Content
76%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 highly actionable, well-organized operational skill: executable commands, complete GraphQL/Python examples, and a valuable gotchas catalog. The main gaps are duplicated content that could be trimmed for token efficiency and the absence of validation/verification checkpoints in the batch project-board workflows, which the rubric caps at 3 for workflow clarity.
Suggestions
Add explicit validation checkpoints to the batch workflows: e.g., for 'move all unassigned items from sprint X to sprint Y', first count and report matching items for user confirmation, then verify each item's Sprint value after mutation before proceeding.
De-duplicate content: state the missing 'project' scope fix and the 'edit overwrites, no append' behavior once (in the gotchas section) and reference them from elsewhere, and drop one of the two equivalent single-item field-update recipes (gh project item-edit vs the GraphQL mutation).
Consider moving the full bulk-pagination Python script and/or the gotcha catalog into a references/ file, keeping SKILL.md as a tighter overview with well-signaled one-level-deep pointers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and operational — commands, GraphQL queries, and gotchas with no padding on concepts Claude already knows — but there is noticeable duplication: the missing 'project' scope appears both in 'Tooling preference' and gotcha 8, 'edit overwrites / no append' appears in both 'Common single-issue actions' and gotcha 9, and the item-edit CLI and GraphQL mutation sections say the same thing twice ('works the same'). This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place level above. | 4 / 5 |
Actionability | Fully executable throughout: concrete gh commands with real flags (--body-file, --iteration-id), complete copy-paste-ready GraphQL queries and mutations, and a complete Python pagination script with subprocess error handling. Placeholders like <ITERATION_ID> are paired with the exact lookup commands that resolve them, covering the common cases. | 5 / 5 |
Workflow Clarity | Sequences are clear and the gotchas section provides real error-recovery guidance, but the batch/destructive workflows lack validation checkpoints — e.g., 'Move all unassigned items from sprint X to sprint Y' is a one-line sketch with no count-confirmation or post-mutation verification loop. Per the rubric, batch operations without validation/verification steps cap workflow clarity at 3, so it cannot score 4 despite the otherwise clear structure. | 3 / 5 |
Progressive Disclosure | No bundle files exist and the skill is a single well-sectioned SKILL.md with clear headers (Where things live, Tooling preference, Common errors, Common workflows) that is easy to navigate. It falls below the top anchor only because some content — the ~70-line bulk-pagination script and the nine-item gotcha catalog — could plausibly live in separate reference files rather than inline; not 3 because what is present is clearly signaled and well-organized, not buried. | 4 / 5 |
Total | 16 / 20 Passed |