oh-my-ai/discovery-interview
Interactive discovery interview → structured product spec. Triggers: spec, PRD, requirements, scoping, brainstorming, new project. Uses AskUserQuestion; WebSearch/WebFetch when user wants research. Outputs user stories, acceptance criteria, constraints.
99
100%
Does it follow best practices?
Impact
96%
2.28xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the key criteria. It provides specific actions, comprehensive natural trigger terms, clear what/when guidance, explicit exclusions to prevent misuse, and a distinct niche. The inclusion of both positive triggers and negative boundaries ('Do NOT use for') is a best practice that makes skill selection highly reliable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'interactive discovery interview', 'structured product specification', 'user stories, acceptance criteria, technical constraints, prioritized requirements'. Also specifies tools used (AskUserQuestion, WebSearch/WebFetch) and output location (docs/specs/ per SPEC_TEMPLATE.md). | 3 / 3 |
Completeness | Clearly answers both 'what' (conduct interactive discovery interview to produce structured product specification with user stories, acceptance criteria, etc.) and 'when' (explicit trigger list). Also includes a 'Do NOT use for' clause which further clarifies boundaries and aids selection. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'write a spec', 'PRD', 'feature spec', 'requirements', 'product requirements', 'scope a project', 'brainstorm a feature', 'flesh out an idea', 'plan a new project'. These are highly natural phrases a user would actually use. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly distinguished from implementation, code review, debugging, and editing skills via explicit exclusions. The focus on interactive discovery interviews for spec creation occupies a clear niche distinct from coding or document editing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently communicates a complex multi-phase interview process. It excels at being concise while remaining highly actionable, with concrete examples of tool usage (AskUserQuestion, WebSearch/WebFetch) and clear validation gates. The progressive disclosure is well-designed with a clean overview table pointing to detailed companion rules, though the absence of bundle files means referenced paths can't be verified.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. It avoids explaining what specs or PRDs are, assumes Claude's competence, and every section serves a clear purpose. The examples are minimal but illustrative. The anti-patterns section is brief and adds value. | 3 / 3 |
Actionability | Provides concrete examples of AskUserQuestion calls with specific option formats, a concrete research loop example with actual WebSearch syntax, specific file output paths (docs/specs/YYYY-MM-DD-<name>.md), and clear minimum thresholds (10-15 questions). The non-negotiables are specific and executable. | 3 / 3 |
Workflow Clarity | The 7-phase process is clearly sequenced with an explicit completeness check gate (Phase 5) that must pass before spec generation. The integrated flow summary provides a clear single-pass overview. Validation is explicit: completeness table must be green, user must confirm summary before spec writing. The anti-patterns section reinforces what not to skip. | 3 / 3 |
Progressive Disclosure | Excellent structure: the SKILL.md serves as a clear overview with a well-organized phase table linking to specific sections in companion rule files. References are one level deep, clearly signaled with both file paths and anchor links. The template reference (SPEC_TEMPLATE.md) is appropriately linked. However, bundle files weren't provided so we can't verify the referenced paths exist, but the structure itself is exemplary. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents