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 body is an effective, tight onboarding guide: it branches on audience, gives concrete example prompts, and provides exact setup steps and doc links. Its only real weakness is inherited from the description — the frontmatter gives Claude no signal for when this skill should activate — plus a slightly vague closing instruction.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and well-budgeted: exact prompts to try, a numbered setup path, and terse doc links, with no explanation of concepts Claude already knows. It falls short of anchor 5 only due to minor conversational padding ("Hi, I'm Ben and this is OpenWork"). | 4 / 5 |
Actionability | Concrete, executable guidance throughout: the exact question to ask ("Are you more technical or non-technical?"), copy-ready example prompts, numbered install steps, and specific doc URLs. It is not anchor 5 because "End with two friendly next actions" is directive without providing example actions. | 4 / 5 |
Workflow Clarity | A clear branched sequence: ask the audience question, tailor explanation by branch, give the technical path (install → configure providers → start session), then close with next actions. No validation checkpoints are needed since nothing destructive or batch-oriented is performed, matching anchor 4 rather than 5 due to the implicit (not explicit) handling of the non-technical closing path. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no need for external reference files (none exist in references/, scripts/, or assets/), and is organized into clear sections (audience branches, skills/plugins, MCP, config). Per the rubric guideline this matches anchor 5 for simple skills with well-organized sections. | 5 / 5 |
Total | 17 / 20 Passed |