Claude Marketplaces

Skills MCP servers Marketplaces Digest Tools

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category

Frontend Development Backend & APIs Testing & QA Security DevOps & CI/CD Git & Pull Requests Documentation Code Review & Quality AI & Agent Building Skill Development

MCP servers by category

Sales & Marketing Web & Browser Automation Databases AI & LLM Tools Cloud & Infrastructure Communication & Messaging Developer Tools Design & Creative Documents & Knowledge Search & Web Crawling

Marketplaces by category

AI Agents & Orchestration LLM Integration Development Tools Frontend & UI Backend & APIs Databases Testing & Code Quality DevOps & Cloud Security & Compliance Git & Version Control

Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

Skills
MCP servers
Marketplaces
Weekly digest
Skill index
MCP index
Marketplace index

Site

About
Tools
Submit
Feedback
Privacy
llms.txt
Plugins reference

Maker

Agent Caffeine
knobs
Wax
Snug
mertduzgun.com

Made by mertduzgun.com

Verify And Stop

juliusbrussee/caveman

Prove existing work meets acceptance conditions without expanding scope.

installs: 101.6K
GitHub stars: 115K
last updated: Oct 26, 2026

View on GitHubSave

Install

$ npx -y skills add juliusbrussee/caveman --skill verify-and-stop --agent claude-code

Installs into .claude/skills of the current project.

Sponsors

CodeRabbitSponsoredTry For Free

Lid closed, agents workingTry it

AppSignalSponsoredStart Free Trial

Keep API keys from agentsGet Snug

Block apps on your iPhoneGet Wax

Devtools for design engineersTry it live

belt - the only tool your agent needsSponsoredone prompt install

Open StepsSponsoredDownload for free

What it does

Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Files

Select a file.

Details

Repository: github.com/juliusbrussee/caveman
First seen: Oct 26, 2026

More from juliusbrussee/caveman

Surgical Patch101.4K
Caveman Evidence Review101.2K
Lean Build101.1K
Caveman Discover101.1K
Caveman Manage100.9K
Migration100.5K
Caveman Setup100.2K
Compress45.8K
Caveman Es513
Caveman Cn437
Caveman587.7K
Caveman Commit412.1K
Caveman Review408.2K
Caveman Compress407.6K
Caveman Help399.3K
Cavecrew355.5K
Caveman Stats354.3K
Caveman Explore104.1K
Caveman Learn103.3K
Safe Refactor103.1K
Caveman Optimize102.4K
Investigate First102.1K

Recommended

1

cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels587.7Kinstalls

2

grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.4Minstalls

3

improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s36.9Kinstalls

4

systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes304.2Kinstalls

5

karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kinstalls

6

find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4Minstalls