Content
65%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 body is concise and actionable with a clear sequenced workflow and good error handling, but it is held back by a missing output-validation checkpoint and a referenced script that is absent from the bundle.
Suggestions
Add an explicit validation step to the workflow (e.g., after Step 4, verify the output file is non-empty and well-formed before summarizing) to satisfy the batch-operation feedback-loop requirement.
Ensure the referenced run_actor.js (and its reference/scripts/ directory) ships with the skill bundle, or inline the script's behavior so the commands are self-contained.
Condense the three near-identical output-format bash blocks into one block with a documented --format flag to reduce repetition.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no padding about what Apify or the platforms are; a dense actor-selection table and direct bash commands assume Claude's competence, with only minor repetition across the three output-format examples that could be tightened. | 4 / 5 |
Actionability | Concrete, copy-paste bash commands with real actor IDs and flag examples are provided, but placeholders (ACTOR_ID, JSON_INPUT) must be substituted and the referenced run_actor.js script is not present in the bundle. | 4 / 5 |
Workflow Clarity | A clear five-step sequence with a progress checklist and an error-handling section is present, but this batch data-extraction workflow lacks an explicit validation/verification checkpoint, which caps workflow clarity at 3 per the guidelines. | 3 / 5 |
Progressive Disclosure | Sections are reasonably organized (Prerequisites, Workflow, Steps, Error Handling), but the only external reference (${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js) is not present in the bundle, so the reference is neither verifiable nor clearly signaled. | 3 / 5 |
Total | 14 / 20 Passed |