Repository
different-ai/openwork agent skills
- skills
- 32
- GitHub stars
- 24k
GitHub description: “The open-source alternative to Claude Cowork (powered by opencode)”
- Stars
- 23,920 (2,411 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Jan 2026
- Homepage
- openworklabs.com
Install all skills
npx skills add different-ai/openworkAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in different-ai/openwork, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks. | different-ai/ | 24k | — | ~465 | Automated safety check: Pass | Unknown | today |
| 2 | Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced. | different-ai/ | 24k | — | ~642 | Automated safety check: Pass | Unknown | today |
| 3 | Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models. | different-ai/ | 24k | — | ~1.1k | Automated safety check: Pass | Unknown | today |
| 4 | Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders. | different-ai/ | 24k | — | ~673 | Automated safety check: Pass | Unknown | today |
| 5 | Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts. | different-ai/ | 24k | — | ~780 | Automated safety check: Pass | Unknown | today |
| 6 | Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests. | different-ai/ | 24k | — | ~917 | Automated safety check: Pass | Unknown | today |
| 7 | Spins up a persistent OpenWork Cloud Den demo on a Daytona sandbox, seeds it with Acme Robotics data and returns shareable URLs and login details. | different-ai/ | 24k | — | ~1.3k | Automated safety check: Pass | Unknown | today |
| 8 | Classifies a failing test, typecheck or CI job before any code changes, by recording the failure and running a clean control to show whether it was already broken. | different-ai/ | 24k | — | ~779 | Automated safety check: Pass | Unknown | today |
| 9 | Reads the advisory design review attached to a pull request's screenshots, fixes the flagged UI problems in product code, and proves each note is gone. | different-ai/ | 24k | — | ~824 | Automated safety check: Pass | Unknown | today |
| 10 | Installs the free OpenWork desktop app on macOS, Windows or Linux by detecting the OS and CPU, choosing the right download and guiding the first task. | different-ai/ | 24k | — | ~564 | Automated safety check: Pass | Unknown | today |
| 11 | 11.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. | different-ai/ | 24k | — | ~926 | Automated safety check: Pass | Unknown | today |
| 12 | Runs OpenWork's agent-first test specs one at a time, locally or on Daytona, and records exact results, skips and runtime mismatches instead of reporting a loose pass. | different-ai/ | 24k | — | ~764 | Automated safety check: Pass | Unknown | today |
| 13 | 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. | different-ai/ | 24k | — | ~758 | Automated safety check: Pass | Unknown | today |
| 14 | 14.Write A Spec Write or extend an E2E journey spec in evals/specs that proves a PR's change to a human reviewer. | different-ai/ | 24k | — | ~3.3k | Automated safety check: Pass | Unknown | today |
| 15 | 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… | different-ai/ | 24k | — | ~355 | Automated safety check: Pass | Unknown | today |
| 16 | Boots, reopens, updates or resets disposable OpenWork preview environments for a pull request, locally or on a private Daytona or Freestyle host. | different-ai/ | 24k | — | ~5.9k | Automated safety check: Pass | Unknown | today |
| 17 | Declares each new or noticeable change as an off-by-default entry in OpenWork's feature registry before any feature code, and covers rollout, kill switches and cleanup. | different-ai/ | 24k | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 18 | Connects the OpenWork MCP Gateway to Claude Code, Codex, Gemini CLI, OpenCode and other clients so the agent can use your organization's skills, plugins and connections. | different-ai/ | 24k | — | ~661 | Automated safety check: Pass | Unknown | today |
| 19 | Advisory review of a diff that flags user-facing UI changes breaking numbered rules in the repository's DESIGN.md, reporting at medium or low severity only. | different-ai/ | 24k | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 20 | Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report. | different-ai/ | 24k | — | ~803 | Automated safety check: Pass | Unknown | today |
| 21 | Produces a browsable screenshot index, and video when motion matters, from a Daytona UI journey as presentation material next to a PR's test evidence. | different-ai/ | 24k | — | ~2.2k | Automated safety check: Pass | Unknown | today |
| 22 | Cuts an OpenWork desktop release through a tag-driven GitHub Actions workflow that makes no commits, with pre-tag checks on open fix PRs and verification afterward. | different-ai/ | 24k | — | ~2.3k | Automated safety check: Pass | Unknown | today |
| 23 | Checklist for reviewing pull requests from forks before approval: DCO sign-offs on every commit, CLA for ee/ paths, and whether the change is safe to merge. | different-ai/ | 24k | — | ~2.3k | Automated safety check: Pass | Unknown | today |
| 24 | Configures and verifies the OpenWork Slack assistant for an approved private-alpha organization, merging manifest changes into its existing Slack app. | different-ai/ | 24k | — | ~1.2k | Automated safety check: Pass | Unknown | today |
| 25 | Checks a published OpenWork desktop release by booting the released macOS binaries through packaged journeys, verifying signing and updater manifests, and publishing evidence. | different-ai/ | 24k | — | ~1.7k | Automated safety check: Pass | Unknown | today |
| 26 | Workspace guide to introduce OpenWork and onboard new users. | different-ai/ | 24k | — | ~411 | Automated safety check: Pass | Unknown | today |
| 27 | 27.Upload Photo Attach a screenshot/image/video to a PR or issue, or embed an image in a GitHub comment. | different-ai/ | 24k | — | ~253 | Automated safety check: Pass | Unknown | today |
| 28 | Flag desktop<-den contract drift introduced by this diff. An agent skill from different-ai/openwork. | different-ai/ | 24k | — | ~1.1k | Automated safety check: Pass | Unknown | today |
| 29 | Flag only new security issues introduced by this diff. An agent skill from different-ai/openwork. | different-ai/ | 24k | — | ~951 | Automated safety check: Pass | Unknown | today |
| 30 | Search and use the skills, MCP connections, and connected services available through the user's OpenWork organization. | different-ai/ | 24k | — | ~370 | Automated safety check: Pass | Unknown | today |
| 31 | Flag concrete false-positive proof introduced by changed specs, not test helper or channel preferences. | different-ai/ | 24k | — | ~735 | Automated safety check: Pass | Unknown | today |
| 32 | Flag customer, prospect, partner, or outside-person identities in the diff. | different-ai/ | 24k | — | ~223 | Automated safety check: Pass | Unknown | today |
Questions, answered from the data.
What is the best skill in different-ai/openwork?
OpenWork Desktop CDP Driver from different-ai/openwork ranks first of the 32 skills in different-ai/openwork listed here, with the highest score: its repository has 24k GitHub stars, its SKILL.md loads about 465 tokens and it passes the automated safety check with no findings. Next come Fake Model Provider Faults and OpenWork Model Alias Manager.
Are the skills in different-ai/openwork official?
None yet. All 32 skills in different-ai/openwork listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from different-ai/openwork?
Run npx skills add different-ai/openwork in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.