caveman
Skill0 starsChanged 2 months agoMITView on GitHub
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user explicitly says "caveman mode", "talk like caveman", "use caveman", "less tokens", or "/caveman". Do NOT trigger on generic brevity requests like "be brief" or "keep it short". 中文:超压缩沟通模式, 去掉冠词/客套/冗余词但保留全部技术精度,token 约省 75%;仅当用户明确说 「caveman mode / 原始人模式 / 少用 token / /caveman」时触发,不因「简短点」 这类泛化要求触发。
- Deletes or force-pushes
184 other projects use a version of this, 136 of them edited.
Adopted by
Most recently taken up by
- Markssuave/Markssuave-Agent-skillstheir own version, first seen Nov 8, 2026
- aegntic/compound-engineeringedited, first seen Nov 8, 2026
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- mjlueck-hash/cavemanedited, first seen Nov 8, 2026
- dhruvsaxena1998/skillstheir own version, first seen Nov 8, 2026
- dalonga-kohi/mawltheir own version, first seen Nov 8, 2026
Used with
Projects with it also use addskill, apply-firmware 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.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
ryanportfolioSkillapply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions184 projects use a version of this.
Word for word · 0
None found.
Edited · 136
- stagewise-io/stagewise★ 6.8k16% same
- codejunkie99/agentic-stack★ 2.3k13% same
- VladSez/easy-invoice-pdf★ 1.1k34% same
- FidelusAleksander/ghcertified★ 99631% same
- shobcoder/shob★ 57531% same
- HoangNguyen0403/agent-skills-standard★ 56534% same
- victorgarciaesgi/regle★ 50886% same
- amazingloft999-droid/mattpocock-skills★ 42286% same
- amanattar/caveman-claude-skill★ 39831% same
- sazardev/goca★ 29931% same
126 more not listed
Wrote their own version · 48
- JuliusBrussee/caveman★ 118ksame name
- microsoft/hve-core★ 1.6ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- AnastasiyaW/claude-code-config★ 214same name
- AnastasiyaW/codex-claude-code-config★ 214same name
- Rifteo/skills★ 37same name
- DangQuangSE/team-development-skills★ 19same name
- ivanrvpereira/.agents★ 19same name
- ishandutta2007/Awesome-Claude-Skills★ 16same name
- justinjohnson25600/hermes_skills★ 14same name
38 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.
In this repository45 other files it gives its agents.
- 3d-creationSkill
- 60fps-animationSkill
- aihotSkill
- arxivSkill
- awesome-design-mdSkill
- buildSkill
- canvas-designSkill
- cli-anything-hubSkill
- data-analyticsSkill
- defineSkill
- design-blueprintSkill
- diagnoseSkill
- dsh-plugin-developmentSkill
- feishu-cliSkill
- find-skillsSkill
- flow-canvasSkill
- frontend-designSkill
- fun-code-reverseSkill
- github-cliSkill
- github-trending-cnSkill
- handoffSkill
- latex-compileSkill
- learn-everythingSkill
- metaSkill
- modern-python-toolchainSkill
- multi-search-engineSkill
- myagents-routerSkill
- office-docsSkill
- perplexitySkill
- planSkill
- product-designSkill
- research-paper-writingSkill
- reverse-proxySkill
- reverse-skill-routerSkill
- reviewSkill
- salesSkill
- shipSkill
- skill-auditSkill
- skill-createSkill
- super-researchSkill
- teachSkill
- verifySkill
- videoSkill
- visualizerSkill
- web-search-exaSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 122 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 75
Read: Read files as needed for the task at hand
- Distinctive: line 76
Write: Write files as needed
- Distinctive: line 77
Bash: Run commands as needed
- Distinctive: line 78
Grep: Search files as needed
“Common” is measured: kept by at least 6 in 10 of the 122 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
上游来源:mattpocock/skills(MIT)。 原 frontmatter 的
description_zh/description_en已并入description(双语各一句,避免重复);version/homepage/allowed-tools为上游专有键,DSH 不识别,已移入本注释。
Caveman Mode(超压缩沟通模式)
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure.
Off only when user explicitly says: "stop caveman", "normal mode", "exit caveman", "turn off caveman", "back to normal", or any clear equivalent.
Priority with other skills
Caveman controls response style only — it does not override the instructions or workflow of other active skills. If another skill (e.g. diagnose, tdd) requires structured multi-step output, follow that skill's structure but apply caveman compression to the prose within each section. The content and steps required by other skills are preserved; only the verbosity is reduced.
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"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.
Technical terms stay exact. Code blocks unchanged. Comments inside code blocks also unchanged — do not abbreviate terms inside code or comments.
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:"
Examples
"Why React component re-render?"
Inline obj prop -> new ref -> re-render.
useMemo.
"Explain database connection pooling."
Pool = reuse DB conn. Skip handshake -> fast under load.
Auto-Clarity Exception
Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question.
Resume caveman immediately after the clear part ends — typically after the warning/confirmation block or once the clarification is delivered. Single sentence resume signal: Caveman resume.
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.
Tools
This skill controls communication style only — it does not restrict what tasks can be performed. All tools remain available for normal use:
- Read: Read files as needed for the task at hand
- Write: Write files as needed
- Bash: Run commands as needed
- Grep: Search files as needed
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.

