Content
93%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.
An exemplary lean lookup skill: fully executable commands, a clear sequenced workflow with fallback branches, and a useful slug index, all within ~45 lines with zero padding. The only minor gap is the absence of a validation checkpoint for confirming that retrieved docs match the installed framework version.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and operational — "Before implementing non-trivial Agent-Native functionality, read the version-matched docs installed with `@agent-native/core`" — with no concept explanations and every section carrying executable guidance. Every token earns its place. | 5 / 5 |
Actionability | Fully executable, copy-paste-ready commands throughout: `pnpm action framework-search --pattern "<feature>"`, `pnpm action docs-search --slug <slug>`, `pnpm add -D @agent-native/core-corpus@<installed-core-version>`, plus concrete `rg` fallbacks. Placeholders like `<feature>` are appropriately parameterized, and the Useful Slugs table maps common needs to real slugs. | 5 / 5 |
Workflow Clarity | A clear 7-step sequence with error-recovery fallbacks ("If it reports that template source is unavailable, install the matching corpus package"; "If the action runner is unavailable, search ... directly with `rg`"). It stops short of anchor 5 because there is no validation checkpoint confirming the found docs match the installed version or that a search returned the relevant result. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no bundle files, and is well-organized into Rule / How / Useful Slugs / Don't sections; the slug table functions as an in-skill index to the docs corpus. Per the rubric's simple-skill exception, well-organized sections without external references merit a 5. | 5 / 5 |
Total | 19 / 20 Passed |