Extracts underlying user intent through one-question-at-a-time interviews before planning or coding.
npx skills add https://github.com/MSC72m/DevForge --skill interview-me-msc72m
Please help me install this Agent Skill. Skill: interview-me Source: https://github.com/MSC72m/DevForge/tree/main/skills/interview-me Command: npx skills add https://github.com/MSC72m/DevForge --skill interview-me-msc72m
High-intent search queries and answers about installing and using this skill.
State a one-sentence hypothesis with a confidence number, then ask one focused question at a time with your best guess attached. Continue until you can predict the user's reactions, then restate the intent and get an explicit yes before planning or coding.
Use it when a request is missing who the user is, why they want it, what success looks like, or the binding constraint. Skip it for unambiguous mechanical tasks like renames, typo fixes, or pure information requests.
Batched questions encourage skim-reading and surface answers, and later questions often depend on earlier answers. One at a time lets the user react to your hypothesis and keeps the framing correct as understanding evolves.
No. It requires a live, responsive user and must not be invoked in non-interactive contexts like CI pipelines, scheduled runs, or autonomous loops. In those cases, flag the underspecified ask as a blocker instead of guessing.
Only an explicit yes to a concrete restatement counts. Responses like "whatever you think is best", "sounds good", or silence are delegation or polite exits, not confirmation, and require follow-up with concrete options or refinement.
It depends on user availability and honest engagement, and polite users may agree with guesses to be agreeable. If several rounds pass without rising confidence, something foundational is missing and the interview should pause to reframe.
CodeCrafterAdi2006Extracts underlying user intent through one-question-at-a-time interviews before planning or coding.
ThedouglerEnforce SPEC-driven development for planning, implementing, testing, and reviewing code changes.
bravrosStress-test plans through round-by-round interviews that lock every open decision branch.
malue-aiGuide users through structured brainstorming to develop ideas into actionable plans.
