Content
86%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.
A lean, well-organized single-purpose skill body: concrete platform and engagement guidance, a clear sequenced workflow, and copy-paste example prompts with no wasted tokens. The only refinements would be explicit validation checkpoints (e.g., verifying the 30-day window per source) and slightly more concrete search mechanics per platform.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~35-line body is lean and assumes Claude's competence: every line gives skill-specific instruction (platforms to search, metrics to capture, de-duplication, ranking, output structure, HTML/ELI5 variants) with no padding and no explanation of concepts Claude already knows. Not a 4 because no section needs trimming. | 5 / 5 |
Actionability | Concrete, specific guidance throughout: named platforms, concrete engagement signals ("upvotes, comments, stars, views, reposts, or prediction odds"), a defined brief structure, and three copy-paste-ready example prompts. It stays below 5 because the actual mechanics of searching each platform and capturing engagement data are left general — a minor gap for an instruction-only skill. | 4 / 5 |
Workflow Clarity | The 8-step workflow is clearly sequenced with implicit quality checkpoints ("De-duplicate repeated stories across platforms", "Rank findings by engagement and relevance, not by editorial placement"). It is not a 5 because there is no explicit validation step, e.g., verifying each source's date falls within the 30-day window before including it. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundle exists), and the body is well organized into Overview, Workflow, and Example Prompts sections — the simple-skill case the rubric scores at 5. | 5 / 5 |
Total | 18 / 20 Passed |