analyze-task
Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and agent-visible files, inspect setup…
Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding, AWS provider setup, Docker provider setup, mocked website server setup, GitLab server setup, gated task download, CUA-Harness hybrid experiment setup,
$ npx -y skills add AMAP-ML/LongHorizon-Harness --skill setup-osworld --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/setup-osworldContext preview
The summary Claude sees to decide when to auto-load this skill.
Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding, AWS provider setup, Docker provider setup, mocked website server setup, GitLab server setup, gated task download, CUA-Harness hybrid experiment setup,
name: setup-osworld description: "Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding, AWS provider setup, Docker provider setup, mocked website server setup, GitLab server setup, gated task download, CUA-Harness hybrid experiment setup, or a final runnable export block. The skill should install/configure the selected supported infrastructure where possible, ask for user confirmation or credentials when required, and report what is fully configured versus still blocked."
Use this skill to make a cloned OSWorld-V2 checkout runnable, not merely to list environment variables. Provision every selected component that can be configured safely from the current machine, and ask the user whenever an action requires credentials, paid resources, DNS changes, SSH keys, secrets, or a destructive/cloud operation.
Supported provider setup:
export the values OSWorld needs.
Docker provider can run.
Unsupported provider setup for now:
For unsupported providers, load `references/unsupported-providers.md`, state that this skill does not automate them yet, and ask whether the user wants AWS or Docker instead.
Optional service setup:
host-side proxy or HF mirror setup.
`experiments/osworld_v2_hybrid` and the sibling `cua-harness/` source tree.
Ask before doing infrastructure work unless the user has already supplied the answers.
Ask for:
host suffix
If the user says "do it unattended", still stop for any cloud spend, DNS, GitHub private-repo authorization, generated secret disclosure, or destructive operation.
1. Read `README.md`, `docs/PROVIDER_SETUP.md`, and the selected references. 2. Load `references/common.md` and complete package/tool setup. 3. Load exactly one provider reference:
4. For OSWorld-web, load `references/website.md`. 5. For GitLab, load `references/gitlab.md`. 6. For gated task classes, load `references/tasks.md`. 7. For proxy needs, load `references/proxy.md`. 8. For CUA-Harness hybrid experiments, load `references/cua-harness.md`. 9. Load `references/verify.md` and run verification for each selected surface. 10. Write final setup outputs:
to print them
items
create or verify the backing resource that makes the variable valid.
user chose manual setup.
describe, with `HOST_SUFFIX`, `GITLAB_URL`, and `GITLAB_PRIVATE_TOKEN` backed by reachable services.
asks to run an agent or evaluator.
files.
and ask the user to authorize GitHub access instead of inventing commands.
smoke-tested", "not configured", or "blocked awaiting user action".
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
Repo: AMAP-ML/LongHorizon-Harness
Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and agent-visible files, inspect setup…
Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants to understand agent…
Migrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the integration.
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up dependencies, download WeaveBench…