Content
85%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-structured, actionable instruction set with strong workflow sequencing and clean progressive disclosure into real reference files. Its only weakness is mild verbosity and some overlap between the conventions and migration-placement sections.
Suggestions
Consolidate the conventions block and the step-4 migration-placement bullets, which repeat overlapping file-purpose guidance, to reduce token cost.
Tighten phrasing in step 2 and step 4 where rules are restated (e.g., 'do not duplicate' guidance appears in multiple steps) into a single authoritative statement.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly directive and non-redundant, but the conventions block and the step-4 migration-placement bullets overlap in content, and a few passages could be tightened; not quite lean enough that every token earns its place. | 2 / 3 |
Actionability | Provides concrete executable guidance — a specific rg command, named files to read, verbatim template usage, and explicit file-placement rules — copy-applicable for an instruction-only skill. | 3 / 3 |
Workflow Clarity | Clear 6-step numbered sequence with explicit validation (step 6 lint/sanity check) and a safety checkpoint in step 4 confirming no repo-specific context was silently dropped, suiting the batch/replacement operations. | 3 / 3 |
Progressive Disclosure | Body is an overview that clearly signals two one-level-deep, real bundle files (references/AGENTS.template.md and references/one-shot-prompt.md), keeping detailed content out of the main skill file. | 3 / 3 |
Total | 11 / 12 Passed |