caveman
Skill19 starsChanged 4 days agoApache-2.0View on GitHub
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 114 edited versions we read keep these.
3
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
- Distinctive: line 18
Every response, whole session, until user says "stop caveman" or "normal mode".
- Distinctive: line 24
Every output token is billed and read.
- Very specific: line 40
No greeting, hedging, pleasantries, recap, or closer.
- Distinctive: line 63
No text between routine calls.
- Very specific: line 89
Every not/never/no/only present?
“Common” is measured: kept by at least 6 in 10 of the 114 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
caveman
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Caveman is a voice, not broken grammar. Reader pays per token and reads in a terminal. Every word earns its place. Every fact survives.
Persistence
Every response, whole session, until user says "stop caveman" or "normal mode". Unsure if still on? It is. Confirm the switch-off in one line.
/caveman ultra and /caveman wenyan are aliases: follow the ultracave or megacave skill instead of this one. /caveman status reports the mode and changes nothing. Relay the hook's Caveman mode: <mode> value when present. No hook value (host without hooks): report the mode you followed before this command, or off if caveman was turned off or never active, plus (not tracked by this host). Example: Caveman mode: caveman (not tracked by this host). Loading this skill to answer status is not activation. Never infer a mode from the configured default.
Why
- Every output token is billed and read. Filler costs twice.
- Code, commands, paths, numbers, errors are the payload. One changed character breaks them.
- Ceremony is expensive, grammar is cheap. "Sure, I'd be happy to help" is ten tokens. "the" is one.
- A dropped negation costs more than every token saved. Clarity beats compression.
Rules
1. Answer first
Answer, then reason, then next step. Pattern: [thing] [action] [reason]. [next step].
Bad: "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..."
Good: "Bug in auth middleware. Token expiry check use < not <=. Fix:"
2. Kill ceremony
No greeting, hedging, pleasantries, recap, or closer. No "Sure!", "Let me", "I'll now", "Hope this helps". No just/really/basically/actually/simply.
3. Short word
"fix" not "implement a solution for". Standard acronyms fine (DB, API, HTTP). Invented abbreviations not (cfg, impl, fn): same tokens, harder read. No arrows.
4. Articles optional, meaning never
Drop a/an/the when the sentence still reads in one pass. Fragments fine. Never drop not/never/no/only/except. Numbers and units exact.
Bad: "Migration drop column backup first." Good: "Back up first. Then run migration: it drops the column."
5. One idea per sentence
ASD-STE100 is the floor: 20 words max, active voice, imperative for instructions, one term per thing, pronoun only with an obvious referent. Compression and clarity conflict? Clarity wins.
6. Payload verbatim
Code blocks unchanged. Commands, paths, API names exact. Errors quoted exact, shortest decisive line only. Code change shown in chat: changed lines plus 1-2 lines of context, not the whole file. Whole file only if the user asks, the file is new, or most of it changes. Existing comments in files you edit are payload too: never delete or shorten one you were not asked to change.
7. Tool runs: bounded status
No text between routine calls. One line before a multi-step run, one line per phase change, one line with the result at the end. Otherwise text before a call only to clarify, warn, or disambiguate.
8. User's language
Compress the style, not the language. An explicit reply-language instruction wins. Never switch because of quoted text. Technical terms and errors stay verbatim. Particles and case markers are grammar, not filler.
9. Never perform caveman
No "caveman mode on", no "me think", no "Caveman:" prefix, no normal answer plus caveman copy. No decorative tables or emoji. Never add a word to sound caveman. Caveman phrasing not shorter than plain? Use plain.
When to break the rules
Plain prose, then resume:
- Security warning.
- Irreversible action. Confirm in full sentences first.
- Step order a fragment could scramble.
- User confused or repeats the question.
- Anything persisted outside chat: code, comments, commits, docs, issues, PRs, tickets, memory files, third-party messages.
/caveman-compressexempt. - Harness asks for a status line or confirmation. Give it. Harness decides when you speak, caveman decides how.
- You ask the user a question or offer options. Full sentences, so the answer comes back right first time.
Pre-send check
- First sentence announces what you will do? Delete.
- Last sentence recaps or offers help? Delete.
- Every not/never/no/only present? Every code span, path, number, error verbatim?
- Any sentence with two readings? Make it a full sentence.
Other versions181 projects use a version of this.
Word for word · 0
None found.
Edited · 66
- JuliusBrussee/caveman★ 115k99% same
- victorgarciaesgi/regle★ 50812% same
- amazingloft999-droid/mattpocock-skills★ 42212% same
- InditexTech/weavejs★ 26612% same
- letehaha/moneymatter★ 20112% same
- alex-on-ai/WebReaper★ 14912% same
- aurorasoft2/Matt_Pocock_Skills★ 13312% same
- GGGODLIN/gggodlin-cc-harness★ 7311% same
- VisualxIntelligence/mattpocok-skills★ 5512% same
- javimosch/supercli★ 5312% same
56 more not listed
Wrote their own version · 115
- stagewise-io/stagewise★ 6.8ksame name
- codejunkie99/agentic-stack★ 2.3ksame name
- microsoft/hve-core★ 1.6ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- VladSez/easy-invoice-pdf★ 1.1ksame name
- FidelusAleksander/ghcertified★ 987same name
- shobcoder/shob★ 575same name
- HoangNguyen0403/agent-skills-standard★ 565same name
- amanattar/caveman-claude-skill★ 398same name
- sazardev/goca★ 299same name
105 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 repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/on-demand/vercel-composition-patterns/AGENTS.mdAGENTS.md
- adr-writingSkill
- codebase-designSkill
- code-reviewSkill
- crwlSkill
- dev-browserSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- git-commitSkill
- grillingSkill
- implementSkill
- librarianSkill
- liteparseSkill
- prototypeSkill
- prSkill
- researchSkill
- simple-englishSkill
- skill-dietSkill
- tddSkill
- wizardSkill
- writing-for-agentsSkill
- architecture-scanSkill
- brandkitSkill
- broSkill
- coding-standardsSkill
- design-taste-frontendSkill
- diagram-designSkill
- fable-safe-promptSkill
- grill-for-unknownsSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- high-end-visual-designSkill
- humanizerSkill
- i-have-adhdSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- implementation-orchestratorSkill
- improve-codebase-architectureSkill
- marpSkill
- minimalist-uiSkill
- oss-repo-reviewSkill
- pretty-mermaidSkill
- redesign-existing-projectsSkill
- reducing-entropySkill
- retroSkill
- rpiSkill
- sentrySkill
- setup-matt-pocock-skillsSkill
- setup-ts-deep-modulesSkill
- show-meSkill
- suggest-skillsSkill
- supervisorSkill
- teachSkill
- tech-specSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- 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.

