NeVibeCode · 2,385 items
Skills for AI and ML
Skills for AI and ML: what each one does, an install command and example prompts.
cuopt-multi-objective-exploration skill Traces Pareto frontiers for multi-objective optimization using NVIDIA cuOpt. It maps tradeoffs between competing goals when no single weighting exists.
CX Codex +1
1,300installs
jetson-diagnostic skill Collects a read-only Jetson snapshot covering device identity, memory, GPU, thermal state, power, storage, services and processes. Use it to inspect a live host.
CX Codex +1
1,300installs
image skill Creates image prompts for Nano Banana and GPT Image 2.5, with model, quality, size, and aspect-ratio guidance.
CX Codex +1
916installs
openai-docs-skill skill Pulls current OpenAI developer documentation through an MCP server without leaving the terminal. Handy when the agent writes Responses API or SDK code and guessing parameters is not an option.
CX Codex +1
1,200installs
gemini-computer-use skill Runs Gemini 2.5 Computer Use agents with Playwright to drive browser workflows. It captures screenshots, calls UI actions, and prompts for confirmation on risky steps.
CX Codex +1
1,200installs
llm-council skill This skill runs several CLI agents as independent planners, strips their identities, and merges the results into one final plan. Useful when a single model's bias is the problem.
CX Codex +1
1,200installs
higgsfield skill Writes and refines prompts for Higgsfield video and image models, choosing camera setups and motion presets. Useful for directors aiming for character consistency and tight shot control.
CX Codex +1
524installs
huawei-cloud-openviking-embedding-switch skill Points OpenViking at a local llama-server for embeddings, rebuilds the vectordb index when the dimension changes, and restarts the server inside its sandbox.
CX Codex +1
15,900installs
huawei-cloud-openviking-agent-integration skill Binds and unbinds OpenViking long-term memory across 8 coding agents in bwrap sandboxes via native MCP, HTTP, or extension hooks without cloud IAM.
CX Codex +1
15,900installs
mandela skill Audits evaluations, metrics, and benchmarks for circular data leakage. Identifies whether external ground-truth enters independently.
CX Codex +1
1,300installs
generate-image
official skill Generate images from text prompts with OpenAI or Google Gemini. Use it to create project textures, icons, sprites, artwork, or mockups.
93installs
ai-agent-builder skill Designs AI agents with function calling, context memory management, and multi-step reasoning based on n8n workflow patterns.
CX Codex +1
4,800installs
Transcription Automation skill A skill for automatic audio and video transcription: meeting notes, subtitles, podcast show notes. Runs through the media-mcp server.
CX Codex +1
4,800installs
llm-security skill This skill checks LLM applications against OWASP Top 10 for LLM 2025. Use it for chatbots, RAG pipelines, agents, and LLM APIs.
CX Codex +1
1,600installs
notebooklm skill Automates Google NotebookLM via browser control. It lets Claude Code query existing notebooks, add sources, and generate Studio outputs like summaries or audio overviews.
325installs
architecture-design skill Lays out the structure of an ML project built on factories and registries. Useful when adding a new dataset or model that needs a registration decorator.
CX Codex +1
379installs
crypto-report skill Breaks down a crypto project's tokenomics, on-chain metrics and competitors, then writes the findings into a markdown report. Handy when you need the full picture on a token fast.
CX Codex +1
4,700installs
thought-based-reasoning skill A skill for Claude and other AI coders that gives the model a method for working through hard problems in explicit steps. Useful when a plain prompt returns the wrong answer.
CX Codex +1
1,400installs
prompt-engineering skill Guides prompt design for agents, subagents, and LLM integrations. Helpful when building production templates, chain-of-thought prompts, or agent hooks.
CX Codex +1
1,400installs
jetson-headless-mode skill Plans a headless-mode switch on Jetson and applies only safe, reversible changes: drops the graphical target and non-essential daemons.
