skill-review

# Skill Review ## Purpose Assess whether a skill earns its place. A skill costs context and attention every time it loads; it must return more than it costs. ## When to Use - Reviewing a skill before publishing it. - A skill that triggers unreliably. - Auditing a skill library for redundancy and dead weight. - Deciding whether two skills should be merged or split. ## Capabilities - Triggering evaluation: does it fire when it should, and stay silent when it should not? - Content quality: is the guidance specific, correct, and actionable? - Redundancy check: does it tell the model something it does not already do? - Overlap detection across a library. ## Inputs - The skill, and the library it sits in. - Real user phrasings for the task it addresses. - The model's behavior on that task without the skill. ## Outputs A verdict with specifics: - **Keep** — Triggers correctly, changes behavior for the better. - **Revise** — Named defects: description, content, or scope. - **Merge or delete** — It duplicates another skill, or adds nothing. ## Workflow 1. **Test the triggering first** — Ten phrasings that should trigger it, and five that should not. This is the fastest way to find that a skill is unusable, and it is the most common defect. 2. **Run the task without the skill** — Establish the baseline. If the model already handles the task well, the skill is not needed. 3. **Run it with the skill** — Compare. The difference is the skill's entire value. If there is no diff...