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.
A well-structured methodology skill: concrete numeric guidance, named patterns with choice criteria, and exemplary progressive disclosure across nine real one-level-deep reference files. The main weakness is redundancy — the core framing and several examples are repeated across the intro, keystone, anti-patterns, framework, and closing sections, which inflates token cost without adding guidance.
Suggestions
State the clickbait-quiz / vanity-result / actionable-segmentation distinction once in its keystone section and reference it elsewhere; it is currently fully re-explained in the intro, the keystone section, the anti-patterns section, framework item 2, and the closing.
Delete or drastically compress the closing section — it restates the intro nearly verbatim ('compounding assets', the three patterns, the same design-choice list) and adds no new guidance.
Remove duplicated examples: 'What kind of pizza are you?' appears in both the intro and the keystone section, 'What kind of marketer are you' appears in both the mapping and anti-patterns sections, and '3 emails later' appears in both the mapping discipline and the closing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The keystone clickbait/vanity/actionable framing is restated five times (intro, keystone section, anti-patterns, framework item 2, closing), and specific examples repeat ('What kind of pizza are you?', 'What kind of marketer are you', '3 emails later', 'compounding assets' each appear twice). Individual sections are efficient and assume practitioner-level knowledge, so it is above anchor 2's padded sections, but the cross-section redundancy is more than minor trimming — it fits anchor 3 (mostly efficient but could be tightened) rather than anchor 4. | 3 / 5 |
Actionability | Concrete, specific guidance throughout: exact ranges ('5-12 questions', '4-8 result categories'), four named scoring patterns with explicit choice criteria, three named lead-capture patterns with tradeoffs, a litmus test, and a 12-consideration framework. It is below anchor 5 because no complete worked example (a sample quiz with segments and matched recommendations) appears inline — those live in the reference files. | 4 / 5 |
Workflow Clarity | The design process is clearly sequenced (format decision → question architecture → scoring → categorization → recommendation mapping → lead capture → measurement) and checkpoints exist (the litmus test, segment-balance review, audit cadence, failure-mode diagnostics). Below anchor 5 because there are no explicit validate-then-proceed or error-recovery loops connecting the framework steps. | 4 / 5 |
Progressive Disclosure | Each major section ends with a 'Detail in [references/...]' link to a real file in the bundle, all nine referenced files exist, references are exactly one level deep, and a consolidated Reference files section lists each with a one-line description. Matches the anchor-5 example of a clear overview with well-signaled one-level-deep references. | 5 / 5 |
Total | 16 / 20 Passed |