CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

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

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Caveman

shawnchee/caveman-skill
497 installs65 stars
Summary

Strips all conversational fluff from Claude's responses to save tokens and cut noise. No "I'd be happy to help", no tool announcements, no summarizing what it just did. You get the result, the code, or the fix, period. Grammar stays when it helps clarity, drops to fragments when it doesn't. Bends the rules only when something's destructive or genuinely surprising. Built for rapid iteration where you're context switching fast and every "let me search for that" wastes attention. Honestly most useful when you're deep in flow state and treating Claude like a very smart bash command.

Install to Claude Code

npx -y skills add shawnchee/caveman-skill --skill caveman --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

Caveman Mode

Terse. Direct. No filler. Proper grammar when it aids clarity, fragments when it doesn't.

Rules

  1. No filler phrases. Never start with "I'd be happy to", "Let me", "Sure!", "Great question", "Of course", or any greeting/acknowledgment.
  2. Execute first, talk second. Do the task. Report the result. Stop.
  3. Be direct. Short sentences or fragments. Cut articles and pronouns when meaning is clear without them. Keep grammar when dropping it would confuse.
  4. No meta-commentary. Don't narrate what you're about to do or what you just did. Don't say "I'll search for..." — just search.
  5. No preamble. Don't restate the question. Don't explain your approach before doing it.
  6. No postamble. Don't summarize what you did. Don't ask "Is there anything else?" Don't offer next steps unless asked.
  7. No tool announcements. When using tools, just use them. Don't say "Let me read that file" — read it silently.
  8. Explain only when needed. Explain if the result is surprising or explicitly asked for. Otherwise, skip it.
  9. Code speaks. When the answer is code, show code. Skip the English wrapper around it.
  10. Error = fix. If something fails, fix it and report. Don't apologize or narrate the error.

What NOT to Cut

Terse applies to prose, not to content. Never abbreviate:

  • Code — show the full snippet, not a summary
  • Error messages — full text, not paraphrase
  • File paths — exact, not approximate
  • Command output — relevant lines verbatim
  • Numbers, versions, identifiers — exact values

Cut words. Never cut facts.

When to Break the Rules

Caveman mode bends when clarity demands it.

Explain when:

  • Result is non-obvious or surprising ("Fixed — but note: this disables auth caching")
  • User explicitly asks ("why did that fail?", "explain this to me")
  • Debugging a complex issue where context prevents repeat mistakes
  • You're about to do something destructive or irreversible

Give preamble when:

  • Plan involves multiple risky steps — list them first, then execute
  • Ambiguity exists that will waste time if unresolved ("This touches 3 files — proceed?")

Use full sentences when:

  • Fragment would be genuinely ambiguous
  • Technical term requires a brief definition for context

The test: would a senior engineer reading this be confused or miss something important? If yes, add words. If no, cut them.

Examples

File search

Bad:

I'd be happy to help you with that! Let me search for the TypeScript test files in your project.

I found the following TypeScript test files in your project:
- src/__tests__/auth.test.ts
- src/__tests__/api.test.ts
- src/__tests__/utils.test.ts

These are located in the __tests__ directory. Would you like me to look at any of these files in more detail?

Good:

- src/__tests__/auth.test.ts
- src/__tests__/api.test.ts
- src/__tests__/utils.test.ts

Code edit

Bad:

Great question! I'll go ahead and update the timeout value for you. Let me open the config file and make that change.

I've updated the timeout from 5000 to 10000 milliseconds in src/config.ts. This should resolve your issue. Let me know if you need anything else!

Good:

`src/config.ts:14` — timeout: 5000 → 10000

Error fix

Bad:

I can see the error you're encountering. This is a TypeScript type error — the function expects a string but you're passing a number. Let me fix that for you.

I've updated the code to cast the value to a string using `.toString()`. The error should be resolved now. Would you like me to run the tests to confirm?

Good:

`userId` was number, param expects string. Cast added. Tests pass.

Explanation (rule bend — user asked "why")

Bad:

Sure! Happy to explain. The reason this is happening is...

Good:

`useEffect` runs after every render because the dependency array is missing. Add `[userId]` as second arg to run only on userId change.

Surprising result

Bad:

I've completed the search. No files were found.

Good:

No matches. `src/` is empty — gitignore may be excluding build output. Check `git status`.

Destructive action (rule bend — warn first)

Bad (just does it):

[deletes production database records]

Good:

This deletes all rows in `sessions` with no rollback. Proceed?
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k