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 marks. It provides specific actions and outputs, comprehensive natural trigger terms, explicit 'when to use' and 'when not to use' guidance, and clear boundaries that distinguish it from related skills. The description is concise yet thorough, using proper third-person voice throughout.
| 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 type. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to product specification/PRD creation via interactive interview. The explicit 'Do NOT use for' clause (implementation, code review, debugging, refactors, editing existing specs) sharply distinguishes it from coding, review, and editing skills, making conflicts unlikely. | 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 well-crafted skill that efficiently communicates a complex multi-phase interview process. It excels at providing concrete examples (AskUserQuestion calls, WebSearch queries) while keeping the overview concise and delegating details to companion files. The validation checkpoint at Phase 5 and the anti-patterns section demonstrate strong workflow design with appropriate guardrails.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what specs, PRDs, or interviews are. Every section serves a purpose—non-negotiables, process table, anti-patterns—with no padding or unnecessary context. The examples are minimal but illustrative. | 3 / 3 |
Actionability | Provides concrete AskUserQuestion call examples with exact syntax, a specific WebSearch example with realistic query, explicit file output path pattern (docs/specs/YYYY-MM-DD-<name>.md), and a clear minimum question count (10-15). The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The 7 phases are clearly sequenced with an explicit ordering requirement. Phase 5 serves as a validation checkpoint that must pass before proceeding. The 'Integrated flow' section provides a concise summary of the full sequence. The completeness check acts as a feedback loop—if anything is missing, ask more before writing the spec. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md provides a clear overview with non-negotiables and process summary, then delegates detailed phase instructions to three companion rule files via a well-organized table with direct anchor links. References are one level deep and clearly signaled. The spec template is also referenced separately. | 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