Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Build heads-up display (HUD) dashboards for AI coding agents — show context usage, active tools, running sub-agents, and task progress in real-time. Use when: monitoring AI agent activity, building developer tools for AI-assisted coding, creating status dashboards for agent workflows.
Add persistent memory to Claude Code that survives across sessions. Use when: maintaining continuity across Claude Code sessions, building agents with persistent project memory, avoiding repeated context setup. Covers claude-mem (AI-compressed session logs) and Claude Subconscious (Letta-based background agent).
Build autonomous financial research agents that analyze stocks, SEC filings, earnings calls, and market data to produce investment reports. Use when: automating investment research, building AI-powered stock analysis, creating financial due diligence agents.
Google AI Studio and Gemini API for multimodal AI. Use when you need multimodal AI (text + image + video + audio), long context up to 1M tokens, code generation with Gemini, grounding with Google Search, or structured output with response schemas.
Assemble and run a Codex-native agent team from one plain-language request. Interviews the user with 2-3 questions, proposes specialized agents synthesized from 7 archetypes + domain detail, then executes with a local lead plus bounded sidecar agents and shared memory in `.kkirikkiri/`. Use when the user explicitly wants delegation, a research/development/analysis/content/product team, or parallel sub-agent work. Korean triggers — 팀 만들어줘, 리서치 팀, 끼리끼리, 팀 구성해줘. English — build a team, research team, agent team, kkirikkiri.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.
Linggen — durable cross-host memory plus browser control over one local MCP server. Memory: three-tier model (core + long-term + episodic staging) of who the user is, not a log of what was done; same `ling-mem` daemon and store in Claude Code, Codex, and OpenClaw. Browser: agent control of the user's own Chrome with per-site permission prompts, and logged-in X session reads.
Offload tasks to local LLMs via LM Studio. Use when a user asks to run local models with LM Studio, save API costs by using local LLMs, create subagents with local models, offload summarization or classification to a local model, or use LM Studio's API for batch processing. Covers local model inference, task delegation, and cost optimization.
Build multi-agent AI systems with Microsoft's Agent Framework (formerly Semantic Kernel Agents). Use when: defining AI agents, orchestrating multi-agent workflows (sequential, parallel, conditional), creating custom agents in Python or .NET, using built-in agents (ChatCompletion, OpenAI Assistant), deploying agent systems, or comparing agent orchestration patterns.