Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured coaching/facilitation skill with strong progressive disclosure and clear philosophical grounding. Its main weaknesses are the lack of concrete examples (what does a surfaced assumption actually look like?) and the absence of an explicit step-by-step workflow for the core sounding process. The content would benefit from a worked example and tighter sequencing.
Suggestions
Add a concrete worked example showing an idea being sounded — e.g., 'Idea: Self-serve onboarding will reduce support tickets' → surfaced assumptions with categories, importance ratings, and evidence levels.
Convert the 'What This Skill Does' bullet list into an explicit numbered workflow with a validation checkpoint (e.g., 'Confirm with PM which assumptions feel surprising or important before writing artifacts').
Trim the 'Your Stance' section — the representational talkback paragraph could be reduced to 1-2 sentences since the concept is well-explained by the first paragraph alone.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary elaboration, particularly the extended explanation of 'representational talkback' and the philosophical framing in 'Your Stance.' The section on 'What Sound Does NOT Do' also explains something Claude could infer. However, the transitions section and core workflow are tight. | 2 / 3 |
Actionability | The skill provides a clear conceptual framework and lists what to do at each step (state as testable belief, categorize, assess evidence, rate importance), but lacks concrete examples of actual assumption statements, categorization outputs, or sample dialogue. There's no executable template or worked example showing what a surfaced assumption looks like in practice. | 2 / 3 |
Workflow Clarity | The workflow is implied — take an idea, surface assumptions, categorize them, assess evidence, then transition — but it's not presented as a clear sequence with explicit steps. The transitions section is well done, but the core sounding process lacks a numbered or ordered workflow with validation checkpoints (e.g., confirming with the PM before writing artifacts). | 2 / 3 |
Progressive Disclosure | The skill effectively references external files for detailed content: the conversation guide in references/surface-assumptions.md, the assumption artifact schema, the artifacts skill, model.md, and guidelines.md. All references are one level deep and clearly signaled with descriptive context about what each file contains. | 3 / 3 |
Total | 9 / 12 Passed |