Content
78%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, executable skill body with strong domain-specific gotchas and real command examples. Its weaknesses are modest redundancy and a monolithic structure that would benefit from splitting large reference blocks into separate files.
Suggestions
Split the bulk GraphQL pagination script and the 9-item gotchas catalog into separate files (e.g., references/bulk-queries.md, references/gotchas.md) referenced one level deep from SKILL.md to improve progressive disclosure.
Collapse the duplicated single-item update methods — keep `gh project item-edit` as the primary path and reference the equivalent GraphQL mutation only where it adds value, noting the equivalence once.
Rewrite the "Common workflows" sketches as numbered steps with explicit validate→fix→retry checkpoints for the batch/destructive cases (bulk sprint moves, body overwrites) to strengthen workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and almost entirely concrete commands/code with little padding and a sound assumption that Claude knows gh/GraphQL basics; minor redundancy (e.g., the GraphQL mutation that "works the same" as `gh project item-edit`) and a few superfluous inline comments keep it just below lean. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready guidance throughout — real `gh` commands with concrete project/field IDs, a complete GraphQL pagination script, and specific single-item update commands covering the common cases. | 5 / 5 |
Workflow Clarity | Multi-step sequences are sketched (e.g., create → addProjectV2ItemById → updateProjectV2ItemFieldValue) with validation present for risky ops (pre-post review, null guards, overwrite warnings), but checkpoints are scattered across a gotchas catalog rather than woven as explicit validate→fix→retry loops inside each workflow. | 4 / 5 |
Progressive Disclosure | Good internal section structure, but the ~308-line doc is monolithic with no bundle files and large inline reference blocks (the bulk GraphQL script, the 9-item gotchas catalog) that would be better split into separate referenced files. | 3 / 5 |
Total | 16 / 20 Passed |