local-places

246.8k

openclaw

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

elevenlabs-agents

572

jezweb

Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, agent versioning with A/B testing, and MCP security. React, React Native, or Swift SDKs. Prevents 34 documented errors. Use when: building voice agents, AI phone systems, agent versioning/branching, MCP security, or troubleshooting @11labs deprecated, webhook errors, CSP violations, localhost allowlist, tool parsing errors.

local-places

244

letta-ai

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

gen-env

188

aiskillstore

Creates, updates, or reviews a project's gen-env command for running multiple isolated instances on localhost. Handles instance identity, port allocation, data isolation, browser state separation, and cleanup.

patchright-skill

188

aiskillstore

Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

model-researcher

88

IgorWarzocha

Add new/custom AI models to opencode.json. Use proactively for bleeding-edge releases, non-standard providers, self-hosted models, or custom endpoints. Examples: - user: "Add the new Claude 4.5" → websearch for API specs, add provider entry with baseUrl, verify model ID format - user: "Use my local Ollama instance" → configure custom provider with http://localhost:11434, set model ID format - user: "Configure this OpenAI-compatible proxy" → add provider with custom baseUrl, set apikey env var, verify compatibility - user: "Model X just released, add it" → research provider documentation, find model ID and capabilities, add to config

run-locally

87

databricks

Run and test the agent locally. Use when: (1) User says 'run locally', 'start server', 'test agent', or 'localhost', (2) Need curl commands to test API, (3) Troubleshooting local development issues, (4) Configuring server options like port or hot-reload.

Testing web applications

83

team-mirai-volunteer

Executes browser-based QA tests using agent-browser CLI, covering happy paths and error paths. Use when testing web apps, verifying UI behavior, running E2E tests, or capturing screenshots on localhost.

local-places

45

EthanAlgoX

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

local-places

34

lllooollpp

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

private-connect

34

treadiehq

Secure remote access to OpenClaw gateway + access private services by name. Use `connect expose` and `connect reach` for tunnels; no VPN or SSH. Expose gateway (localhost:18789) for phone/remote access; reach services by name (staging-db, prod-api).

Playwright

33

oxedom

Use when running E2E checks or debugging the web app with Playwright MCP, especially when you need to (1) ensure the demo user exists with superadmin permissions via demo.sql, and (2) login via /demoLogin on localhost.

ArgoCdCommand

20

julianobarbosa

ArgoCD CLI interaction for the cafehyna-hub cluster. USE WHEN managing ArgoCD applications or ApplicationSets, syncing or deploying, checking application status, or managing clusters/repos/projects via the argocd CLI at argocd.cafehyna.com.br or localhost:8080 (via port-forward).

zotero-search

9

urschrei

Search the user's local Zotero library, find related papers via Semantic Scholar, and discover citations/references. **Claude Code only** - this skill requires a local Zotero instance and access to a port on localhost. Use when the user asks to search their Zotero library, find papers on a topic, explore citations of a paper, or find related literature. Supports cross-referencing Semantic Scholar results against the local library.

web-automation

9

mauromedda

Web automation, debugging, and E2E testing with Playwright. Handles interactive (login, forms, reproduce bugs) and passive modes (network/console capture). Triggers on "e2e test", "browser test", "playwright", "screenshot", "debug UI", "debug frontend", "reproduce bug", "network trace", "console output", "verify fix", "test that", "verify change", "test the flow", "http://localhost", "open browser", "click button", "fill form", "submit form", "check page", "web scraping", "automation script", "headless browser", "browser automation", "selenium alternative", "puppeteer alternative", "page object", "web testing", "UI testing", "frontend testing", "visual regression", "capture network", "intercept requests", "mock API responses". PROACTIVE: Invoke for security verification, UI fix verification, testing forms/dropdowns, or multi-step UI flows. ON SESSION RESUME - check for pending UI verifications.

