Content
86%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, well-structured instruction skill that assumes Claude's competence and delegates the detailed schema to a single clearly-linked reference. Weak spots are the absence of a worked example and only implicit validation in the workflow.
Suggestions
Add one short worked example of a completed VOICE PROFILE block so the output contract is copy-paste concrete, not just schema-shaped.
Insert an explicit validation checkpoint in the Collection Workflow (e.g., "verify each banned move is observable in the source set before locking the profile").
Consolidate the overlapping 'what the author never does', 'Banned Moves', and 'Hard Bans' treatments to remove redundancy across sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and operational throughout — short bullets, no explaining of concepts Claude already knows, and an explicit "The point is not literary criticism. The point is operational reuse" — with every section earning its tokens. | 5 / 5 |
Actionability | Concrete, actionable guidance is provided via a source-priority ladder, a 5-step collection workflow, a specific extraction checklist, and a schema-backed output contract, but there is no fully worked example of a completed VOICE PROFILE to copy. | 4 / 5 |
Workflow Clarity | The Collection Workflow is a clear numbered sequence feeding into extraction and a schema-defined output contract, with persistence and downstream-use sections; validation is only implicit (the schema's conflict-callout note) rather than an explicit checkpoint. | 4 / 5 |
Progressive Disclosure | Well-organized sections with one clearly signaled, one-level-deep reference (references/voice-profile-schema.md) that holds the detailed schema, keeping the overview in SKILL.md and the reusable structure in the bundle file. | 5 / 5 |
Total | 18 / 20 Passed |