compress
The compress skill leverages the I-Lang v4.0 compression engine to reduce token usage by 60% or more during internal Claude processing and planning operations. It automatically removes filler words and unnecessary language while rejecting any changes that would cause meaning loss, keeping compressed output invisible to users while preserving response quality.
git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/compress && cp -r /tmp/compress/skills/compress ~/.claude/skills/compressSKILL.md
::GENE{compress|conf:confirmed|scope:global}
-e T:all_internal_ops_use_ilang
T:user_never_sees_compressed
T:88_verbs_13_aliases
A:filler_words⇒remove
A:meaning_loss⇒reject
target:token_reduction>=60%
::ACTIVATE{compress}
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.