Loading...
Loading...
Found 39 Skills
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.
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.
Use when a subtask is ready to implement and has a subtask JSON file with acceptance criteria and deliverables.
Execute Python code in isolated rootless containers with MCP server proxying to reduce context bloat from 30K to 200 tokens
Execute Python code in isolated rootless containers with MCP server proxying for token-efficient agent workflows
Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking.
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.
Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs.
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib
EMIT phase. Pre-emit debug, write files, post-emit verify from disk. Any new unknown triggers immediate snake back to planning — restart chain.
Use when building features that execute untrusted user code, AI-generated code, or need isolated code execution environments. Covers the @deno/sandbox SDK.