Skip to content

Explore Cloud Local Providers API keys Developers Docs

Explore

MCP servers and skills: search, filter by where they run, and compare.

Conduit

The open directory of tools for AI agents. Free to browse, honest about what runs where.

Catalog

Explore
Cloud tools
Local tools
Skills
Categories

Developers

List your project
Documentation
Public API
llms.txt

Account

Sign in
Dashboard

Conduit lists open-source projects by their authors. Listing is not an endorsement or a security review.

Privacy Termsv2026.10.14-98

No tools match “”.

↑↓ navigate openesc close

Explore tools · Conduit

Explore Cloud Local Providers API keys Developers Docs

Filters2ShowHide

More filters

More filters

Search the catalog

All26
Local26
Local + Cloud0
Hosted0
Cloud only0

1–26 of 26 tools for “creative-coding”

Skills CC-BY-4.0 AND Apache-2.0 Clear all

Nothing matches every word exactly, so these are the closest matches.

deepstream-sopNVIDIA
Local
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators pe
in the skill textvideo summarization. # DeepStream SOP Inference Microservice Skill This skill guides AI coding assistants in building, extending, and debugging the **NVIDIA DeepStream SOP (Standard Operating Procedure) Inference
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

Local runs on your computer · Local + Cloud also runs on Conduit’s servers · Hosted is run by its author, you connect by URL

tilegym-monkey-patch-kernels-to-transformersNVIDIA

Local

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weig

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

nemotron-voice-agent-builderNVIDIA

Local

Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) cust

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-cutile-pythonNVIDIA

Local

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for compl

in the skill textFor complex or ambiguous tasks, **present approach options to the user before coding**. This prevents wasted effort on the wrong implementation. ### Clarify for These Task Types

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

skill-card-generatorNVIDIA

Local

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 discussing skill capabilities.

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-converting-cutile-to-juliaNVIDIA

Local

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

deepstream-profile-pipelineNVIDIA

Local

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or mea

in the skill textStage 0 — Preset-apply (at pipeline-creation time) Trigger: any time the coding agent is about to generate a new DS pipeline AND the user

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

deepstream-run-mv3dtNVIDIA

Local

Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custo

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-improve-cutile-kernel-perfNVIDIA

Local

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

accelerated-computing-cudfNVIDIA

Local

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-adding-cutile-kernelNVIDIA

Local

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when a

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

nvidia-skill-finderNVIDIA

Local

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manag

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

deepstream-import-vision-modelNVIDIA

Local

Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT e

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-converting-cutile-to-tritonNVIDIA

Local

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idiom

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

deepstream-devNVIDIA

Local

NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracki

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

paidf-curation-and-retrievalNVIDIA

Local

Use when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining nearest-neighbor matching on Curat

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

paidf-orchestration-setupNVIDIA

Local

Audit, prepare, and deploy PAIDF Orchestration on a Kubernetes GPU cluster - single-GPU H100/L40S hosts, managed Kubernetes, kubeadm, and similar. Select for requests to set up, install, deploy, confi

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

ambient-healthcare-agent-with-nemotron-voice-agentNVIDIA

Local

Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

deepstream-generate-pipelineNVIDIA

Local

Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to in

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

physical-ai-defect-image-generationNVIDIA

Local

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles col

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

tilegym-cutile-autotuningNVIDIA

Local

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

physical-ai-image-attribute-augmentationNVIDIA

Local

Run the PAIDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attr

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

physical-ai-video-data-augmentationNVIDIA

Local

Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augme

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

physical-ai-event-video-generationNVIDIA

Local

Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generatio

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

paidf-orchestration-write-dagNVIDIA

Local

Use when a user describes a custom PAIDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

isaac-mission-control-showcaseNVIDIA

Local

Run and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window, driven through the isaac-sim-remote Python server, with Nova Carter SIL. Use for

OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key

Written in

Any26
Node.js (npx)0
Python (uvx / pip)0
Go0
Docker0

Written in

Any26
Node.js (npx)0
Python (uvx / pip)0
Go0
Docker0

API key

Either26
No key needed26
Needs a key0

API key

Either26
No key needed26
Needs a key0

Who stands behind it

Anyone26
Official26
Verified owner0
Community0

Who stands behind it

Anyone26
Official26
Verified owner0
Community0

Category

All categories26
Developer tools25
Databases0
Browser & web0
Search3
Files & documents4
Productivity0
Communication0
Cloud & infrastructure4
Data & analytics10
Design & media13
Memory & knowledge2
Utilities0
Writing1

Category

All categories26
Developer tools25
Databases0
Browser & web0
Search3
Files & documents4
Productivity0
Communication0
Cloud & infrastructure4
Data & analytics10
Design & media13
Memory & knowledge2
Utilities0
Writing1

Newer or easy to miss

Everything26
Created in the last 30 days0
Added to Conduit this week26
Few stars, complete information0

Newer or easy to miss

Everything26
Created in the last 30 days0
Added to Conduit this week26
Few stars, complete information0

What it is

Any26
Skills (SKILL.md)26
Subagents0
Commands0
Rules0
Instructions0

What it is

Any26
Skills (SKILL.md)26
Subagents0
Commands0
Rules0
Instructions0

License type

Any type26
Open source · permissive26
Open source · weak copyleft0
Open source · copyleft0
Source-available0
No licence0
Proprietary0
Hosted service0
Licence not read yet0

License type

Any type26
Open source · permissive26
Open source · weak copyleft0
Open source · copyleft0
Source-available0
No licence0
Proprietary0
Hosted service0
Licence not read yet0

Type

Everything26
MCP servers0
Skills26

Type

Everything26
MCP servers0
Skills26

License

Any license44
0BSD0
AGPL-3.011
Apache-2.0593
Apache-2.0 AND CC-BY-4.019
BSD-2-Clause0
BSD-2-Clause-Patent0
BSD-3-Clause4
BSD-3-Clause-Clear1
BSL-1.00
BlueOak-1.0.00
CC-BY-4.012
CC-BY-4.0 AND Apache-2.026
CC-BY-SA-4.01
CC0-1.016
No license241

License

Any license44
0BSD0
AGPL-3.011
Apache-2.0593
Apache-2.0 AND CC-BY-4.019
BSD-2-Clause0
BSD-2-Clause-Patent0
BSD-3-Clause4
BSD-3-Clause-Clear1
BSL-1.00
BlueOak-1.0.00
CC-BY-4.012
CC-BY-4.0 AND Apache-2.026
CC-BY-SA-4.01
CC0-1.016
No license241