Content
71%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 body is well-structured with a clear sequenced workflow, a concrete output template, and excellent progressive disclosure to a single real reference file. Its main weakness is internal redundancy across the principles, focus-areas, and reference-summary sections that inflates the token budget.
Suggestions
Consolidate the overlapping "Key Principles", "Common Areas to Focus On", and "Style Guide Reference" sections to remove repeated rules (overused words, numbers, punctuation).
Add one fully worked example showing a corrected sentence with rule citation to make the output template concrete.
Insert an explicit verification checkpoint (e.g., re-confirm each correction against the cited style-guide rule) before producing final output.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly useful task-specific guidance, but several sections are redundant — "Common Areas to Focus On", "Style Guide Reference", and the Step 2/3 checklists repeat the same rules (overused words, numbers, punctuation) — so it could be tightened. | 3 / 5 |
Actionability | Provides a concrete four-step workflow and a copy-paste output template with exact fields (Location, Issue Type, Original, Correction, Rule Reference), plus inline key rules; minor gap is the absence of a worked filled-in example. | 4 / 5 |
Workflow Clarity | The four phases (Initial Assessment, Detailed Line Edit, Mechanical Review, Output Results) are clearly sequenced, and the compliance checklist serves as a verification artifact; validation checkpoints are otherwise implicit rather than explicit. | 4 / 5 |
Progressive Disclosure | SKILL.md is an overview that summarizes key rules inline and defers the full guide to a single clearly-signaled, one-level-deep reference (./references/EVERY_WRITE_STYLE.md, which exists), with easy navigation. | 5 / 5 |
Total | 16 / 20 Passed |