Content
82%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 content is a well-structured, highly actionable triage workflow with concrete commands, a clear output contract, and explicit stop checkpoints. Its main weakness is mild redundancy between the label-policy section and the final workflow step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean and assumes Claude's competence, with concrete commands and a tight template, though the label policy is restated in step 5 and a few passages could be trimmed. | 4 / 5 |
Actionability | It provides copy-paste-ready `gh issue view` and `graphql` commands with exact JSON fields, a search command, a full comment template, and a type-to-route table covering the common cases. | 5 / 5 |
Workflow Clarity | Five numbered steps are clearly sequenced with explicit stop/validation checkpoints (unresolvable input, non-open issue), but there is no validate-fix-retry feedback loop, which the task does not strictly require. | 4 / 5 |
Progressive Disclosure | The skill is a single self-contained file with well-organized sections and no nested references; no content clearly belongs in separate files, though at ~120 lines it is more than a pure overview. | 4 / 5 |
Total | 17 / 20 Passed |