agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible…
dotnet-agent-gotchas
Flags agent mistakes in .NET code -- async misuse, NuGet errors, deprecated APIs, DI.
dotnet-semantic-kernel
Integrates AI/LLM via Semantic Kernel. Plugins, prompt templates, memory stores, agents.
nia
Use Nia MCP server for external documentation, GitHub repos, package source code, and research. Invoke when needing to index/search remote codebases, fetch…
audit-context-drift
Audit CONTEXT.md (the project glossary) for drift against the ADRs in docs/adr, using parallel read-only sub-agents, then apply verified fixes. Use for…
nemotron-lightning35
Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by distillation from Super 3 Base,…
nemotron-super35
Reference desk for NVIDIA Nemotron 3.5 Super (120B-A12B), covering vision-language architecture, MTP, distillation pretraining from Ultra 3 Base, Indic CPT,…
aicr-cross-review
Multi-agent PR review using Claude Code, Codex, and CodeRabbit. Runs parallel reviews with integration impact analysis, then one cross-review round to a 2-of-3…
add-middleware
Add a new NeMo Relay guardrail or intercept type, registration surface, or pipeline stage. Do not use for changing an existing middleware implementation…
contribute-integration
Add or change a third-party framework integration that attaches NeMo Relay to framework tool, LLM, or lifecycle boundaries. Do not use for core runtime or…
nemo-relay-plugin-build
Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic`…
nemoclaw-contributor-onboard-messaging-channel
Guide NemoClaw contributors through adding or reviewing a new messaging channel in the manifest-first messaging architecture. Use when onboarding a channel for…
simready-foundation-conform-fet-003-physx
Use for repairing exact FET_003_PHYSX SimReady conformance for rigid body physics (physx) conformance. Use when a profile, validation report, or user request…
simready-foundation-conform-fet-023-robot-materials
Use for repairing SimReady robot material organization under the top-level Looks scope.
tripy-compilation
Work with the nvtripy compilation pipeline. Use when: using tp.compile, creating InputInfo or DimensionInputInfo, understanding the Trace → MLIR → TensorRT…
skill-card-generator
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or…
feedback
Turns the user's unstructured feedback about how a product or system behaves into verified, agent-ready GitHub issues. Splits a complaint into points, checks…
dispatching-subagents
Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one…
langchain-cn-models
Integrate Chinese LLM providers (DeepSeek, Qwen, GLM, etc.) into LangChain. Use when a developer asks to connect a Chinese model via LangChain or wire up a…
agent-memory
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search…
go-best-practices
Modern Go patterns — error handling, concurrency, structured logging with slog, and Go 1.22+ features agents miss
adversarial-debate
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a…
computer-use
Claude Computer Use tool integration for desktop automation. Enables Claude to interact with computer environments through screenshots, mouse control, keyboard…