different-ai/openwork

Agent skills in the GitHub repository different-ai/openwork, each with its code score out of 100.

The open-source alternative to Claude Cowork (powered by opencode)

Repository score

62 / 100 C

Skills

34

Verified

0

Average skill score

60

GitHub stars

24,493

License

Not identified by GitHub

Open different-ai/openwork on GitHub

34 skills in this repository

1. openwork-models

   Manage OpenWork inference model aliases, openwork model overlays, discounts, validation, and automated base model refreshes from models.dev. Use when adding, removing, discounting…

   76B
2. launch-workshop

   Start, size, check, hand out, fix and stop a hands-on OpenWork workshop (one private Den + 1-99 Daytona desktops, fictional Outlook/Calendar/Drive/Jira/Confluence). Use when the u…

   73B
3. shadcn

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

   72B
4. record-a-demo

   Screenshots, recording, and presentation artifacts.

   71B
5. preview-my-work

   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…

   69C
6. speed-up-ci

   CI is slow, time to green, how long do checks take, p50/p90, make CI faster, speed up a job or spec, hillclimb CI. Use to measure PR CI time, find where a job's seconds go, and la…

   69C
7. fix-design-notes

   Design notes on a PR, "Design review (advisory)" in the evidence check, "worth fixing", layout.split-row, OW-LIST, a reviewer says the UI looks off. Use to read what the design re…

   67C
8. write-a-spec

   Extend a core journey in evals/core or write a one-off proof in evals/proofs that proves a PR's change to a human reviewer. Use when a PR changes user-visible behaviour, when a re…

   66C
9. dry-run-a-risky-change

   Billing, plans, seats, permissions, access rules, auth, flag removals or data migrations that could lock real organizations out or change what they pay. Use before merging or depl…

   64C
10. create-plugin

    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',…

    63C
11. install-openwork

    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 t…

    63C
12. set-up-openwork-team

    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 comp…

    63C
13. verify-openwork

    Prove an OpenWork change works on the real product before calling it done. Start the product, drive the change the way a user or client would, capture screenshots, and show the pr…

    63C
14. browser-automation

    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 smok…

    62C
15. daytona-windows-cert

    test on Windows, enterprise CA, corporate certificate, GPO cert, TLS fetch failed, Windows sandbox, daytona windows, self-hosted cert. Use when validating OpenWork Windows enterpr…

    62C
16. set-up-openwork-slack

    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…

    62C
17. run-tests

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

    58C
18. connect-openwork-mcp

    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 u…

    57C
19. daytona

    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).

    57C
20. reproduce-chat-states

    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…

    57C
21. hunt-a-prod-error

    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, f…

    56C
22. daytona-seeded-cloud-demo

    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.

    55C
23. drive-desktop-cdp

    Drive the running OpenWork app over CDP from the shell, headless by default (nothing opens on screen). Evaluate JS, take screenshots, open a new session, send a prompt with a chos…

    55C
24. measure-chat-flicker

    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, foldin…

    55C
25. openwork-connect

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

    55C
26. review-a-contributor-pr

    Review a fork PR, review an external contributor PR, check provenance (DCO) and ee/ CLA, run /test, carry a fork commit into a same-repo branch, is this PR safe to merge. Checklis…

    55C
27. get-env-var

    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 en…

    54D
28. fake-model-faults

    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 pr…

    53D
29. open-a-pr

    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.

    53D
30. validate-a-release

    Validate the release, check the released binaries, is 0.18.x safe to roll out, prove a published desktop release. Checks the RELEASED mac-arm64 enterprise and cloud binaries' sign…

    53D
31. add-a-feature

    Decide whether work needs a feature flag (any change to product behavior users can see does), then declare it, roll it out (per organization, for everyone, cloud or self-hosted),…

    52D
32. workspace-guide

    Workspace guide to introduce OpenWork and onboard new users.

    50D
33. diagnose-a-red-run

    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.

    49D
34. upload-photo

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

    44D

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.