cosmos3-post-training
Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
nvfleetint
Query NVIDIA Fleet Intelligence with the nvfleetint CLI. Use for ad hoc questions about fleets, nodes, GPUs, node groups, compute zones, alerts, agent health,…
proteinmpnn-nim
Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. Sends user-provided PDB files and design parameters to…
herdr-agent-coordination
Use alongside the managed herdr skill whenever recognized agents communicate through Herdr: peer tasks, reports, questions, corrections, return paths, origin…
reflect
Review a session's transcripts (the main agent and every subagent it spawned) for confusion and waste, such as hallucinated paths and symbols, repeated…
agent-routing
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression).…
mcp-cli
Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations
context-window-management
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context…
design-orchestration
Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies,…
agently-task-dev
Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollectio…
ollygarden-otel-auto-instrumentation
Universal OpenTelemetry auto-instrumentation planning and review guidance. Use when deciding whether agent/library instrumentation is sufficient, when tuning…
dspy-better-together
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
dspy-reasoning-modules
Use for DSPy reasoning modules including RLM, ProgramOfThought, CodeAct, Parallel, sandboxed execution, and long-context workflows.
watch-video
Give Claude eyes and ears on any online video, then analyze it. Downloads a video from a URL (YouTube, Instagram, X, Vimeo, and 1000+ yt-dlp sites), extracts…
review-readiness
Agent-led PR/working-tree review triage. Start from the diff, add RNA graph/business context only where it changes review decisions, and state when raw git…
agent-memory
Full AI agent memory stack — Mem0 unified memory engine with vector search (Qdrant) and knowledge graph (Neo4j), plus SQLite for structured data. Complete…
polyclaw
Trade on Polymarket via split + CLOB execution. Browse markets, track positions with P&L, discover hedges via LLM. Polygon/Web3.
write-plan
MUST use after brainstorming and before executing. Creates detailed implementation plans with checkpoints, verification criteria, and execution options.
opper-node-sdk
Use the Opper Node/TypeScript SDK (opperai) for AI task completion, structured output with JSON Schema or Zod, knowledge base semantic search, streaming…
disk-raccoon
macOS cache cleanup Agent (Little Raccoon). Performs a read-only checkup of development tool caches and application caches on the Mac, judges which ones can be deleted according to the safety levels in the cache map, and executes cleanup after user confirmation. Use when: the user says the disk is full, clean up caches, the Mac is running out of space, some app is taking up dozens of GB, help me slim down, cache…
ip-coach
Personal IP launch coach. Through a 7-stage in-depth interview, guide users to find their own content niche, platform rules, first milestone, and commitment mechanism, produce a "launch profile" that can be continuously fed to an agent, and automatically invoke the /goal skill to break down the first milestone into an executable automated planning system, providing ongoing companionship during execution. When the user says "launch," "do self-media," "do personal...
odai-orchestration
Optional multi-capability orchestration for Odai. Use when the user requests division of labor, independent planning or review, parallel production, or model routing configuration for Codex, Claude Code, or Copilot; the governance skill odai is independently usable.