Content
68%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 highly actionable with executable gh commands and clear organization, but it is weakened by significant command repetition and a workflow that lacks explicit validation checkpoints around batch rerun operations.
Suggestions
Consolidate the repeated 'gh run list' / 'gh run view --log' / '--log-failed' blocks into a single reference plus the table to cut redundancy.
Add an explicit validation step to the Example Workflow (e.g. confirm failure with 'gh run view --log-failed' before rerunning, and verify the rerun with 'gh run watch --exit-status').
Consider moving the 'Useful Commands Reference' and 'Common Flags' tables into a separate reference file to keep SKILL.md a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Prose is lean with no concept over-explanation, but commands repeat heavily across sections (e.g. 'gh run list' appears ~5 times, 'gh run view --log' / '--log-failed' each duplicated) and 'Check Runs for a Specific Branch' reprints the Quick Status block, which could be consolidated. | 3 / 5 |
Actionability | Commands are fully executable and copy-paste ready, covering the common cases (list, watch, view, rerun, cancel, PR checks, JSON/jq scripting) with concrete flag usage, matching the 5 anchor. | 5 / 5 |
Workflow Clarity | The 'Example Workflow' gives a watch -> diagnose -> rerun sequence but has no explicit validation/feedback checkpoint, and 'gh run rerun' is a batch operation; per the rubric, missing validation for batch/destructive operations caps this at 3. | 3 / 5 |
Progressive Disclosure | No bundle files exist, but the body is well organized with clear section headers and two reference tables and has no nested references; minor organization gaps from the inlined, repetitive reference material keep it just below 5. | 4 / 5 |
Total | 15 / 20 Passed |