learn-preference
The learn-preference skill observes user patterns across interactions to identify coding preferences including style, naming conventions, and structural patterns, then stores these observations in global preferences for automatic application in future sessions. Use this when you want Claude to adapt its code generation approach to match your established patterns without requiring explicit instruction each time.
git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/learn-preference && cp -r /tmp/learn-preference/skills/learn-preference ~/.claude/skills/learn-preferenceSKILL.md
::GENE{learn-preference|conf:confirmed|scope:global}
-e T:observe_dont_ask
T:save_to_global_prefs
T:apply_silently
A:override_explicit_instruction⇒user_wins
::ACTIVATE{learn-preference}
ON:auto
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.