NeVibeCode · repository · 22 items
caveman: a set by juliusbrussee
The juliusbrussee/caveman repository on GitHub: 22 cards with a description and an install command.
caveman skill Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off.
Claude Code CX Codex Cursor +1
591,500installs
caveman-commit skill Generates terse Conventional Commits messages focused strictly on intent. Ideal for keeping git history clean without boilerplate or AI signatures.
Claude Code CX Codex Cursor +1
414,700installs
caveman-review skill Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews.
Claude Code CX Codex Cursor +1
410,700installs
caveman-compress skill Rewrites CLAUDE.md and todo files into terse caveman-speak so the model reads fewer input tokens. The source gets overwritten; a readable backup stays out of tree.
Claude Code CX Codex Cursor +1
410,300installs
caveman-help skill A quick reference for Caveman modes and commands in Claude Code and other supported hosts. Use it when you need to control response style or find related skills.
Claude Code CX Codex Cursor +1
401,800installs
cavecrew skill cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters.
Claude Code CX Codex Cursor +1
357,900installs
caveman-stats skill Displays recorded output and cache-read tokens for Claude Code sessions or points to host native usage stats. Useful for tracking raw token consumption.
Claude Code CX Codex Cursor +1
356,700installs
caveman-explore skill A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches.
Claude Code CX Codex Cursor +1
106,500installs
caveman-learn skill This skill reads Caveman learn reports, proposes token-cost reductions, and asks for consent before each edit. Use it for heavy CLAUDE.md files or repeated context.
Claude Code CX Codex Cursor +1
105,700installs
safe-refactor skill Restructures code while preserving existing behavior, enforcing verification boundaries before structural edits.
Claude Code CX Codex Cursor +1
105,500installs
caveman-optimize skill This skill turns a Caveman report observation into an operator-selected candidate and a paired baseline evaluation. Approval is required before code changes.
Claude Code CX Codex Cursor +1
104,800installs
investigate-first skill The skill keeps the agent in diagnosis mode: gather evidence, rank hypotheses, name the cause. Only then does it touch code.
Claude Code CX Codex Cursor +1
104,400installs
verify-and-stop skill Proves existing work meets acceptance criteria without expanding scope. Useful for validation tasks and last-mile checks.
Claude Code CX Codex Cursor +1
104,000installs
surgical-patch skill The skill constrains AI coding agents to the narrowest layer responsible for a bug. It prevents unwanted refactoring and demands focused regression checks.
Claude Code CX Codex Cursor +1
103,800installs
caveman-discover skill Finds and labels every LLM workflow in your repository so Caveman Cloud breaks down spend by actual job rather than grouping everything into one bucket.
Claude Code CX Codex Cursor +1
103,500installs
lean-build skill Prevents overbuilding when adding new features or integrations. It sets strict acceptance bounds, cuts speculative abstractions, and stops immediately once proof passes.
Claude Code CX Codex Cursor +1
103,500installs
caveman-evidence-review skill A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes.
Claude Code CX Codex Cursor +1
103,500installs
caveman-manage skill The skill reads an experiment's state and results in Caveman Cloud, weighs the evidence, then reports one recommendation or blocks the action.
Claude Code CX Codex Cursor +1
103,300installs
migration skill Enforces reversible, compatibility-safe transitions for schema, data, and API updates. Useful whenever data loss or rollout downtime is unacceptable.
Claude Code CX Codex Cursor +1
102,900installs
caveman-setup skill Routes LLM API calls through the Caveman Cloud gateway to measure token costs without altering app behavior. Useful for tracking model spend across a repo.
Claude Code CX Codex Cursor +1
102,500installs
ultracave skill Compresses AI agent replies into short fragments while keeping code, commands, paths, and critical limits intact. Useful for terse coding sessions.
Claude Code CX Codex Cursor +1
25,100installs
megacave skill Switches agent responses to Classical Chinese (wenyan) to reduce terminal output. Activated via /megacave or /caveman wenyan.
Claude Code CX Codex Cursor +1
24,400installs