Content
92%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 exemplarily lean delegation stub: it resolves the target file path precisely, defines argument handling, and includes an anti-drift guardrail ("do not improvise a separate workflow and do not summarize from memory"). Its only structural weakness is total dependence on an external sibling file with no guidance for handling its absence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~10-line body is lean and efficient with zero padding: it states the delegation target, the exact path resolution, and the argument mapping without explaining anything Claude already knows. Every token earns its place, matching anchor 5. | 5 / 5 |
Actionability | Guidance is concrete for an instruction-only skill — exact relative path "../hep-search/SKILL.md", the instruction to read and follow it exactly, and the argument rule "treating everything typed after /skill:agentlas-search as that command's request". The minor gap is that all executable domain content lives in an external sibling file with no fallback if it is absent, fitting anchor 4 rather than 5. | 4 / 5 |
Workflow Clarity | The single task is unambiguous: locate the sibling skill directory, read its SKILL.md, follow it exactly, and pass the user's request through. The simple-skill exception applies (no destructive or batch operations), so a clear single-purpose instruction earns 5. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files and a single clearly-signaled, one-level-deep reference (the sibling hep-search/SKILL.md), which is exactly the well-organized, easy-to-navigate structure the rubric rewards. | 5 / 5 |
Total | 19 / 20 Passed |