Agent skills, documented and installable — Page 15

Get authoritative, current OpenAI developer docs with citations, plus model-selection and migration guidance.

Map git contributors and files into a security-focused ownership graph with bus factor and sensitivity flags.

Build, verify, and launch WinUI 3 desktop apps in C# with grounded Microsoft guidance.

Get language- and framework-specific security reviews and secure-by-default coding guidance for Python, JavaScript/TypeScript, and Go.

Route SendGrid requests to the right sub-skill for sending transactional email or receiving via Inbound Parse Webhook.

A curated, weekly-updated collection of 11211+ OpenClaw agent skills across 14 categories.

Maintain agent continuity, durable memory, and identity state across sessions through Notion-backed journals and LTM.

Model-led arXiv collection: author queries, judge relevance per result, then merge and dedupe into a final paper set.

This skill should be used when the user asks to "provision GPU instance", "spin up a cloud server", "list compute plans", "browse GPU pricing", "deploy AI machine", "one-click GPU running an LLM", "deploy a private LLM endpoint", "OpenRouter-ready endpoint", "agent deploy GPU", "spin up my own OpenAI-compatible endpoint", "extend compute instance", "resize compute instance", "destroy server instance", "check instance status", "list my instances", "top up compute credits", "check credit balance", "run inference on the grid", "decentralized inference", "OpenAI-compatible API", "confidential / TEE inference", "list grid models", "check grid capacity", "run a node", "provide compute", "become a grid node", "node operator", "join the grid", "stake to run a node", "serve a model on the grid", "earn from compute", "deploy an always-on AI agent", "deploy a hosted OpenClaw agent", "spin up a ClawPod", "agent pod", "hosted agent with its own wallet", "free agent trial", "deploy a processor", "se

Installs the NEXO Desktop runtime with local memory, guard checks, Deep Sleep, and MCP tools.

Turn fuzzy intentions into measurable, verifiable goals before work begins.

Translates a Figma design into code that matches the screenshot, using the project's existing components and tokens.

Build a durable CLI for Codex that runs by name from any working directory.

Pick the right ASP.NET Core app model and follow current Microsoft guidance for building and maintaining web apps.

Generate p5.js algorithmic art from a written philosophy, with seeded randomness and parameter controls.

Generate project-specific design system rules for Figma-to-code workflows.

Draft, test, and iteratively refine agent skills with quantitative evals and baseline comparisons.

Automate George banking (Erste/Sparkasse AT): balances, transactions, and SEPA file upload in JSON.

Multi-EVM agent wallet SDK with onchain identity (ERC-8004), payment rails (x402), cross-chain liquidity (Li.Fi bridging + DEX aggregation + DeFi Composer),...

Draft a design philosophy and render it as a .pdf or .png artwork.

Step-by-step guide for building MCP servers that expose external services as LLM-callable tools.

Read and mutate Linear issues, projects, and comments through a bundled Node CLI.

Review your installed agent skills to see what you actually use, what overlaps, and what may no longer be worth keeping.

Upgrade a raw multi-agent framework into a Claude Code-style system with memory retrieval, role coordination, evidence-based verification, and safety gates.