Agent Skills
Instruction packs that give your AI agent know-how — some work anywhere, some only with the tool they came with.
✦ Standalone skills3,266
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons435
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
🔌 Needs setup first142
Each relies on something you set up separately — such as an app, a command-line tool or an account — and its page names what that is.
vercel-labs · Official
1,736 standalone skills
work-iterations
✓★ 24by microsoft
List, create, and assign iterations for Azure DevOps projects and teams.
boards-my-work
✓★ 24by microsoft
This skill retrieves and displays work items assigned to the user in Azure DevOps, organized by type and sorted by recently changed. It prompts for a project name or lists available projects if not provided, then fetches work item details and displays them in a formatted table with clickable links.
liquid-theme-a11y
✓★ 20by shopify
Implement WCAG 2.2 accessibility patterns in Shopify Liquid themes. Covers e-commerce-specific components including product cards, carousels, cart drawers, price display, forms, filters, and modals. Use when building accessible theme components, fixing accessibility issues, or reviewing ARIA patterns in .liquid files.
liquid-theme-standards
✓★ 20by shopify
CSS, JavaScript, and HTML coding standards for Shopify Liquid themes. Covers BEM naming inside stylesheet tags, design tokens, CSS custom properties, Web Components for themes, defensive CSS, and progressive enhancement. Use when writing CSS/JS/HTML in .liquid files or theme asset files.
shopify-liquid-themes
✓★ 20by shopify
Generate Shopify Liquid theme code (sections, blocks, snippets) with correct schema JSON, LiquidDoc headers, translation keys, and CSS/JS patterns. Use when creating or editing .liquid files for Shopify themes, working with schema, doc, stylesheet, javascript tags, or Shopify Liquid objects/filters/tags.
agent-graphs
✓★ 19by launchdarkly
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
migrate
✓★ 19by launchdarkly
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
snippets
✓★ 19by launchdarkly
Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
built-in-metrics
✓★ 19by launchdarkly
Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provider package → custom extractor + trackMetricsOf → raw manual) and picks the lowest-ceremony option that still captures duration, tokens, and success/error.
launchdarkly-guarded-rollout
✓★ 19by launchdarkly
Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety thresholds.
launchdarkly-experiment-setup
✓★ 19by launchdarkly
Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design between iterations, and stop with a winner.
mcp-configure
✓★ 19by launchdarkly
Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.
custom-metrics
✓★ 19by launchdarkly
Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metric kinds via API, emit events via SDK, and query results.
launchdarkly-flag-command
✓★ 19by launchdarkly
Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Use when the user types `/flag`, asks to quickly find a flag by name/key, wants a direct flag detail summary, or needs fast disambiguation between similar flags.
sdk-install
✓★ 19by launchdarkly
Install and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Parent onboarding Step 6 is first flag.
search
✓★ 17by notion
Search the user's Notion workspace using the Notion MCP server. Use for finding pages, databases, and content by keywords or natural-language queries.
tasks-explain-diff
✓★ 17by notion
Generate a rich Notion document explaining code changes. Creates comprehensive documentation with background, intuition, code walkthrough, and verification steps.
create-database-row
✓★ 17by notion
Insert a new row into a specified Notion database using natural-language property values. Handles property name matching and validation.
find
✓★ 17by notion
Quickly find pages or databases in Notion by title keywords. Returns precise matches rather than comprehensive results.
database-query
✓★ 17by notion
Query a Notion database by name or ID and return structured, readable results with optional filters and sorting.
tasks-setup
✓★ 17by notion
Set up a Notion task board for tracking tasks. Guides users through using a template or connecting an existing board.
research-documentation
✓★ 17by notion
Search across your Notion workspace, synthesize findings from multiple pages, and create comprehensive research documentation with proper citations and actionable insights.
meeting-intelligence
✓★ 17by notion
Prepare meeting materials by gathering context from Notion, enriching with research, and creating both an internal pre-read and external agenda saved to Notion.
tasks-build
✓★ 17by notion
Build a task from a Notion page URL. Fetches task details, marks it in progress, implements the work, and updates status in Notion.
spec-to-implementation
✓★ 17by notion
Turn product or tech specs into concrete Notion tasks. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking.
tasks-plan
✓★ 17by notion
Create an implementation plan from a Notion task or specification. Breaks down requirements into actionable steps with estimates and dependencies.
create-task
✓★ 17by notion
Create a new task in the user's Notion tasks database with sensible defaults for due date, status, owner, and project.
create-page
✓★ 17by notion
Create a new Notion page, optionally under a specific parent. Automatically structures content based on page type (meeting notes, project pages, etc.).
knowledge-capture
✓★ 17by notion
Transform conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context with proper organization and linking.
pinecone-query
✓★ 14by pinecone-io
Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the CLI skill instead. Requires PINECONE_API_KEY environment variable and Pinecone MCP server to be configured.