link-langchain

8

BI4O

Quickly integrate a LangGraph backend (localhost:2024) into a new Next.js project and create a minimalist /chat page that supports true streaming AI conversations. Suitable for scenarios that need a fast chat UI setup: 1) integrating a locally deployed LangGraph Studio backend, 2) creating a chat page with real-time streamed responses, 3) connecting directly from the client using the LangGraph SDK, 4) implementing polished UI interactions (avoid double bubbles, smooth loading animations).

devtools

7

sanand0

Use CDP at localhost:9222 to test/debug websites, automate browser tasks

model-researcher

6

justinlevinedotme

Add new/custom AI models to opencode.json. Use proactively for bleeding-edge releases, non-standard providers, self-hosted models, or custom endpoints. Examples: - user: "Add the new Claude 4.5" → websearch for API specs, add provider entry with baseUrl, verify model ID format - user: "Use my local Ollama instance" → configure custom provider with http://localhost:11434, set model ID format - user: "Configure this OpenAI-compatible proxy" → add provider with custom baseUrl, set apikey env var, verify compatibility - user: "Model X just released, add it" → research provider documentation, find model ID and capabilities, add to config

browser-testing

6

ingpoc

Use when testing web applications, debugging browser console errors, automating form interactions, or verifying UI implementations. Load for localhost testing, authenticated app testing (Gmail, Notion), or recording demo GIFs. Requires Chrome extension 1.0.36+, Claude Code 2.0.73+, paid plan.

BrowserBridge

6

lawless-m

Real-time browser debugging and interaction via WebSocket bridge server on localhost:3141

screenshot-local

2

AntJanus

Use when capturing screenshots of local projects, documenting web app UI, taking screenshots of localhost dev servers, or generating images for READMEs and docs. Use when asked to "screenshot my app", "capture the UI", "take a screenshot of localhost", "generate screenshots for docs", "batch screenshot my pages", or "set up shot-scraper".

live-env-playwright

2

itsAR-VR

Use when asked to check the live app, run QA, verify deploy, or log in and test. Hard constraint: live-only (never localhost); always test against NEXT_PUBLIC_APP_URL using Playwright MCP.

local-places

2

insight68

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

mkcert-local-ssl

faahim

Generate locally-trusted SSL certificates for development domains using mkcert. No more browser warnings for localhost.

run-app-locally

jmblab

Run the project locally for development and quick verification. Use when the user asks to start, test, or check the app on localhost.

madsense-local-backend-auth

mikebd

Obtain an auth token and QA company header for local backend GraphQL calls on localhost:8081 using credentials from a local config env file. Use when running authenticated local smoke tests, resolver checks, or manual GraphQL requests in this repo's dev environment.

agent-sync

wutao667

Synchronize state and communicate between Aris (local) and Xiaoyue (remote). Use when collaborating across hosts, sharing context, or reporting progress. Endpoints used: http://localhost:3001/send and the HTTPS-enforced https://chat.wutao6.cfd/send. Includes two-way credential management (Aris_🌬️/aris-secret-key, Xiaoyue_🍵/xiaoyue-secret-key) and enforces that messages end with one of two tags ([This conversation round has ended, do not reply] or [Awaiting your reply]) to prevent infinite loops between AIs.

tldraw-canvas

dakdevs

Interact with open tldraw desktop canvases via a local HTTP API at localhost:7236. Create, read, update, and delete shapes. Take screenshots. Build diagrams, flowcharts, wireframes, and visual layouts programmatically. Use when the user asks to draw, diagram, sketch, wireframe, create a visual, modify a canvas, add shapes, create a flowchart, create an architecture diagram, or work with tldraw. Also triggers on "draw on canvas", "add to canvas", "update the diagram", "show me on the canvas", or any reference to tldraw files (.tldr).

orb-eye

q15432123

Control Android device via Orb Eye accessibility service. Use when user wants to interact with Android phone UI - open apps, click elements, type text, swipe, check notifications, or view screen content. HTTP API at localhost:7333.