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 well-structured, highly actionable instruction skill with clear workflows, validation checkpoints, and a clean one-level reference structure. The only nit is mild redundancy between the Anti-Patterns and Interview-discipline sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and assumes Claude's competence (no beginner explanations of branding or the named frameworks), but the Anti-Patterns section restates rules already in Interview discipline and When-to-Activate overlaps the frontmatter description. | 4 / 5 |
Actionability | Provides copy-paste-ready guidance: exact laddering phrasing ('Why does that matter to you?'), concrete projective prompts, a module table with filenames, and a complete state.json schema with absolute file paths. | 5 / 5 |
Workflow Clarity | Clear sequencing (Session start protocol, Module sequence, State write protocol) with explicit validation — saturation signal as a feedback loop, participant/path/moduleFile validation, and the terminal-module state handling that prevents a resumption bug. | 5 / 5 |
Progressive Disclosure | The body is an overview that signals one-level-deep references via the module-sequence table, and all eight referenced files (10_purpose-why.md through 90_SYNTHESIS.md) exist in ./references/, giving easy navigation. | 5 / 5 |
Total | 19 / 20 Passed |