Content
78%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 SKILL.md body is a well-structured, actionable overview: it provides concrete CLI commands and file paths, a numbered quick-start workflow with a test-before-deploy checkpoint, and cleanly delegates detailed schema/logging/standby docs to real one-level reference files. It is efficient with only minor conceptual padding and lacks an explicit deploy-time validation feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely efficient — terse command blocks ('apify run', 'apify push'), bullet-form Do/Don't lists, and pointed security notes — but contains minor padding such as the "What are Apify Actors?" conceptual explanation and repeated reiteration of the local-storage-not-synced caveat that could be trimmed. | 4 / 5 |
Actionability | Most guidance is concrete and executable: exact CLI commands, template flags ('apify create <actor-name> -t ts_empty'), file paths ('storage/key_value_stores/default/INPUT.json'), and concrete concurrency ranges; minor gaps exist where schema configuration is delegated to references without an inline starter example. | 4 / 5 |
Workflow Clarity | The Quick Start Workflow gives a clearly numbered 8-step sequence with a 'Test locally' checkpoint before 'Deploy', and the body repeatedly flags validation (input validation, sanitize crawled data, npm audit); it stops short of an explicit validate→fix→retry feedback loop for the deploy step, so it sits just below the top anchor. | 4 / 5 |
Progressive Disclosure | The body is a clean overview that offloads detailed material to seven real, one-level-deep reference files (actor-json.md, input-schema.md, output-schema.md, dataset-schema.md, key-value-store-schema.md, logging.md, standby-mode.md), each linked with clear signaling, so navigation is easy and content is appropriately split. | 5 / 5 |
Total | 17 / 20 Passed |