Content
75%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 strong, executable workflow: concrete gh commands, a logical four-step sequence, and a clear output template with essentially no filler. Its gaps are minor — one invalid CLI flag in the 24h delta step and the absence of error-recovery guidance for failed or empty API responses.
Suggestions
Fix the invalid delta commands: replace "gh issue list --state closed --since 24h" with working syntax, e.g., "gh issue list --repo <owner/repo> --state closed --search 'closed:>=24h' --json number,title,closedAt".
Add brief error-recovery guidance (auth failure, rate limits, empty results) to Step 2 to give the workflow an explicit feedback loop.
Consider moving the output template to an assets/template.md file and referencing it, which would tighten SKILL.md further and support progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is almost entirely lean instruction with concrete commands and no concept explanations Claude already knows; the opening line "This skill performs a 'deep read' of a repository. It avoids superficial listings..." is a minor instance of rationale that could be trimmed, fitting anchor 4 rather than anchor 5's every-token-earns-its-place. | 4 / 5 |
Actionability | Concrete, copy-paste-ready commands with explicit --json field lists (e.g., "gh pr list --repo <owner/repo> --state open --json number,title,body,author,...") cover the workflow. However, "gh issue list --state closed --since 24h" is not valid gh CLI syntax, a minor executability gap that keeps it at anchor 4 rather than anchor 5's fully executable coverage. | 4 / 5 |
Workflow Clarity | A clearly sequenced four-step process (Initialize Mental Model → Retrieve State & Delta → Deep Analysis → Pattern Synthesis) with a mergeability checkpoint ("Verify mergeability with gh pr view <number> --json mergeable,statusCheckRollup"). There are no error-recovery or feedback loops (e.g., what to do on auth failure or empty results), which anchor 5 requires; this lands at anchor 4. | 4 / 5 |
Progressive Disclosure | No bundle files exist, and the ~80-line body is well-organized with clear section headers and a compact inline output template, so nothing needs offloading. It sits just above the under-50-line simple-skill case, with only minor organization gains available (e.g., moving the output template to an asset file), matching anchor 4. | 4 / 5 |
Total | 16 / 20 Passed |