Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill body is highly actionable with a well-sequenced, validation-checked workflow and an executable bundled script. It is somewhat verbose and keeps nearly all detail inline rather than using progressive disclosure to split reference material into separate files.
Suggestions
Move the 16-check reference table and/or the per-dimension rubric anchors into a separate reference file (e.g. references/rubric.md) and link to it from SKILL.md, so SKILL.md reads as an overview and trims the inline token load.
De-duplicate the inline statistics and the Research References table — either cite inline without restating each claim in a second table, or move all provenance to the reference file.
Consolidate the duplicated foundational-scoring explanation (the '50% foundational / 50% intelligence' framing appears in the intro, Step 5, and the 16-checks section).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly operational and dense, but inline statistics (e.g. '4.8x more citations', '76% of ChatGPT's most-cited pages') are restated in the trailing Research References table, and several sections could be tightened. Not a 3 because of that duplication and padding; not a 1 because it largely avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | Provides an executable command ('node <skill-path>/scripts/aeo-audit.mjs <url> --max-pages=10 --out=<output-dir>/aeo-audit.json'), concrete JSON field names, an explicit scoring formula, and a copy-paste report template. Not a 2 because the guidance is concrete and executable rather than pseudocode or abstract. | 3 / 3 |
Workflow Clarity | A clearly sequenced 7-step workflow with explicit validation checkpoints: stop on script error, sanity-check divergence of >25 points with a re-read loop, and rationale-before-score discipline. Not a 2 because validation and feedback loops are explicit, not implicit. | 3 / 3 |
Progressive Disclosure | The single bundle file (scripts/aeo-audit.mjs) is one level deep and cleanly signaled, but SKILL.md itself is the full content — rubric anchors, the 16-check table, the report format, and research references all live inline rather than being split into referenced materials. Not a 3 because SKILL.md is not an overview pointing to detailed materials; not a 1 because organization is clear and references are not deeply nested. | 2 / 3 |
Total | 10 / 12 Passed |