Caveman
- 5 installs
- 33 repo stars
- Updated July 27, 2026
- dirnbauer/webconsulting-skills
Puts the agent in an ultra-terse communication mode that cuts token usage about 75% by dropping filler while keeping full technical accuracy.
About
Switches responses to a compressed caveman style that drops articles, pleasantries and hedging but preserves exact technical terms, code and errors. A developer uses it to save tokens or get brief answers, with full prose restored for warnings and destructive actions.
- Ultra-compressed responses that drop filler while keeping technical accuracy
- Auto-clarity exception restores full prose for warnings and destructive actions
Caveman by the numbers
- 5 all-time installs (skills.sh)
- Ranked #2,303 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/dirnbauer/webconsulting-skills --skill cavemanAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5 |
|---|---|
| repo stars | ★ 33 |
| Last updated | July 27, 2026 |
| Repository | dirnbauer/webconsulting-skills ↗ |
What it does
Puts the agent in an ultra-terse communication mode that cuts token usage about 75% by dropping filler while keeping full technical accuracy.
Files
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 says "stop caveman" or "normal mode".
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. Errors quoted exact.
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 after clear part done.
Example -- destructive op:
Warning: This will permanently delete all rows in the users table and cannot be undone.>
```sql
DROP TABLE users;
```
>
Caveman resume. Verify backup exist first.
---
Credits & Attribution
This skill is based on the excellent work by [Matt Pocock](https://github.com/mattpocock).
Original repository: https://github.com/mattpocock/skills
Copyright (c) Matt Pocock - Agent skills for real engineering workflows (MIT License)
Special thanks to Matt Pocock for their generous open-source contributions, which helped shape this skill collection. Adapted by webconsulting.at for this skill collection
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k