skills.rest
timikalo7
timikalo7COMMUNITY
Explore all skills by this author →
GitHub

caveman-mode

Applies a terse, action-first communication and working style to agent responses.

Updated Jun 9, 2026
Search Tags:#workflow#communication style#agent behavior#autonomy#terse#user preference#commit cadence
One-click install
npx skills add https://github.com/timikalo7/Execute --skill caveman-mode-timikalo7
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-mode
Source: https://github.com/timikalo7/Execute/tree/main/.claude/skills/caveman-mode
Command: npx skills add https://github.com/timikalo7/Execute --skill caveman-mode-timikalo7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? This Skill eliminates verbose, filler-heavy AI responses by enforcing the owner's preferred terse working style, so every interaction is dense, blunt, and action-first without repeated reminders. ## Core Features & Use Cases - Terse Communication Rules: Minimal preamble, short blunt sentences, and results-first replies with no narration of planned actions. - Working Cadence Enforcement: Do-don't-ask autonomy for routine work, small commits pushed often, and mechanical fixes for recurring problem classes. - Quality Gate Preservation: Terse style never skips verification — visual-qa and security-gate checks still run before work is marked done. - Use Case: When collaborating with an owner who dislikes reading essays, the agent leads with the result or a screenshot, surfaces blockers plainly, and commits each phase separately instead of dumping one large change. ## Quick Start Ask the agent to work in caveman mode on your next task so it replies tersely, commits small, and pushes often.

Frequently Asked Questions about caveman-mode

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI agent respond more tersely?▼

Load a style skill like caveman-mode that defines explicit communication rules: minimal preamble, short blunt sentences, and results-first replies. The rules persist across tasks so you never repeat the preference.

How to enforce small commits and frequent pushes with an AI agent?▼

Define a working cadence rule requiring each phase to be its own commit with a quality gate before every push. The agent then splits work into small commits automatically instead of batching a day's work into one blob.

Does a terse communication style skip code verification steps?▼

No. The skill explicitly states terse does not mean skipping verification, quality gates, or accessibility. Visual-qa and security-gate checks still run before any work is considered done.

When should an AI agent ask before acting versus act autonomously?▼

Under this autonomy contract, the agent makes the reasonable call on routine work and keeps going, letting the owner redirect if needed. It still surfaces blockers immediately with a blunt heads-up rather than staying silent.

What are the limitations of a terse working style for agents?▼

Terse style still requires a one-line rationale for non-obvious decisions and immediate plain reporting of blockers. It is unsuitable when stakeholders need detailed explanations or audit-ready narratives of each change.

Related Skills

Explore More Personal & Entrepreneur Skills→
AllBeingsFutureAllBeingsFuture
9

update-user-profile

Update user profile entries with key-value pairs for persistent preferences.

Community
Basic
jleechanorgjleechanorg

requesting-code-review

Run static scans, quality gates, and independent subagent reviews before commits.

Official
Intermediate
veegee82veegee82
2

bootstrap-userspace

Detect host persistence surfaces and initialize the LDD trace store at session start.

Community
Advanced
pipecat-aipipecat-ai
15.1k

prose-review

Review added comments, docstrings, and changelog entries for change-narration instead of code documentation.

Official
Intermediate