Different AI

Reproduce chat errors, retries, parallel tool calls, and app creation in a running desktop application. Check how messages and cards appear, including interrupted replies, grouped steps, and error details.

• Check error messages and retry progress
• Inspect text retained after an interrupted reply
• Review grouped parallel tool calls

Guides review of pull requests from external forks, covering code ownership, contribution terms, security-sensitive changes, and tests tied to the reviewed commit. It produces a review record and supports moving changes to a maintainer branch when needed.

• Reviewing external contributions before approval
• Checking code provenance and contribution terms
• Verifying security reviews and tests for a specific commit

Read design review notes attached to a pull request’s screenshots, locate the affected components, and fix the product code using the team’s design rules. Repeat the review and inspect screenshots to verify the result.

• Resolving design notes on a pull request
• Reproducing reported layout problems locally
• Fixing shared components behind repeated UI issues

Prepares an OpenWork Cloud/Den demo on Daytona with Acme Robotics sample data. It checks service health and sign-in, keeps the sandbox active, and returns URLs and credentials ready to share with demo participants.

• Preparing a cloud demo with sample organization data
• Checking demo health endpoints and account sign-in
• Keeping a demo active and organizing access details

Create or revise pull request descriptions using a fixed template and concise language. It organizes the user problem, previous behavior, implementation, release note, and verification details so reviewers can understand the change before reading the diff.

• Write a concise description for a new pull request
• Shorten a lengthy pull request description
• Write a release note describing a visible user change

Review code changes for newly introduced security issues with a plausible attack path. Produce findings for the Warden security summary, including affected lines, severity, a minimal fix, and observable conditions for confirming the issue is resolved.

• Checking a PR for newly introduced vulnerabilities
• Reviewing CI changes that expose secrets or write access
• Inspecting Electron changes for unsafe permissions

Measure chat layout jumps while a response runs by tracking the Working line through CDP, a browser debugging connection. Count upward movements and compare the same prompt before and after changes to status lines, step rows, or folding behavior.

• Checking layout jumps after changing progress displays
• Measuring jumps caused by collapsing content
• Comparing flicker before and after a UI change

Set up OpenWork for a team, from creating an organization and inviting members to sharing AI models and skills. It covers dashboard setup and terminal setup, with human ownership of accounts and shared access to provider keys.

• Create an OpenWork organization and invite teammates
• Share AI models without distributing provider keys to members
• Create a skill and share it with a team

Connect OpenCode browser tools to a locally running OpenWork Electron app to inspect its UI, enter a task, and check the response. This skill supports exploration and debugging through CDP, Chrome's remote control protocol.

• Connecting browser tools to a local Electron development app
• Inspecting screen state during debugging
• Entering a task in the composer and running it

Set up and troubleshoot Daytona sandbox environments, which provide isolated spaces for running applications. The skill covers CLI authentication, persistent desktop and server sandboxes, diagnostic logs, shared secrets storage, snapshot refreshes, and environment deletion.

• Troubleshooting Daytona authentication and organization selection
• Keeping an Electron or server sandbox available for debugging
• Preparing shared secrets storage for sandboxes

Reproduce model connection failures and interrupted responses in the desktop app using a local fault server and test providers. Check error messages and retry behavior for refused connections, DNS failures, HTTP errors, stalled requests, and cut streams.

• Checking error messages for model connection failures
• Testing responses to rate limits and server errors
• Reproducing stalled requests and interrupted replies

Attach screenshots, images, or videos to GitHub pull requests and issues using GitHub CLI. It also covers embedding images within comment text, adding alternative text, and retrieving an uploaded asset’s URL from the posted comment.

• Attach a screenshot to a pull request
• Add a video to an issue report
• Embed an image within a GitHub comment

Investigate opaque errors in shipped OpenWork builds using local logs and Sentry exception reports. Identify the change that caused the failure, reproduce it on the affected runtime, file a Linear issue, and reply to the original report.

• Investigating unexplained errors in shipped OpenWork builds
• Identifying the PR that introduced a failure
• Reproducing errors on the affected runtime

Build and maintain interfaces with shadcn/ui by finding, adding, and combining components. The skill uses project settings, component documentation, and change previews to guide styling, debugging, preset changes, and updates that preserve local edits.

• Building settings pages and dashboards from existing components
• Fixing form and dialog composition issues
• Updating components while preserving local edits