entrevistar
Skill1 starsChanged 4 months agoLicence not identifiedView on GitHub
Extrai o que o usuário realmente quer, e não o que ele acha que deveria querer, por meio de uma entrevista de uma pergunta por vez até atingir ~95% de confiança sobre a intenção. Use quando o usuário pedir algo subespecificado ("construa X" sem "para quem" ou "por que agora"), quando ele invocar explicitamente ("me entreviste", "questione meu plano", "temos certeza disso?"), ou quando você perceber que está preenchendo requisitos ambíguos em silêncio antes de existir qualquer plano, spec ou código.
In this repository27 other files it gives its agents.
- blindarSkill
- ci-cdSkill
- construirSkill
- contextoSkill
- depurarSkill
- design-de-apiSkill
- documentarSkill
- especificarSkill
- fontes-oficiaisSkill
- frontendSkill
- git-profissionalSkill
- implementarSkill
- lancarSkill
- memoriaSkill
- migrarSkill
- observabilidadeSkill
- otimizarSkill
- planejarSkill
- prdSkill
- questionarSkill
- recuperarSkill
- refinar-ideiaSkill
- revisar-codigoSkill
- simplificar-codigoSkill
- telemetriaSkill
- testar-navegadorSkill
- teste-primeiroSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

