Content
100%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.
An exemplary instruction-only skill body: fully executable gh-based workflow with tight sequencing, pre-action validation, user confirmation, and per-item failure handling, all at minimal token cost. Organization is clean and self-contained with nothing that belongs in bundle files. No weaknesses identified.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence: no explanation of what gh, GitHub, or pull requests are; every line is instruction (commands, field lists, derivation rules, card templates). Matches the 'every token earns its place' anchor; there is nothing padded to trim. | 5 / 5 |
Actionability | All guidance is copy-paste executable: exact gh commands with explicit --json field lists, jq filters, and literal card/confirmation templates. Deriving states (lifecycle, approval status, checks) from named JSON fields leaves no ambiguity about how to execute, matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | A clear 5-step sequence (resolve → fetch metadata → confirm → approve → report) with explicit validation checkpoints: state derivation (merged/closed/open), checks status, prior-approval detection, and mandatory user confirmation before any approval. Error recovery is specified ("If gh refuses... report that specific failure and continue with the rest"), satisfying the feedback-loop expectation for a batch-capable operation. | 5 / 5 |
Progressive Disclosure | This is a single-file, single-purpose skill with no bundle files (references/, scripts/, assets/ absent) and no external references needed. Content is appropriately contained in well-organized, clearly headed sections with no dangling file references, which merits the top score under the simple-skill provision. | 5 / 5 |
Total | 20 / 20 Passed |