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 exceptionally well-crafted skill that embodies its own principles — it's concise, actionable, and clearly structured. The intensity level table with parallel examples across all six modes is particularly effective, giving Claude exact behavioral templates. The Auto-Clarity section showing when to break out of caveman mode for safety-critical situations demonstrates thoughtful boundary design.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill practices what it preaches — it's lean, uses tables and examples efficiently, and never explains concepts Claude already knows. Every section earns its place with no filler or unnecessary context. | 3 / 3 |
Actionability | Provides concrete before/after examples at every intensity level, specific rules for what to drop and keep, exact trigger phrases, and clear patterns to follow. The examples are directly usable as templates for behavior. | 3 / 3 |
Workflow Clarity | For a behavioral/communication skill (not a multi-step process), the workflow is clear: activation triggers, persistence rules, intensity switching via /caveman command, auto-clarity exceptions, and explicit deactivation conditions are all well-sequenced and unambiguous. | 3 / 3 |
Progressive Disclosure | For a standalone skill under 80 lines with no need for external references, the content is well-organized into logical sections (Rules, Intensity, Auto-Clarity, Boundaries) with clear headers and a table for quick reference. No bundle files are needed. | 3 / 3 |
Total | 12 / 12 Passed |