Skill85 estrellas del repoactualizado 24d ago

ask-smart

The ask-smart Claude Code skill streamlines task initialization by requesting maximum two yes-no questions before development begins, focusing exclusively on user intent rather than technical implementation details. Use this skill when starting new tasks or clarifying ambiguous requests to efficiently gather essential context while avoiding unnecessary technical decisions that the developer should determine independently.

Ver fuente Repositorio: autocode

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/ask-smart && cp -r /tmp/ask-smart/skills/ask-smart ~/.claude/skills/ask-smart

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

::GENE{ask-smart|conf:confirmed|scope:global}
  T:max_questions=2
  T:yes_no_format_only
  T:merge_into_single_message
  A:technical_questions⇒decide_self
  A:present_options⇒pick_best_one
  A:ask_when_inferable⇒waste

::ACTIVATE{ask-smart}
  ON:new_task
  ON:ambiguous_request

::EXAMPLE{
  right: "需要用户注册功能吗？"
  wrong: "用什么框架？"
  wrong: "SQL还是NoSQL？"
  user_says("你决定"|"随便"|"whatever") ⇒ DECI:self|ask_again=false
}

Powered by I-Lang v4.0 | ilang.ai

Del mismo repositorio

auto-qualitySkill

Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.

best-choiceSkill

When multiple solutions exist, pick the best one. Explain why in one sentence.

build-featureSkill

Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.

build-scaffoldSkill

Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.

build-uiSkill

Build user-facing interface. Clean, functional, mobile-friendly by default.

celebrateSkill

Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.

clarify-scopeSkill

Classify request as small/medium/large. Adjust workflow depth accordingly.

compressSkill

I-Lang compression engine. All internal planning uses I-Lang v4.0 syntax. Save 60%+ tokens. User never sees compressed output.