CX Codex +1
1,200installs
jetson-llm-benchmark skill Benchmarks LLM and VLM serving performance across vLLM, llama.cpp, and Ollama on NVIDIA Jetson, producing structured JSON outputs to compare tuning runs.
CX Codex +1
1,200installs
jetson-llm-serve skill Creates a serving recipe for LLMs or VLMs on Jetson with vLLM or SGLang. Use it when an OpenAI-compatible model server is needed.
CX Codex +1
1,200installs
jetson-inference-mem-tune skill Picks the serving stack and memory flags for an LLM or VLM on NVIDIA Jetson. Use it when a model won't fit or the server keeps hitting OOM.
CX Codex +1
1,200installs
jetson-package skill Selects Jetson-compatible containers, vLLM runtimes, and Jetson AI Lab PyPI indexes for Orin and Thor. Prevents loading generic ARM64 wheels that lack target SM kernels.
CX Codex +1
1,200installs
jetson-memory-audit skill A skill that snapshots Jetson memory and checks how much DRAM actually came back after you stop a workload.
CX Codex +1
1,200installs
nemoclaw-user-guide skill Directs AI assistants to official NemoClaw docs via an MCP server or llms.txt. Useful when installing, running, or troubleshooting OpenClaw, Hermes, and Deep Agents.
CX Codex +1
1,200installs
ideogram4 skill Generates images with legible in-image text and brand color control via Ideogram 4. Useful for video title cards and thumbnails.
CX Codex +1
471installs
medical-imaging-review skill Structures medical imaging AI reviews with verifiable citations and qualitative synthesis. Rejects statistical pooling and meta-analyses.
CX Codex +1
691installs
memory-setup skill Configures Moltbot/Clawdbot memory search across files and past sessions. Use it when an agent loses context between conversations.
CX Codex +1
1,700installs
modelchk skill Assesses task risk and complexity to recommend a sufficient model tier and reasoning effort. Use it before costly, ambiguous, or high-risk work.
CX Codex +1
1,200installs
flash skill A skill that writes and deploys Runpod Serverless with runpod-flash: @Endpoint decorators, local iteration, and shipping endpoints.
CX Codex +1
13,700installs
agent-evaluation skill Framework for testing agents, prompts, and skills using multi-dimensional scoring rubrics and LLM-as-judge prompts.
CX Codex +1
1,300installs
jetson-speculative-decoding skill A skill that adds EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when token generation is the slow part.
CX Codex +1
1,100installs
jetson-download-bsp skill This skill downloads NVIDIA Jetson Linux BSP artifacts into your workspace: the BSP image, sample rootfs, public_sources, x-tools and guides. It runs during Auto Setup.
CX Codex +1
1,100installs
jetson-customize-usb skill Configures USB2 and USB3 SS ports on Jetson Orin and Thor boards via kernel DT overlays. Keeps host xHCI controller probes from failing when toggling ports.
CX Codex +1
1,100installs
axiom-security skill Routes security work for credentials, encryption, passkeys, AI features, certificates, and code signing. Use it when these concerns enter the project.
CX Codex +1
1,200installs
companion-clis skill Use this skill to guide Runpod work with the HuggingFace, GitHub, Docker, and AWS command-line tools. It fits tasks involving models, worker repositories, images, or network volumes.
CX Codex +1
13,200installs
qianwen-audio-tts skill A skill that turns text into speech with Claude TTS models — voiceovers, narrations, audio versions of articles. Runs through an HTTP API and a Python script.
CX Codex +1
5,600installs
qianwen-vision skill Analyzes images and videos using Qwen VL and QVQ models. Extracts text via OCR, reads charts and tables, and handles visual reasoning directly in the agent.
CX Codex +1
5,700installs
qianwen-image-generation skill This skill creates and edits images with Wan and Qwen Image models. Use it for illustrations, posters, reference-based edits, and text rendered in images.
CX Codex +1
5,600installs
1,121–1,160 of 2,385
