Agent skills for Claude Code

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting…

Bun as runtime, package manager, bundler, and test runner.

Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding…

Create, modify, inspect, and validate STEP-first parametric CAD parts and assemblies.

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy…

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.

Show real token usage and estimated savings for the current session.

This skill should be used when the user wants to visualize data.

Embedding database for RAG and semantic search.

Operate the Clerk CLI (`clerk` binary) for authentication, user/org/session management, impersonation, local webhook testing, deploy…

Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.

Structured medical case presentation for clinical rounds, conferences, and documentation.

Zero-shot image classification and image-text search.

Build AI agents on Cloudflare Workers using the Agents SDK.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking…

Open Design renewal + seat-expansion business case for a growing customer: realized value, usage proof, and the expansion ROI.

Review, refactor, document, and validate code changes in the current branch

Reviews code changes and suggests improvements

Use this skill to create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers.

Use this skill when the user asks to analyze, tear down, or reverse-engineer a competitor''s paid ads.

Analyze competitors in a given market segment.