Content
92%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 tight, opinionated instruction skill that delivers concrete file pointers, a validation-gated review process, and well-organized sections without padding. The only gap is the absence of inline content before/after examples, which are delegated to the deslop reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and practitioner-voiced throughout; it assumes Claude's competence and never pads with SEO basics, with every section (principles, questions, facts, process) earning its place. | 5 / 5 |
Actionability | Concrete commands ("npm --prefix web run types:check", prettier) and real file pointers (src/shared/billing.ts, opense-fact-sheet.md) anchor the guidance, but no inline before/after content examples are shown since the craft is delegated to the deslop skill. | 4 / 5 |
Workflow Clarity | The Process section sequences spawn-subagents -> return old/new proposals -> verify against file and code -> apply -> sweep -> typecheck/prettier, with explicit validation checkpoints and a feedback loop for subagent-introduced errors. | 5 / 5 |
Progressive Disclosure | Under 50 lines with no bundle files needed and clearly organized sections (Principles, Questions, Facts to verify, Process), meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 19 / 20 Passed |