caveman
Skill11 starsChanged 41 days agoMITView on GitHub
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
- Deletes or force-pushes
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 111 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Default: full. Switch: /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra|off.
- Very specific: line 23
Never drop not/never/no/only/except — flip meaning worse than any token saved.
- Distinctive: line 31
No self-reference. Never name or announce the style.
“Common” is measured: kept by at least 6 in 10 of the 111 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
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.
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.
Preserve user's dominant language exactly — reply in the language user writes, never switch regardless 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.
No self-reference. Never name or announce the style. No "caveman mode on", "me caveman think", no third-person caveman tags. Output caveman-only — never normal answer plus "Caveman:" recap. Exception: user explicitly ask what the mode is.
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
userstable 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 text, memory files, third-party messages (/caveman-compress exempt). "stop caveman" or "normal mode": revert. Level persist until changed or session end.
Other versions184 projects use a version of this.
Word for word · 6
- stagewise-io/stagewise★ 6.8k100% same
- fardita/ai-config★ 1100% same
- jjsizemore/jjskills★ 1100% same
- SiamAlSobari/ai-web-tester★ 1100% same
- theDRElabs/opencode-config★ 1100% same
- GktuOktay/claude-agency★ 0100% same
Edited · 143
- codejunkie99/agentic-stack★ 2.3k77% same
- VladSez/easy-invoice-pdf★ 1.1k77% same
- FidelusAleksander/ghcertified★ 98779% same
- shobcoder/shob★ 57579% same
- HoangNguyen0403/agent-skills-standard★ 56577% same
- victorgarciaesgi/regle★ 50858% same
- amazingloft999-droid/mattpocock-skills★ 42258% same
- amanattar/caveman-claude-skill★ 39874% same
- sazardev/goca★ 29979% same
- InditexTech/weavejs★ 26658% same
133 more not listed
Wrote their own version · 35
- JuliusBrussee/caveman★ 115ksame name
- microsoft/hve-core★ 1.6ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- Rifteo/skills★ 37same name
- DangQuangSE/team-development-skills★ 19same name
- ivanrvpereira/.agents★ 19same name
- justinjohnson25600/hermes_skills★ 14same name
- takara-ai/miru-code★ 12same name
- mxrsv/agents-skills★ 9same name
- PanPanFR/oh-my-openkilo★ 9same name
25 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use ultracave, addskill and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JuliusBrusseeSkillultracave
Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".
Also in 6 projects that use this
ryanportfolioSkilladdskill
Create, import, update, or install repository or personal skills; includes runtime ownership, resources, and discovery validation.
Also in 5 projects that use this
ryanportfolioSkillastra-fullreview
Full multi-agent Codex review on gpt-6-astra at medium reasoning. Same verified lifecycle as codex-fullreview. Use for /astra-fullreview or 'full Astra review with sub-reviewers'.
Also in 5 projects that use this
JuliusBrusseeSkillcaveman-explore
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
Also in 11 projects that use this
- +8 more from ryanportfolio
In this repository95 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ask-mattSkill
- brainstormingSkill
- cavecrewSkill
- caveman-commitSkill
- caveman-compressSkill
- caveman-helpSkill
- caveman-reviewSkill
- caveman-statsSkill
- codebase-designSkill
- code-reviewSkill
- design-an-interfaceSkill
- diagnosing-bugsSkill
- dispatching-parallel-agentsSkill
- domain-modelingSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- implement-specSkill
- improve-codebase-architectureSkill
- loop-meSkill
- prototypeSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- researchSkill
- resolving-merge-conflictsSkill
- setup-matt-pocock-skillsSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- tddSkill
- teachSkill
- test-driven-developmentSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- writing-for-agentsSkill
- writing-great-skillsSkill
- writing-plansSkill
- writing-skillsSkill
- brainstormingSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- playwright-cliSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

