MCP servers and skills: search, filter by where they run, and compare.
Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.
Node.jsMIT★ 1Few starsNo key
Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to
OfficialSkillMIT★ 143k in collectionNo key
Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Open-source browser automation for AI agents. MCP server + Chrome extension + YAML workflow engine + knowledge packs. Give your AI agent a browser and domain expertise.
Node.jsApache-2.0★ 5No key
WebView automation for Kotlin Multiplatform. Run page workflows in an embedded WebView on Android, iOS and desktop, from your app, a test, or an LLM agent over MCP or Koog.
SkillMIT★ 105No key
A free, cross-platform UI for local AI agents. Orchestrate Ollama, embedded GGUF models, DuckDB RAG, and MCP tools on mobile, desktop, or headless Docker without YAML configs.
SkillMIT★ 8No key
Agent skill (Claude Code, Codex, Cursor, OpenCode, Hermes Agent and more): turn a process description into a self-contained, clickable HTML workflow diagram plus a PNG for slides.
SkillMIT★ 8No key
The official Writ MCP connector — turn your saved browser workflows into tools your AI assistant can call. Zero dependencies, one file.
Node.jsMIT★ 1Few starsNeeds a key
Build 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 c
OfficialSkillApache-2.0★ 44k in collectionNo key
Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower expor
OfficialSkillMIT★ 40k in collectionNo key
一段配音，变成一支逐帧代码渲染的口播动效片 —— Claude Code / Codex Skill（9:16 · 16:9 · 60fps · 封面）
SkillMIT★ 14No key
From AI Assistance to Agentic Workflows: Making MCP Practical in the Browser
SkillMIT★ 189No key
Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.
SkillApache-2.0★ 502No key
⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel, Target Memory & Deterministic Automation.
Node.jsApache-2.0★ 13No key
How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs AG
OfficialSkillMIT★ 143k in collectionNo key
Use when the user wants to performance-test, load-test, or stress-test a public website end-to-end with k6. Produces a hybrid (protocol + browser) test suite, SLO-backed thresholds, a load-generator m
OfficialSkillApache-2.0★ 285 in collectionNo key
Debug and verification workflow for runtime-bundle and module-resolution regressions. Use when diagnosing unexpected module inclusions, bundle size regressions, or CI failures related to NEXT_SKIP_ISO
OfficialSkillMIT★ 143k in collectionNo key
Automate 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, autom
OfficialSkillApache-2.0★ 44k in collectionNo key
Use this skill when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local artifact through Latchshot, including report, QA, archive, and
OfficialSkillMIT★ 40k in collectionNo key
🚀 High-performance AI Agent Control Plane, Task Orchestration & Model Context Protocol (MCP) Platform
PythonApache-2.0★ 180No key
Resumable browser, HTTP API and MCP automation for AI agents. Replay CSV/Excel batches, verify results and hold uncertain writes for review.
Node.jsMIT★ 1Few starsNo key
Who stands behind it
