Content
72%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 content is highly actionable with concrete commands and examples, but the batch extraction workflow lacks an embedded validation checkpoint and all detail is inlined into a single file rather than progressively disclosed.
Suggestions
Insert an explicit validation checkpoint in the run sequence, e.g. 'Verify result count > 0 and spot-check fields before summarizing; if empty, consult the error table and retry.'
Move the long Supported Marketplaces list and per-workflow input schemas into a reference file (e.g. references/marketplaces.md) and link from SKILL.md.
Remove the verbatim repeat of the frontmatter description under the H1 to trim tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient actionable reference (JSON inputs, field tables, commands, error table) with no concept-explanation fluff; minor trim opportunities exist in the repeated intro line and per-workflow 'Best for:' audience labels. | 4 / 5 |
Actionability | Copy-paste ready 'node --env-file=...' commands, the concrete Actor ID 'apify/e-commerce-scraping-tool', per-workflow JSON input examples, and --format/--output flags cover the common cases fully. | 5 / 5 |
Workflow Clarity | A 5-step progress checklist and 3-step run sequence exist with an error-handling table, but this batch extraction workflow lacks an explicit validation checkpoint (e.g. verify result count before summarizing), capping it at 3 per the batch-operation guideline. | 3 / 5 |
Progressive Disclosure | Section structure is good, but everything is inlined into one monolithic SKILL.md with no reference docs split out; the only external reference (reference/scripts/run_actor.js) is not present as a bundle file, and long marketplace lists and per-workflow schemas could live in separate files. | 3 / 5 |
Total | 15 / 20 Passed |