SkillsAdd

Install skills for AI.
Extend your AI agent.

A local directory of open agent skills — ranked, searchable, and one command away.

How to install Browse ranked skills

Catalog338,192

Summaries326,311

With docs109,547

Ranked9,908

Feature your product here Home premium unit · reach builders installing agent skills View pricing →

Topics

Agent workflows 143,147 Design & UI 86,994 Testing 28,627 Docs & files 15,572 React 9,905 Databases 8,825 Marketing 8,084 Mobile 7,090

Ranked skills

All Official With docs

#

Skill

Source

8W Activity

Installs

nemo-mbridge-perf-expert-parallel-overlap Official Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_…

mapbox-search-integration Official Complete workflow for implementing Mapbox search in applications - from discovery questions to production-ready integ…

mapbox/mapbox-agent-skills

figma-use-figjam Official This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which h…

figma/mcp-server-guide

nemo-mbridge-perf-moe-long-context Official Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, an…

vss-manage-video-io-storage Official Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). N…

shopify-admin-execution Official Run a validated Admin GraphQL operation against a specific store using Shopify CLI. Use this when the user wants an e…

shopify/shopify-ai-toolkit

vss-setup-video-analytics-api Official Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optio…

vss-generate-video-calibration Official Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when…

nemo-mbridge-perf-moe-comm-overlap Official MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backen…

vss-manage-alerts Official Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries…

vss-query-analytics Official Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9…

nemo-mbridge-perf-moe-hardware-configs Official Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then …

nemo-mbridge-perf-hierarchical-context-parallel Official Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anch…

dd-monitors Official Monitor management - list, search, file-based create, and alerting best practices.

datadog-labs/agent-skills

nemo-mbridge-resiliency Official Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption…

cash-flow-snapshot Official Reads AR/AP, historical cash timing, and known fixed costs from QuickBooks, PayPal, Stripe, or Square — or a CSV uplo…

anthropics/knowledge-work-plugins

tools Official Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, creat…

launchdarkly/ai-tooling

next-partial-prefetching-optimizer Official Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache…

vss-setup-behavior-analytics Official Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not fo…

nemo-mbridge-perf-megatron-fsdp Official Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and …

zustand Official Zustand adapter for json-render's StateStore interface. Use when integrating json-render with Zustand for state manag…

vercel-labs/json-render

nemo-rl-docs Official Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, …

nemo-mbridge-perf-moe-dispatcher-selection Official Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization…

configs-create Official Create and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, a…

launchdarkly/ai-tooling

nemo-mbridge-perf-tp-dp-comm-overlap Official Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code …

holoscan-setup Official Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, a…

mcore-linting-and-formatting Official Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and c…

configs-targeting Official Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, at…

launchdarkly/ai-tooling

configs-variations Official Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters…

launchdarkly/ai-tooling

huggingface-trackio Official Track and visualize ML training experiments with Trackio.

huggingface/skills

configs-update Official Update, archive, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties,…

launchdarkly/ai-tooling

holoscan-install-container Official Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda ins…

reviewing-oracle-to-postgres-migration Official Identifies Oracle-to-PostgreSQL migration risks by cross-referencing code against known behavioral differences (empty…

github/awesome-copilot

huggingface-local-models Official Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, q…

huggingface/skills

amazon-ec2-image-builder Official Creates and automates custom image builds with EC2 Image Builder - Linux, Windows, and macOS AMIs, and container imag…

aws/agent-toolkit-for-aws

online-evals Official Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling …

launchdarkly/ai-tooling

projects Official Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, …

launchdarkly/ai-tooling

huggingface-community-evals Official Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.

huggingface/skills

lbo-model Official This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transact…

anthropics/financial-services

migrating-oracle-to-postgres-stored-procedures Official Migrates Oracle PL/SQL stored procedures to PostgreSQL PL/pgSQL.

github/awesome-copilot

fixed-income-portfolio Official Review fixed income portfolios by pricing multiple bonds, retrieving reference data, analyzing cashflows, and running…

anthropics/financial-services

built-in-metrics Official Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provi…

launchdarkly/ai-tooling

using-n8n-skills-official Official Use when working with n8n workflows in any capacity.

creating-oracle-to-postgres-migration-integration-tests Official Creates integration test cases targeting Oracle for .NET data access artifacts.

github/awesome-copilot

holoscan-install-conda Official Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to cont…

custom-metrics Official Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metric…

launchdarkly/ai-tooling

snippets Official Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common ins…

launchdarkly/ai-tooling

migrate Official Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: …

launchdarkly/ai-tooling

ui-toolkit/web Official

anthropics/knowledge-work-plugins

holoscan-install-wheel Official Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda insta…