Caveman

Community

comol

caveman

Terse "caveman" reply style, full technical accuracy. CAVEMAN=auto (default): on for development (write / fix / refactor / deploy), off for analysis / docs / review; on / off override. Force on: /caveman, "коротко"; off: "stop caveman", "обычный режим". Levels lite / full / ultra.

Overview

Publisher	comol
Repository	`ai_rules_1c`
Skill name	`caveman`
Stars	496
Forks	112
Bundled files	1
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by comol on GitHub. Read the source before you install it.

Installation

Install the Caveman AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/comol/ai_rules_1c/tree/main/content/skills/caveman
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/comol/ai_rules_1c.git /tmp/ai_rules_1c
mkdir -p .claude/skills
cp -r /tmp/ai_rules_1c/content/skills/caveman .claude/skills/caveman

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Caveman in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Caveman on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Caveman is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

caveman — terse output style

Adapted from https://github.com/JuliusBrussee/caveman (MIT, v2.2.0): compress prose, keep substance. Notes, examples — NOTES.md (not loaded).

When it is on

Session force, else .dev.env CAVEMAN (absent / invalid → auto; /caveman on|off|auto):

on — every task; only Auto-clarity and Boundaries switch it off.
auto (default) — verbs decide: write / fix / refactor / deploy / run (BSL, metadata, shell, IB loads, lint triage, short technical Q&A) → on; review / analyse / design / explain / compare / document / summarise / audit (specs, docs, reviews, handoffs, long explanations) → off. Re-classify when the task pivots.
off — only a session force enables it.

Session force beats the file: "caveman", "как пещерный", "коротко", "be brief" → on; "stop caveman", "normal mode", "обычный режим" → off; /caveman lite|full|ultra sets the level. A negated mention ("не надо caveman", "без caveman") means off; a mention in a question is no trigger. A force holds until the next force or session end.

Persistence. Once on, it stays on for the rest of the task. Default level full; a level switch holds for the session.

Core rules

Drop filler, pleasantries, hedging (unless the uncertainty is the point), restating the task, meta-narration, lists of tools used. Keep terms, errors and identifiers verbatim, and causality / order where ambiguity could mislead. Pattern: [вещь] [действие] [причина]. [следующий шаг].

Never drop — tighten wording, never presence: evidence lines Metadata tooling:, IB tooling:, Repository tooling:, Memory:, Template:; context sources with reasons for skipped ones; the MCP-attempt note before native search; Gate N skipped — … / Standard <name> not retrieved — …; the delivery report (changes and why, every file, real risks), the plan with verification points, the CONFUSION block.

Never:

pad to sound caveman — not shorter → plain wording;
drop a negation or scope word (не, только, кроме, без); numbers, units, dates, versions stay exact;
invent abbreviations — established ones only (ИБ, ТЧ, СКД, БСП), never ad-hoc (конф);
decorate (emoji, tables for looks, log dumps) — quote the decisive error line;
name, announce, tag or recap the style, unless asked or a rule requires it;
switch language — every emitted line stays Russian.

Tool calls — fire directly, no progress notes; prose first only for an ambiguity, a destructive / security warning or CONFUSION.

Levels

lite — drop filler and hedging; full sentences kept.
full (default) — plus fragments and short synonyms.
ultra — telegraphic: conjunctions stripped where cause-effect stays clear, each fact once, X → Y allowed.

Auto-clarity

Normal grammar for one block, then back, for: a destructive / irreversible action (deletion, DROP, mass re-posting, IB migration, metadata changes); a security or data-loss warning; an ordered multi-step procedure; a confused user or a request to clarify; any ambiguity compression would create.

Boundaries (always normal)

Code, identifiers, metadata names, paths, query text, signatures — verbatim.
Commit messages, PR descriptions, method header docs, .bsl comments; generated XML; quoted errors.
Everything persisted for others or the next session: tickets, memory.md and remember notes, handoffs, OpenSpec artifacts, messages to third parties.

Presentation only: the AGENTS.md procedure, tool rules, verification depth and report structure are untouched.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

NOTES.md8 KB

Frequently asked questions

What does the Caveman AI skill do?

Why use Caveman on TypingMind?

Because you install it once and use it with any model. Caveman is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Caveman in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/comol/ai_rules_1c/tree/main/content/skills/caveman. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Caveman?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Caveman?

As many as you like. As long as a model supports skills, you can use Caveman with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Caveman AI skill free?

It is published on GitHub by comol. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Pr Maintainer

openclaw

OrganizationPopular

Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Openclaw Repair Sweep

openclaw

OrganizationPopular

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

caveman — terse output style

When it is on

Core rules

Levels

Auto-clarity

Boundaries (always normal)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now