Total 54,319 skills, AI & Machine Learning has 9022 skills
Showing 12 of 9022 skills
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope, because the CLI or dashboard wizard performs it. Creating a Slack app for the first time is not: if no Slack app exists yet, use setup-slack-channel for the provider half and return here for the code.
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setup_required, sits at "Waiting for runtime", the Channel is Online but a Slack mention gets no reply, or a Slack app was built with Socket Mode instead of an Intelligence Request URL. Scoped to an OpenTag checkout, or the OpenTag example inside a channels-sdk clone — the phases assume those conventions (app/channel.tsx, app/env.ts, INTELLIGENCE_CHANNEL_NAME, a local agent on port 8123) and do not describe a project scaffolded by copilotkit init, which already ships its own channel host. If the Slack app and Channel already exist and the question is about declaring or customising the Channel in code, use the copilotkit-channels skill instead.
Turn the current conversation into a spec (Problem, Solution, User Stories, Decisions) and publish it as a GitHub issue. Validates a feature before any code is written.
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
Self-diagnosis skill for 5dive agents. Trigger this skill whenever the user says something is broken, not working, or behaving unexpectedly — or when any tool or command exits with an error. Runs a structured health check covering auth state, service health, disk, memory, recent CLI errors, and skill integrity. Surfaces a root-cause summary so the agent can fix the problem itself instead of asking the user. Also exposes a security audit sub-command for SSH keys, open ports, auth failures, and risky file permissions.
Parse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with domain/range, search for ontology terms by keyword, and parse or summarize raw OWL/XML files. Currently supports CMSO and ASMO; the broader OCDO ecosystem (CDCO, PODO, PLDO, LDO) is planned. Use when exploring what classes or properties an ontology provides, finding the right CMSO term for a crystal structure or simulation concept, understanding parent-child class relationships, or onboarding to an unfamiliar materials ontology, even if the user only says "what ontology terms describe my FCC copper simulation" or "show me the CMSO class hierarchy."
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.
Transform a user-supplied photo into an expressive minimal zine poster made only from original source-derived illustration, an artistic proposition, emotional tension, visual metaphor, spacious negative space, art-directed high-chroma color, and unconstrained authorial typography. Let wording, language, amount, placement, type voices, scale, direction, legibility, and image interaction follow expression and aesthetic judgment rather than presets. Preserve source orientation by default with a 3:5 portrait output or 5:3 landscape output. Add source-derived distributed supporting accents and a natural isolated-contour option alongside adaptive paper-edge transitions. Support an exact `单色块模式` trigger for one contiguous saturated color field with all remaining forms in neutral ink. Use for authored abstract or editorial reinterpretations that communicate an emotion or idea without embedding, cropping, tracing, or preserving the original photographic material in the final image.
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-first: a GPU utilization check, then a kernel breakdown, then a single-kernel deep dive only when one kernel dominates.