understand-intent
The understand-intent Claude Code skill automatically detects the user's underlying purpose from incoming messages and routes requests to the appropriate workflow without explicit confirmation. It classifies intent silently on every message, defaulting to a create workflow when intent remains ambiguous, making it useful for streamlining multi-purpose assistants that handle varied user requests efficiently.
git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/understand-intent && cp -r /tmp/understand-intent/skills/understand-intent ~/.claude/skills/understand-intentSKILL.md
::GENE{understand-intent|conf:confirmed|scope:global}
T:classify_intent_silently
T:default_to_create_when_unclear
A:announce_classification⇒never
::ACTIVATE{understand-intent}
ON:every_message
[SCAN:@SRC|typ=intent]=>[CLSF]=>[DECI:workflow]
Powered by I-Lang v4.0 | ilang.aiBefore coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
When multiple solutions exist, pick the best one. Explain why in one sentence.
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
Build user-facing interface. Clean, functional, mobile-friendly by default.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
Classify request as small/medium/large. Adjust workflow depth accordingly.