Content
92%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.
An exemplary short, self-contained instruction skill: token-efficient, well-sequenced with a tool fallback, and ending in a concrete handoff to adjacent skills. The single gap is actionability polish — the analysis framework is specific but no example report structure shows what the findings output should look like.
Suggestions
Add a brief example of the expected output (e.g., a 3-line skeleton of the findings report: angle observed, evidence, recommended move) to make the 'report the angles and gaps' step fully concrete.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is lean with zero padding: no concept explanations Claude already knows, and lines like 'longevity alone does not establish profitability' and 'absence is opportunity' deliver non-obvious domain judgment in few tokens. Every token earns its place, matching the level-5 anchor and clearly above level 4's 'minor instances of over-explanation'. | 5 / 5 |
Actionability | Guidance is mostly executable for an instruction-only skill: a concrete tool ('Use `research_campaign_opportunity`'), an explicit fallback ('Ask for public ad-library links or examples when the tool does not return competitor ads'), and specific analysis dimensions (price framing, trial, guarantee, urgency). It falls short of level 5 because no example output or report format covers the common case, leaving the final 'report the angles and gaps' deliverable underspecified. | 4 / 5 |
Workflow Clarity | The numbered sequence (find what they run → read the pattern → turn it into your move) is clear and unambiguous, with a conditional fallback branch in step 1 when the tool returns nothing. The skill is explicitly read-only ('Reads and research only; this does not spend money'), so no destructive/batch validation cap applies, and it meets the simple-skill exception where a clear single-purpose flow can score 5. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ directories exist), and the body is well-organized into numbered sections plus a Rules section — exactly the case the guidelines allow to score 5. The one cross-reference ('take it to the **ad-copy-generation** or **launch** skill') is clearly signaled and one level deep. | 5 / 5 |
Total | 19 / 20 Passed |