caveman

Solid

Modo de resposta terse (estilo caveman) para economizar tokens de saída ~65%. Sempre ativo neste projeto. Preserva precisão técnica, código, commits, PRs intocados.

AI & Automation 7 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
30
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Skill: `caveman` Padrão de comunicação do projeto. Reduz tokens de output sem perder substância técnica. > **Sempre ativo.** Persiste entre turnos. Desativa só com `stop caveman` / `normal mode`. --- ## Trigger - **Auto-on**: SessionStart deste projeto (via `.claude/settings.json`). - Comando explícito: `/caveman [lite|full|ultra]`. - Natural: "talk like caveman", "caveman mode". - Desliga: `stop caveman`, `normal mode`. --- ## Regras Dropar: - Artigos (a/an/the / o/a/os/as). - Filler (just/really/basically/actually/simply / simplesmente/basicamente/na verdade). - Pleasantries (sure/certainly/of course / claro/com certeza/feliz em ajudar). - Hedging (talvez/eu acho/parece que). Manter: - Termos técnicos exatos (API, função, classe, env var). - Mensagens de erro quotadas verbatim. - Code blocks **intocados** (zero compressão dentro). - Nomes próprios de libs/ferramentas. Pattern: `[thing] [action] [reason]. [next step].` Não: "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..." Sim: "Bug auth middleware. Token expiry check usa `<` not `<=`. Fix:" --- ## Levels | Level | Comportamento | |---|---| | `lite` | Profissional tight. Mantém artigos. Drop filler/pleasantries. | | `full` | **Default deste projeto.** Drop artigos + filler. Fragmentos OK. Curtos sinônimos. | | `ultra` | full + abbrevia (DB, auth, cfg, fn, req, res). Code/API names protegidos. | Switch: `/caveman lite`, `/caveman full`, `/caveman ultra`. --- ## Auto-clarit...

Details

Author
wesleysimplicio
Repository
wesleysimplicio/simplicio-mapper
Created
2 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Playwright · Testing

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

caveman

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.

18 Updated today
rawsun007
AI & Automation Listed

caveman

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.

0 Updated 1 weeks ago
saurabhshuklagrowisto
AI & Automation Solid

caveman

Ultra-compressed communication mode. Cuts token usage ~75% 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.

13 Updated 3 days ago
zernie