Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-structured, lean instruction skill with concrete signal criteria, a clear workflow, and a specific output format; it earns top progressive-disclosure marks as a compact single-purpose skill. The main gaps are the absence of an explicit validation/self-check loop and a worked example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence without explaining what a hashtag or trend is, with only minor rhetorical framing ("Think like an editor with a finger on the pulse") that could be trimmed, placing it just below fully lean. | 4 / 5 |
Actionability | It gives concrete, specific guidance—defined signal criteria (velocity, cross-surface, relevance, runway), a four-step approach, and a fielded output format—so an instruction-only skill is mostly executable, though no worked example of a real trend is provided. | 4 / 5 |
Workflow Clarity | The four-step "How to approach it" sequence is clearly ordered and the skill is non-destructive analysis, so the destructive-operation validation cap does not apply; it sits below 5 only because there is no explicit validation/feedback loop. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, single-purpose, has no external bundle files, and is organized into well-signaled sections (When to use, What a real signal looks like, How to approach it, Output format), matching the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |