Loading...
Loading...
Found 21 Skills
Personal wiki at ~/.ultrabrain/ that accumulates knowledge across sessions using an LLM-maintained-wiki pattern. Use when the user asks factual, technical, or decision-oriented questions that may have been previously captured (check index.md before answering), or explicitly asks to capture/記下來/save session content, ingest/整合 raw entries into the wiki, lint/檢查 the vault, or bootstrap a new vault. Skip for small talk, current-file questions, or code-execution requests.
Guide for creating and managing E2B sandboxes using ComputeSDK. Use when building applications that need E2B Firecracker microVM sandboxes for secure code execution, AI code runners, or isolated development environments on E2B.
Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors, streaming corruption, safety settings, rate limits.
Agent skill for sandbox - invoke with $agent-sandbox
This skill is designed for any requests related to running/executing/evaluating code (such as run this code, execute script, plot with Python, run code/plot/execute script). Create a code_latest sandbox via AgentBay SDK, call run_code to execute and return results. Supports Python, JavaScript, R, Java.
Add live coding with Monaco Editor in Slidev. Use this skill for interactive code demos, executable code, and real-time editing.
Execute ArkTS-Sta code snippets and files via the Playground HTTP API. Use this for testing ArkTS syntax, learning ArkTS features, verifying code logic, or demonstrating code execution results.
Use xAI's Grok model with agentic tool calling for X (Twitter) search, web search, code execution, and real-time data access. Invoke when user needs Twitter/X insights, current events, alternative perspectives, or complex multi-step research.
Use when "codex", "use gpt", "gpt-5", "openai codex", "let openai", "full-auto", "autonomous code generation"
Create and deliver terminal-based presentations from markdown files with themes, code execution, mermaid/d2 diagrams, LaTeX/typst formulas, and PDF/HTML export capabilities.
[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.
Design and scaffold the code execution pattern for MCP-based agent systems. Use when building agents that interact with many MCP tools, when intermediate data is too large for model context, when you need loops/conditionals across tool calls, or when PII must stay out of the model context. Based on Anthropic's engineering guidance.