Content
71%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 a strong, well-structured operational guide: concrete CLI commands, a clear sequenced workflow with verification steps, and exemplary progressive disclosure that offloads schema and standby-mode detail to real, one-level-deep reference files. Its main weaknesses are repetition (the same warnings appear two to three times), a concept-intro section that assumes Claude lacks basic knowledge, and the absence of a minimal runnable actor code example. Given a weak description field but strong content, the highest-leverage fix is deduplicating repeated warnings and adding a small main.js/main.py sample.
Suggestions
Deduplicate the repeated warnings — state the npm-start prohibition and the local-storage-not-synced caveat once each (Local Testing is the natural home) and cut the "What are Apify Actors?" concept intro to two lines.
Add a minimal runnable actor entry-point snippet (e.g., a 10-line src/main.js with Actor.main and a Dataset.push) under the "Implement logic" step so the core step is copy-paste ready like the rest of the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly tight imperative lists, but includes unnecessary padding: the "What are Apify Actors?" concept intro, the npm-start prohibition repeated three times (Best Practices ✗ list, Commands section, Quick Start), the local-storage-not-synced warning duplicated (✗ list and Local Testing section), and the generatedBy note duplicated from frontmatter. Not a 2 because the bulk is efficient and actionable; not a 4 because the redundancy is noticeable. | 3 / 5 |
Actionability | Concrete, executable commands throughout ("apify create <actor-name> -t project_empty", "apify info # Should return your username", exact schema file paths, storage/key_value_stores/default/INPUT.json). Falls short of 5 because the core "Implement logic" step has no runnable actor entry-point code sample for any of the three supported languages. | 4 / 5 |
Workflow Clarity | The 8-step Quick Start is clearly sequenced with explicit checkpoints (verify CLI with "apify --help", verify auth with "apify info", test locally with "apify run" before "apify push"), and the Local Testing section clarifies verification. Not a 5 because there is no validate→fix→retry feedback loop for local test failures; not a 3 because validation checkpoints are present and explicit. | 4 / 5 |
Progressive Disclosure | Clean overview body with seven well-signaled one-level-deep references ("See [references/actor-json.md](references/actor-json.md)" etc.); all seven referenced files exist and contain no nested references, and detailed schema/logging/standby material is appropriately split out of SKILL.md. Matches the top anchor: easy navigation, clear overview, appropriate split. | 5 / 5 |
Total | 16 / 20 Passed |