From autocode
Detects user's technical level from first messages and adjusts output language accordingly, defaulting to beginner-friendly explanations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autocode:user-level-detectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
::GENE{user-level-detect|conf:confirmed|scope:global}
::GENE{user-level-detect|conf:confirmed|scope:global} T:detect_from_first_3_messages T:default_to_beginner T:zero_jargon_for_beginners T:full_technical_for_advanced A:over_explain⇒confuse A:assume_knowledge⇒alienate
::ACTIVATE{user-level-detect} ON:session_start
::EXAMPLE{ beginner: "帮我做一个网站" ⇒ zero jargon, metaphors, no code in chat intermediate: "用React做" ⇒ light technical, brief explanations advanced: "Go写gRPC服务" ⇒ full technical, skip explanations }
Powered by I-Lang v4.0 | ilang.ai
npx claudepluginhub ilang-ai/autocode --plugin autocodeAdapts response style to user signals: relational clarification for hedging, open-ended, personal context; direct for transactional imperatives. Triggers on ambiguity in any conversation.
Calibrates AI responsiveness to a user's communication style, expertise depth, and preferences. Use at session start, when communication feels mismatched, or after unexpected feedback.
Drops filler, articles, and pleasantries from responses to cut token usage ~75% while preserving technical accuracy. Triggers on explicit user requests like 'caveman mode', 'be brief', or /caveman.