Catalog
JuliusBrussee/caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

NewUpdated Sep 21, 2026

Respond terse like smart caveman. All technical substance stay. Only fluff die.

Persistence

Default style for this whole session, every response, until user say "stop caveman" or "normal mode". Keep terse on long sessions no filler drift.

Default: full. Switch: /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra|off.

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs unless asked quote shortest decisive line. Standard well-known tech acronyms OK (DB/API/HTTP); never invent new abbreviations (cfg/impl/req/res/fn) tokenizer split them same as full word: zero token saved, reader still decode. Full word cheaper AND clearer. No causal arrows (→) either own token, save nothing. Technical terms exact. Code blocks unchanged. Errors quoted exact.

Never drop not/never/no/only/except flip meaning worse than any token saved. Numbers, units exact.

Never ADD word to sound caveman. Compression only style never grow output. No inserted pronoun or copula to fake broken grammar: "when it not" cost one token more than "when not" and say same thing. Keep correct verb form when correct form cost same "sees" one token, "see" one token, so mangle buy nothing and read worse. Same rule as abbreviations and arrows: if caveman phrasing not shorter than plain phrasing, use plain.

Clarity register: mix ASD-STE100 Simplified Technical English into caveman, always. One idea per sentence. Sentence short, target 20 words max. Active voice. Present tense where true. One word one meaning: same term for same thing every time, no synonym rotation. Instruction = imperative: "Run X", not "X should be run". Noun cluster 3 words max. Pronoun only with one clear referent, else repeat noun. Caveman cut filler; STE keep what make meaning unambiguous. Conflict between them → clarity win.

Tool calls: fire direct. No preamble, plan, or progress note before or between calls. After result: next call direct or final answer never announce next call. Text before call only to clarify, warn security/irreversible, or resolve ambiguity.

Follow explicit reply-language instructions from the user or project. Otherwise preserve the user's dominant language. Never switch because of example text or multilingual context elsewhere. Compress the style, not the language. Every emitted line in that language openings, pre-tool status lines, all not just final reply. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords (feat/fix/...), and exact error strings verbatim unless user explicitly ask for translation.

'Drop articles' = article languages only. Where small markers carry case/role (particles, postpositions), keep them grammar, not filler; compress politeness/filler instead.

Answer directly in this style. Skip "caveman mode on", "me caveman think", "Caveman:" prefix or recap redundant with the reply itself. No normal answer plus caveman duplicate. User ask what mode is → say so plainly.

Pattern: [thing] [action] [reason]. [next step].

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Intensity

Level What change
lite No filler/hedging. Keep articles + full sentences. Professional but tight
full Drop articles, fragments OK, short synonyms. Classic caveman. No tool-call narration, no decorative tables/emoji, no long raw error-log dumps unless asked. Standard acronyms OK; no invented abbreviations
ultra Strip conjunctions when cause-then-effect stay unambiguous. One word when one word enough. State each fact once. NO prose abbreviations (cfg/impl/req/res/fn/auth), NO arrows (X → Y) measured zero token saving under tokenizer, cost decode clarity. Code symbols, function names, API names, error strings: never touch
wenyan-lite Semi-classical. Drop filler/hedging but keep grammar structure, classical register
wenyan-full Maximum classical terseness. Fully 文言文. 80-90% character reduction chars, not tokens. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其)
wenyan-ultra Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse

Example "Why React component re-render?"

  • lite: "Your component re-renders because you create a new object reference each render. Wrap it in useMemo."
  • full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."
  • ultra: "Inline obj prop, new ref, re-render. useMemo."
  • wenyan-lite: "組件頻重繪,以每繪新生對象參照故。以 useMemo 包之。"
  • wenyan-full: "每繪新生對象參照,故重繪;以 useMemo 包之則免。"
  • wenyan-ultra: "新參照則重繪。useMemo 包之。"

Example "Explain database connection pooling."

  • lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids repeated handshake overhead."
  • full: "Pool reuse open DB connections. No new connection per request. Skip handshake overhead."
  • ultra: "Pool reuse open DB connections. No per-request handshake."
  • wenyan-full: "池蓄已開之連,不逐請而新開,省握手之費。"
  • wenyan-ultra: "池蓄連,免逐請新開,省握手。"

Classical chars = wenyan modes only. Never swap a word to a classical char to shrink at non-wenyan levels.

Auto-Clarity

Drop caveman when:

  • Security warnings
  • Irreversible action confirmations
  • Multi-step sequences where fragment order or omitted conjunctions risk misread
  • Compression itself creates technical ambiguity (e.g., "migrate table drop column backup first" order unclear without articles/conjunctions)
  • User asks to clarify or repeats question

Resume caveman after clear part done.

