Content
72%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 concise, actionable, and well-structured for a single-file skill, but its batch labeling workflow lacks an explicit validation step after labels are applied. Adding a verify-labels checkpoint would raise workflow clarity.
Suggestions
Add an explicit validation checkpoint after applying labels (e.g., re-run `gh issue view {number} --json labels` to confirm the expected type/effort/priority/area labels are present before moving on).
Replace the placeholder label string 'type,effort/level,P#,area.domain' with a concrete worked example so the apply step is fully copy-paste ready.
Tighten the 'When uncertain, note it' rule by specifying how ambiguity is surfaced in the summary table (e.g., a dedicated 'Needs review' column) to make the feedback loop explicit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's knowledge, avoiding explanations of what issues or labels are, with only minor elaboration in the output template, matching anchor 4. | 4 / 5 |
Actionability | Provides concrete, executable gh commands and a real example range (60-67), but placeholders like {number} and P# plus a vague 'explore the codebase if needed' step leave minor gaps, fitting anchor 4. | 4 / 5 |
Workflow Clarity | The numbered process is clearly sequenced, but as a batch, state-mutating operation it lacks an explicit validation checkpoint after applying labels, so per the batch-operation guideline workflow clarity is capped at 3. | 3 / 5 |
Progressive Disclosure | No bundle files exist and the single-file skill is under ~90 lines with well-organized sections (Scope, Process, Rules), so per the simple-skill note it qualifies for anchor 5. | 5 / 5 |
Total | 16 / 20 Passed |