New Checked the same way as MCP servers

Agent Skills, and what they let an agent do

Read straight from each publisher's repository. For every skill: what it allows the agent to do, the scripts it ships, and what fixed checks matched. Nothing is run.

All skills230

Clear filters

algorithmic-artAnthropic · 1 scriptCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather th…OfficialRuns commands1 high finding
claude-apiAnthropic · 4 scriptsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the…OfficialRuns commands2 findings
docxAnthropic · 15 scriptsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional docume…OfficialReaches the networkRuns commands
mcp-builderAnthropic · 2 scriptsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/Type…OfficialReaches the networkRuns commands
pdfAnthropic · 8 scriptsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PD…OfficialRuns commands
pptxAnthropic · 15 scriptsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted conte…OfficialReaches the networkRuns commands
skill-creatorAnthropic · 10 scriptsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or opt…OfficialReaches the networkRuns commands
slack-gif-creatorAnthropic · 4 scriptsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."OfficialRuns commands
web-artifacts-builderAnthropic · 2 scriptsSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple sin…OfficialDestructive commandsReaches the network2 high findings
webapp-testingAnthropic · 4 scriptsToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.OfficialReaches the networkRuns commands1 finding
xlsxAnthropic · 12 scriptsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting…OfficialReaches the networkRuns commands
changelog-videoHeyGen · 1 scriptTurn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says…OfficialRuns commands
changelog-videoHeyGen · 1 scriptTurn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says…OfficialRuns commands
code-slice-heroHeyGen · 3 scriptsA tiled headline surface flips cell by cell under a sweeping depth field to reveal the rear headline. HyperFrames block, 1920×1080, 8s, 18 variables.OfficialRuns commands
cuboid-carouselHeyGen · 6 scriptsA chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.OfficialReaches the networkRuns commands
figmaHeyGen · 1 scriptBring Figma into a HyperFrames video - rendered assets, brand tokens, components, storyboard frames as reconstructed motion (frames read as states, not slides), shaders and connector-assisted motion. Use when the person pastes a figma.com link or asks to use a…OfficialRuns commands1 finding
frost-sequence-camera-orbitHeyGen · 61 scriptsAn orbiting camera follows an ice logo as it breaks apart, reforms into two text moments, and fades. HyperFrames block, 1920×1080, 22.5s, 216 variables.OfficialRuns commands
glass-shard-titleHeyGen · 3 scriptsGlass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.OfficialRuns commands1 finding
hyperframesHeyGen · 6 scriptsRead first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and wh…OfficialReaches the networkRuns commands5 findings
media-useHeyGen · 69 scriptsGet or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that look…OfficialReaches the networkRuns commands1 high finding
motion-doctrineHeyGen · 2 scriptsGATEWAY — load FIRST before composing any HyperFrames animation or video. The high-level motion law that makes a multi-scene video feel like ONE continuous camera move instead of a stack of independently-animated slides. Covers the vector law (how you exit det…OfficialReaches the networkRuns commands1 finding
motion-doctrineHeyGen · 2 scriptsGATEWAY — load FIRST before composing any HyperFrames animation or video. The high-level motion law that makes a multi-scene video feel like ONE continuous camera move instead of a stack of independently-animated slides. Covers the vector law (how you exit det…OfficialReaches the networkRuns commands1 finding
orbit-cardHeyGen · 5 scriptsA single feature card orbits a dot sphere on approved Blender camera motion. HyperFrames block, 1920×1080, 10s, 4 variables.OfficialRuns commands
remotion-to-hyperframesHeyGen · 13 scriptsBring existing video code or footage into HyperFrames and verify it frame by frame against the original - Remotion first, also Motion Canvas, Lottie, Three.js, p5.js, canvas or plain HTML/CSS animation, or renders from Manim, After Effects or Blender. Use to p…OfficialDestructive commandsRuns commands1 high finding
agent-browserVercelBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include reques…OfficialRuns commands
agentcoreVercelRun agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use…OfficialRuns commands
coreVercel · 3 scriptsCore agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, han…OfficialRuns commands
derive-clientVercelReverse-engineer a website's internal API by recording browser traffic into a HAR file, then generate a standalone client or CLI that calls the endpoints directly, with no browser needed after the first recording. Use when asked to "derive a client", "build a …OfficialRuns commands
dogfoodVercelSystematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces…OfficialRuns commands
electronVercelAutomate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a nativ…OfficialRuns commands
protected-vercel-deploymentsVercelAccess and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Source…OfficialRuns commands
slackVercelInteract with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what…OfficialRuns commands
webmcp-genVercelBuild and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create webmcp.init.js, define deterministic checks, or compare WebMCP with accessibility-tree automation.OfficialRuns commands
accessAnthropicManage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.OfficialRuns commandsEdits files
accessAnthropicManage iMessage channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the iMessage channel.OfficialRuns commandsEdits files
accessAnthropicManage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Telegram channel.OfficialRuns commandsEdits files
agent-developmentAnthropic · 1 scriptThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, sy…OfficialRuns commands1 high finding
claude-securityAnthropicClaude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you …OfficialRuns commandsEdits files
configureAnthropicSet up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.OfficialRuns commandsEdits files1 finding
configureAnthropicCheck iMessage channel setup and review access policy. Use when the user asks to configure iMessage, asks "how do I set this up" or "who can reach me," or wants to know why texts aren't reaching the assistant.OfficialRuns commands
configureAnthropicSet up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.OfficialRuns commandsEdits files1 finding
example-commandAnthropicAn example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layoutOfficialRuns commands
hook-developmentAnthropic · 6 scriptsThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentio…OfficialDestructive commandsRuns commands5 high findings
math-olympiadAnthropic · 2 scriptsNo description.OfficialRuns commands
plugin-settingsAnthropic · 3 scriptsThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior co…OfficialRuns commands2 high findings
receiptsAnthropic · 1 scriptGenerate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for" check-ins. Mines ~/.claude/projects locall…OfficialRuns commands1 high finding
session-reportAnthropic · 1 scriptGenerate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.OfficialRuns commands1 finding
siegeAnthropic · 1 scriptWork on one hard mathematics problem in rounds: each round a judge writes a few self-contained questions, independent workers answer them, and the judge keeps a ledger of what is proved, refuted and open, until the judge concludes or the rounds run out, and th…OfficialRuns commandsEdits files

Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.