different-ai

Drive the OpenWork dev renderer with Chrome MCP and verify workspace UI flows. Triggers when user mentions: - "use Chrome MCP with OpenWork" - "hook up to pnpm dev renderer" - "add an OpenWork workspace through the UI"

Create a PR with structured evidence: build verification, UI screenshots uploaded to an ephemeral host, API test results, and a verification comment. No screenshots committed to the repo. Triggers when user mentions: - "create a pr" - "make a pr" - "open a pr" - "push and pr"

Boot up the Den dev stack and the OpenWork desktop app locally, then test common flows like sign-in, dashboard, and telemetry. Triggers when user mentions: - "test den" - "test the app locally" - "boot up den" - "den dev flow" - "test sign in"

Generate or update the internal OpenWork release changelog tracker as plain markdown release sections. Triggers when user mentions: - "generate changelog markdown" - "track this release" - "add a changelog entry"

CUPID app architecture guidance for apps/app/src/app/**

Manage Vercel environment variables for OpenWork projects from the CLI, including linking the local app directory first. Triggers when user mentions: - "add a vercel env var" - "set a vercel env var" - "vercel environment variable"

Fetch and fast-forward the OpenWork enterprise repo and its subrepos to their latest remote heads when it is safe to do so. Triggers when user mentions: - "get latest changes" - "update context repo to latest" - "pull all subrepos"

Recover or verify Chrome MCP before UI-flow testing. Triggers when user mentions: - "chrome mcp is broken" - "chrome mcp bootstrap" - "browser broker missing" - "cannot connect to chrome mcp"

test on Windows, enterprise CA, corporate certificate, GPO cert, TLS fetch failed, Windows sandbox, daytona windows, self-hosted cert. Use when validating OpenWork Windows enterprise TLS/OS-trust fixes in a Daytona Windows sandbox.

get an env var, fetch a secret, missing env var, missing token/API key, load secrets from Infisical, infisical. Fetch secrets from the team's Infisical workspace into the shell environment so subsequent commands can use them.

upload a photo/image/screenshot, host an image, get a public image URL, put images on Vercel Blob, embed images in a PR/comment/doc. Upload local images to Vercel Blob and print public URLs.

Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.

create a fraimz, make fraimz, prove it works, frame proof, PR proof, validate experience, e2e evidence, fraimz.html. The full fraimz loop — frame the claim, drive the real app via CDP, validate/repair, output fraimz.html. Use whenever a task ends with "please create a fraimz" or any change needs end-to-end proof.

do e2e tests, run e2e, validate feature, prove it works, PR proof, frame proof, pnpm evals. Launches OpenWork on Daytona or local Electron and runs the coded eval flows via CDP. Launch + run mechanics; the proof loop itself is the fraimz skill.

write the voice-over, demo script first, voiceover instead of PRD, voiceover-first development, align on the demo, script the demo, ship a feature demo-first. The whole demo-driven journey — approve the narration BEFORE any code, then build on a fresh worktree until the demo holds and open the PR with the proof on it. Use when a feature request arrives, or when the user runs /voiceover.

Manage OpenWork inference model aliases, openwork model overlays, discounts, validation, and automated base model refreshes from models.dev. Use when adding, removing, discounting, auditing, or updating OpenWork models, including requests like "update the models" that should trigger the GitHub update-models workflow and report when its PR merges.

Debug production issues on Vercel using logs, database inspection, and proper deployment waiting

Make features testable by design. Testing pyramid from fast (local) to slow (UI). Expose APIs securely for testing.

Manage DNS records for domains hosted on Vercel using the Vercel CLI

Workspace guide to introduce OpenWork and onboard new users.

Access and update company administrative information stored in Notion

Create and register new OpenCode skills in this repo

Keep the 0 Finance CLI aligned with product capabilities.

Create new OpenCode skills with valid SKILL.md frontmatter.

Create new OpenCode agents with a gpt-5.2-codex default.

Create OpenCode custom commands for repeatable tasks.

Create targeted Cal links for specific people or teams

Use Chrome MCP to verify OpenWork UI flows, especially any feature that touches remote behavior. Triggers when user mentions: - "test with chrome mcp" - "ui verification" - "remote behavior test"

Start the OpenWork dev stack via Docker and verify real user flows via Chrome MCP. Triggers when user mentions: - "dev-up.sh" - "docker dev stack" - "verify in chrome mcp" - "test the real flow"

Run owpenbot/openwrk integration tests with Telegram test tokens. Triggers when user mentions: - "owpenbot tests" - "telegram test tokens" - "openwrk integration test"

Create OpenCode plugins and know where to load them.

Fast preflight for sandbox lifecycle work: sync pins, create a worktree, and run the standard Docker + Chrome MCP verification path. Triggers when user mentions: - "sandbox lifecycle" - "sandbox stuck" - "docker + chrome mcp"

Add a new lead to your Notion CRM with PULL analysis. You provide the context, the skill structures it and creates the entry.

Draft a personalized outreach message for a lead. Fetches lead data from Notion, reads Feedback Insights for what's working, and applies the 5-element framework.

Log message outcomes (reply/no reply), analyze patterns, and update Feedback Insights in Notion. This is the learning engine of the CRM.

Bootstrap your AI-powered CRM. Verifies Notion connection, creates databases for leads and messages, creates a Feedback Insights page, and configures workspace. Run this first.

Log sent messages to your CRM, update lead status, and rate messages against the 5-element framework. Use after sending a message.

Reliable browser automation through explicit Chrome DevTools Protocol endpoints.