, and the instruction 'One-shot — do NOT change mode, write flag files, or persist anything' clearly bounds behavior. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Modes, Skills, Deactivate, Configure, More). Content is appropriately sized for a single file reference card. Links to full docs externally for deeper information without nesting references. | 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
655b7d9
- 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.