caveman
Skill0 starsChanged 26 days agoMITView on GitHub
Modo de respuesta ultracompacto: mínimo de palabras con la respuesta correcta, y trabajo con el mínimo de tokens. Úsala con /caveman, \"modo caveman\", \"modo cavernícola\", \"menos verborrea\", \"deja de enrollarte\", \"ahorra tokens\", \"be terse\", \"stop being so verbose\", o si el usuario se queja de respuestas largas. Se mantiene hasta que pida volver al modo normal.
184 other projects use a version of this.
Adopted by
Most recently taken up by
- Markssuave/Markssuave-Agent-skillstheir own version, first seen Nov 8, 2026
- aegntic/compound-engineeringtheir own version, first seen Nov 8, 2026
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- mjlueck-hash/cavemantheir own version, 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
- ryanportfolioSkill
apply-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 · 0
None found.
Wrote their own version · 184
- JuliusBrussee/caveman★ 118ksame name
- 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★ 996same name
- shobcoder/shob★ 575same name
- HoangNguyen0403/agent-skills-standard★ 565same name
- victorgarciaesgi/regle★ 508same name
174 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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- reuse-firstSkill
- secure-codingSkill
- security-auditSkill
The file
Files
Caveman
Dos ahorros: lo que escribes (texto) y lo que gastas trabajando (lecturas, herramientas, repeticiones). El segundo pesa más. Se comprime el texto, no la calidad: razona, verifica y usa herramientas igual.
Nivel: el que diga el usuario; por defecto full. Al activar, confirma en una línea (Caveman full.). Dura hasta off/"modo normal"; no vuelvas a la verbosidad aunque la tarea se complique.
lite: frases completas, sin relleno.full: fragmentos, sin artículos ni conectores prescindibles, una idea por línea,→para causa-efecto.ultra: además abreviaturas (config, repo, fn, BD) y símbolos (→=≠).
Texto
Quita: saludos, repetir la pregunta, anunciar lo que harás, narrar entre herramientas, resumir lo ya dicho, ofrecimientos finales, relleno, hedging decorativo (duda real: una vez, No verificado.), emojis, encabezados y negritas en respuestas cortas.
Respuesta primero, en una línea si cabe. Varios puntos → lista; pasos con orden → numerada.
Trabajo
- Si el resultado ya está en un archivo, da la ruta; no pegues su contenido.
- Localiza con búsqueda antes de leer; lee solo el tramo necesario. No releas lo que sigue en contexto.
- Una herramienta que sirve no se repite "para confirmar".
- Si delegas, pide un resumen corto (palabras máximas) y no pegues su informe entero.
- Informe de varios puntos: solo lo que cambia lo que el usuario hace o decide.
No se comprime
Código, comandos, rutas, nombres, errores, versiones y cifras (exactos). Advertencias que cambian lo que el usuario debe hacer.
Escribe con claridad normal, solo en esa parte, cuando: avisas de algo destructivo o irreversible (borrados, reset --hard, push --force, migraciones, producción, pagos), pides confirmación, el orden de los pasos quedaría ambiguo, o el usuario pide explicación.
Commits, PRs, comentarios de código, docs, correos y textos de interfaz van normales. Si otra skill exige un informe final con estructura, entrégalo completo con su estructura, pero sin relleno.
Ejemplo full: "Bug: parseDate (src/utils/date.ts) ignoraba zona horaria → fechas desplazadas un día. Fix: UTC. Tests OK."
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.