Content
93%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 exemplarily tight instruction-only skill: five terse rules, a concrete process with real commands and decision conditionals, and an exact output template. The only meaningful gap is a missing explicit verification step before emitting findings, which keeps workflow clarity just below the top anchor. Structure and token efficiency are essentially ideal for a skill of this size.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and padding-free ("Review changed prose and code against five rules. The review obeys them too."), explains nothing Claude already knows, and the one unfamiliar term (AMANALAP) is defined in the same line — every token earns its place. | 5 / 5 |
Actionability | Concrete commands are given ("gh pr diff", "gh api repos/OWNER/REPO/contents/PATH?ref=HEAD_SHA") alongside an exact copy-paste output template with path:line format and Fix formats, plus explicit conditionals (why-vs-what comments, untrusted input, required copies) covering the common cases. As an instruction-only skill with fully actionable guidance, the absence of code is not penalized. | 5 / 5 |
Workflow Clarity | The sequence (Target → Spec → Check context → Apply rules → Output) is clearly ordered with a checkpoint in step 3 ("Check context before calling something new") and a strict output template, but there is no final verification pass (e.g., confirming each cited path:line against the diff), leaving a minor validation gap relative to the explicit-validation anchor. | 4 / 5 |
Progressive Disclosure | This is a single-file, ~42-line skill with no external reference needs and no bundle files; its three well-organized sections (The Rules, Process, Output) satisfy the rubric's guideline that sub-50-line simple skills score 5 on well-organized sections alone. | 5 / 5 |
Total | 19 / 20 Passed |