Content
75%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 an efficient, actionable, well-sequenced workflow: select an Actor from a table, fetch its live schema via mcpc, ask preferences, run a script, summarize. Main gaps are the missing example of an actor input JSON, three redundant command variants, and no explicit output-verification checkpoint for batch actor runs.
Suggestions
Add one concrete example of --input JSON for a representative Actor (e.g., apify/instagram-post-scraper with a post URL) so the placeholder is immediately usable.
Collapse the three quick/CSV/JSON bash blocks into a single command showing the optional --output/--format flags.
Add a verification checkpoint after Step 4 (e.g., confirm the output file exists and is non-empty before reporting, and re-check failed runs via the Apify console link) to close the batch-operation validation gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: an actor-selection table, concrete commands, and step headings with no explanations of concepts Claude already knows. It is not 5 because the three near-duplicate bash blocks for quick/CSV/JSON differ only in flags and could be one command, and the parenthetical "(No need to check it upfront)" is filler. | 4 / 5 |
Actionability | Commands are executable and specific (the mcpc tools-call invocation with auth header, and run_actor.js with --actor/--input/--output/--format flags). It is not 5 because JSON_INPUT is a never-exemplified placeholder — no sample actor input JSON is given, and the referenced run_actor.js script is not part of the bundle to verify. | 4 / 5 |
Workflow Clarity | A clear 5-step sequence with a copyable progress checklist, a pre-run schema fetch in Step 2, and an Error Handling section with recovery actions (e.g., Timeout → reduce input or increase --timeout). It is not 5 because there is no explicit output verification step after a batch actor run — Step 5 only asks to report results, not validate them. | 4 / 5 |
Progressive Disclosure | A single well-organized file with clear per-step sections, no nested or buried references, and an external script correctly kept out of the SKILL.md. It is not 5 because at ~110 lines the 17-row actor table is borderline content that could live in a reference file, and no reference files exist to demonstrate one-level-deep disclosure. | 4 / 5 |
Total | 16 / 20 Passed |