Loading...
Loading...
Found 11,924 Skills
Deep dive into Claude Code source code to learn production-grade AI agent architecture patterns
Query AI Engineer Europe 2026 conference data — speakers, talks, schedule, and more. Use when building apps, AI integrations, or tools on top of conference data. Provides REST endpoints (JSON + plain text), an MCP server for agent tool calls, and a CLI. Covers 150+ talks, 150+ speakers, workshops, and the full 3-day schedule.
Use when the user says "silly sausage", "silly-sausage", invokes /silly-sausage, or expresses lighthearted exasperation at a mistake the agent made. Also triggers on the phrase appearing anywhere in user input — no slash required.
Apply the ai-env agentic development environment template to the current repo, with intent-preserving merge for existing files
AI-first knowledge base and startup OS with file-based storage, AI agents, scheduled jobs, and embedded apps
Use this skill when the user or agent wants to take a DBTI personality assessment, do a trading personality quiz, get investment style label, DBTI test, 做题, DBTI测评, 投资人格测试, 交易风格测评, Agent人格标签, agent personality, investment personality test
Runtime patch for Claude Code that unlocks hidden features, removes restrictions, and enables advanced capabilities like multi-agent swarms and computer use.
Review the current conversation and propose structured improvements to skills, documentation, and agent rules.
Distil domain expertise into high-quality agent skills using a principle-driven approach. Use this when you need to create a new skill or improve an existing one, focusing on expertise transfer rather than mechanical instructions. This skill emphasises research, synthesis, critique, and the four core truths of skill design.
Analyze codebase with parallel mapper agents to produce .planning codebase documents
Switch model profile for GSD agents (quality balanced budget)
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.