Content
86%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.
A lean, well-structured instruction skill with a concrete core command, clear sequencing, and an explicit push-recheck feedback loop. The only notable gap is the unspecified command for fetching failed-job logs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place: a trigger, four workflow steps, guardrails, and an output spec with zero padding or explanation of concepts Claude already knows. Lean and efficient, matching the anchor-5 example. | 5 / 5 |
Actionability | Step 1 gives a concrete executable command ("gh pr checks --json name,bucket,state,workflow,link") and the workflow is instruction-only, so lack of code is not penalized. However, "inspect failed jobs and extract the first actionable error" omits the concrete log-fetching command (e.g., "gh run view --log-failed"), leaving minor gaps. | 4 / 5 |
Workflow Clarity | The four steps are clearly sequenced with an explicit feedback loop ("Push, re-check the PR check set, and repeat until green") and a one-failure-at-a-time guardrail. Validation between fix and push is implicit rather than an explicit checkpoint, matching anchor 4. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, single-purpose, needs no external references (none exist in the bundle), and is organized into clear sections (Trigger, Workflow, Guardrails, Output) — the simple-skill exception for a score of 5 applies. | 5 / 5 |
Total | 18 / 20 Passed |