Content
100%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 model of lean, unambiguous instruction: it names the exact tool, the exact output behavior, and the ordered failure-handling procedure in two sentences. Nothing is missing for a skill of this scope and nothing should be cut.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The two-sentence body ('Call the ctx_doctor tool and show its table to the user unchanged. If a row failed, list the fixes it names, in order.') is entirely load-bearing — even 'unchanged' and 'in order' prevent concrete failure modes. Every token earns its place and nothing explains what Claude already knows. | 5 / 5 |
Actionability | The instruction is fully executable for an instruction-only skill: it names the exact tool ('ctx_doctor'), specifies output handling ('show its table to the user unchanged'), and defines the failure path ('If a row failed, list the fixes it names, in order'). Per the rubric's scoring notes, absence of code is not penalized when guidance is this concrete. | 5 / 5 |
Workflow Clarity | This is a simple single-task skill and the single action is unambiguous, covering both the success path and the failure branch — the rubric's simple-skill exception allows a 5 here. No destructive or batch operations exist that would require validation checkpoints. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references or bundle files (no references/, scripts/, or assets/ exist), and the entire body is appropriately contained in SKILL.md. The rubric's guideline for short, self-contained skills supports a 5; adding sections or reference files would only add noise. | 5 / 5 |
Total | 20 / 20 Passed |