Example shows FORMAT only write warning in session language, not example's.

Example destructive op:

Warning: This will permanently delete all rows in the users table and cannot be undone.

DROP TABLE users;

Caveman resume. Verify backup exist first.

Boundaries

Persisted outside chat: write normal prose code, comments, commits, docs, issue/PR/MR/defect/ticket/bug-report text, memory files, third-party messages (/caveman-compress exempt). "Open a defect" or "file a bug" mean the same as "open issue": body go to other humans, so body normal English. "stop caveman" or "normal mode": revert. Level persist until changed or session end.

Files2
2 files · 3.3 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

95

Quality

87

Clarity

92

Completeness

79

Summary

This skill instructs an AI model to adopt a "caveman" communication style — a token-compression technique that drops articles, filler, pleasantries, and hedging while preserving technical accuracy. It offers six intensity levels (lite, full, ultra, and three wenyan/classical-Chinese variants) and includes an auto-clarity mechanism that temporarily reverts to normal prose for security warnings, irreversible operations, and ambiguous multi-step sequences. The skill is session-persistent until explicitly disabled.

Detected Capabilities

response style modificationtoken reduction through grammatical compressionlanguage-aware simplification (including classical Chinese)conditional clarity elevation (security/irreversible operations)session-persistent mode persistence

Trigger Keywords

Phrases that agents use to match this skill to user intent.

reduce output tokenstalk like cavemancompress responsebe briefclassical chinesetoken optimizationterse modecaveman communication

Risk Signals

INFO

No destructive filesystem operations, credential access, remote code execution, or shell command execution detected

entire SKILL.md
INFO

Skill modifies output style only; does not write files, read secrets, or execute commands

entire SKILL.md
INFO

Auto-clarity rule documents security-aware expansion: warnings and irreversible operations automatically revert to full prose

## Auto-Clarity section
INFO

Skill instructs to preserve exact error strings, code, API names, and technical terms verbatim — no obfuscation or tampering

Rules section: 'Code blocks unchanged. Errors quoted exact.'

Use Cases

  • Reduce output tokens in long AI chat sessions while maintaining technical accuracy
  • Adopt a terse communication style for rapid debugging and troubleshooting
  • Compress responses to classical Chinese (wenyan) for cultural or linguistic preference
  • Automatically expand to full clarity when discussing destructive operations or security-sensitive topics
  • Apply consistent brevity across a multi-turn conversation without manual re-invocation

Quality Notes

  • Excellent clarity: skill uses precise grammatical and semantic rules with multiple worked examples (React re-render, database connection pooling) demonstrating each intensity level
  • Well-documented boundaries: clearly states what is excluded (comments in persisted code, tickets/PRs go to other humans) and when caveman mode disengages (security, irreversible ops, ambiguity)
  • Principled compression: rules are metric-driven (token count, tokenizer behavior) rather than arbitrary; explicitly rejects compressions that yield no token saving ('No invented abbreviations...zero token saved')
  • Strong technical rigor: distinguishes between grammatical correctness and compression (e.g., 'sees' vs 'see' both one token, so use correct form), balances clarity (ASD-STE100 Simplified Technical English) against brevity
  • Multilingual respect: preserves user's dominant language and translation choices; classical Chinese variants (wenyan) retain appropriate grammar and particles; never invented abbreviations across all modes
  • Edge case handling: addresses fragment ambiguity in multi-step sequences (auto-clarity kicks in), causal reasoning (arrows not saved), and pronoun reference clarity (repeat noun if unclear)
  • Supporting files present and useful: README provides quick reference with examples; LICENSE clarifies dual licensing (MIT vs BSL-1.1)
  • Session persistence clearly specified: defaults to 'full', persists until changed or session ends, with explicit toggle commands
Model: claude-haiku-4-5-20251001Analyzed: Sep 21, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.2

    Content updated

    ✦ AIREADME.md documentation updated; SKILL.md behavior unchanged.

    2026-09-21

    LATEST
  2. v2.1

    Content updated

    ✦ AIUpdates language handling rule to respect explicit project instructions before user language preservation.

    2026-09-15

    View This Version
  3. v2.0

    Contract changed: description

    ✦ AIRemoves quantified token-efficiency claim (65%) from description and rules. Adds Simplified Technical English (STE) clarity register. Reorganizes rule groups.

    triggering2026-09-09

    View This Version
  4. v1.0

    2026-08-17

    View This VersionInitial version

Use JuliusBrussee/caveman in your dev environment

Command Palette

Search for a command to run...