Total 55,942 skills, AI & Machine Learning has 9312 skills
Showing 12 of 9312 skills
Audit AI agent skills for security risks before installation or periodically. Works on Claude Code, OpenClaw, and all platforms. Detect prompt injection, data exfiltration, malicious commands, obfuscated code, privilege abuse, supply chain risks, memory poisoning, trust exploitation, and behavioral manipulation. Use before installing third-party skills from any marketplace.
Reads a user's Link financial data — transactions, balances, and wallet sources — so agents can answer questions about spending and available source capabilities. Use when the user says "check my balance", "how much did I spend", "show my transactions", "what accounts are connected", "summarize my spending", "recent purchases", or asks about their financial activity, account balances, or linked sources.
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
End-to-end orchestration for non-trivial software feature development. Use this skill whenever the user asks to implement a PR-sized feature, break down a plan, have subagents review a plan, run a plan-review-development-acceptance loop, coordinate multiple review perspectives, produce an acceptance report, or generate an HTML PR summary. Prefer this skill for multi-step code changes even if the user only says "build this feature" and the task is not a tiny one-file edit.
For post-market review, focusing on daily review / market research / transaction summary. This Skill is mainly used in scenarios such as answering user questions, writing reports, and creating financial articles. This report generates a large amount of output and is not suitable for simple conversation scenarios. For obtaining various information and data, you can use the wind.financial.data tool with appropriate keywords or keyword combinations. After the market closes, you need to quickly review the entire day's market to understand what happened, which signals are worthy of attention, and how to respond tomorrow.
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.
Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.
Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.
Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.