Skill rating

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn

Connect the OpenWork MCP Gateway (https://api.openworklabs.com/mcp/agent) to Claude Code, Codex, Gemini CLI, Cursor, VS Code, Claude Desktop, or ChatGPT so the agent can use the user's OpenWork organi

Set up OpenWork for a team - sign up for OpenWork Cloud, create the organization, invite teammates, share models through the AI Gateway, and share a skill. Use when a team or company wants OpenWork wi

Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task. Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer.

Test is red, typecheck failed, CI job failed, flaky, timed out, was this already broken. Use to classify any failing check before changing code or calling it pre-existing.

Drive a running OpenWork desktop window over CDP from the shell. Evaluate JS, take screenshots, open a new session, send a prompt with a chosen model, wait for the run to finish. Use when checking a U

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 updati

Create an OpenCode plugin for OpenWork. Scaffolds the plugin file with the correct API shape, tool definitions, and hook registration. Use when the user asks to 'create a plugin', 'write a plugin', or

Write or extend an E2E journey spec in evals/specs that proves a PR's change to a human reviewer. Use when a PR changes user-visible behaviour, when a reviewer asks "show me", or when the coverage dec

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 subseque

Run the tests, run one spec, run e2e locally or on Daytona, investigate a skipped spec. Use for executing @openwork/testkit agent-first verification.

Reproduce a known chat state in the running desktop on demand (model provider errors and retries, Code Mode and Den script failures, parallel tool steps, app creation, sequential commands) and check h

Make the desktop's model provider fail on demand (connection refused, DNS not found, socket reset, 429, 5xx, 401, 402, stalled or cut stream) with a local fault server and test providers. Use when rep

Measure whether the chat jumps while a turn runs by sampling the Working line's position over CDP and counting upward moves. Use when changing step rows, live status lines, folding, or anything that c

Local OpenWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests.

Configure and verify the OpenWork Slack assistant for an approved private-alpha organization, using its existing Slack app and individual-account connector. Use when a user wants @openwork in Slack or

Search and use the skills, MCP connections, and connected services available through the user's OpenWork organization.

Warn when user-facing UI changes drift from DESIGN.md. Advisory only; findings never gate Warden clearance.

Daytona seeded cloud demo, demo credentials, Acme Robotics seed. Use when the user asks to spin up, keep running, seed, or prepare an OpenWork Cloud/Den Daytona demo instance.

Review a fork PR, review an external contributor PR, check DCO sign-off, check ee/ CLA, carry a fork commit into a same-repo branch, is this PR safe to merge. Checklist for pull requests from forks be

A user saw internal_error, "Unexpected server error", a 500, or an opaque failure in a shipped OpenWork build. Find the cause from local logs and Sentry, name the regressing PR, file the issue, and re

Screenshots, recording, and presentation artifacts.

Workspace guide to introduce OpenWork and onboard new users.

Flag desktop<->den contract drift introduced by this diff. High findings gate Warden clearance; medium findings are advisory only.

Boot, reopen, update, or reset OpenWork PR previews. Discover script worlds; choose preview-desktop (app only), preview-den (Den only), preview-full (Den plus desktop), or preview-app-web locally, on

Flag concrete false-positive proof introduced by changed specs, not test helper or channel preferences. Advisory only; never gates Warden clearance.

Flag only new security issues introduced by this diff. Reported in the Warden security summary.

Flag customer, prospect, partner, or outside-person identities in the diff. Reported in the Warden security summary.

Daytona CLI setup, sandbox debugging, keep a sandbox alive, secrets volume, snapshot refresh. Use when Daytona itself is the problem, not for running tests (see run-tests).

Open a PR, write or rewrite a PR description, "the PR body is too long", or check whether a PR description is readable. Use whenever a PR is created or its body is edited.

Validate the release, check the released binaries, is 0.18.x safe to roll out, prove a published desktop release. Boots the RELEASED mac-arm64 enterprise and cloud binaries through the packaged journe

Cut an OpenWork release, release the app, publish a new version, rerun or recover a release tag, verify release assets. Tag-driven GitHub Actions release that makes zero commits to the repo.

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 fixe

Attach a screenshot/image/video to a PR or issue, or embed an image in a GitHub comment.