analyze-task
Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and…
Migrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the integration.
Claude Code
$ npx -y skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent --agent claude-code
Codex
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a codex -y
Cursor
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a cursor -y
Gemini CLI
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a gemini-cli -y
GitHub Copilot
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a github-copilot -y
OpenCode
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a opencode -y
Windsurf
$ npx skills add AMAP-ML/LongHorizon-Harness --skill migrate-osworld-agent -a windsurf -y
name: migrate-osworld-agent description: "Migrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the integration."
Use this when adding an upstream OSWorld agent to this repo.
1. Read the upstream agent. 2. Read local patterns before editing:
3. Copy the agent into `mm_agents/` with a clear, non-conflicting name. 4. Adapt only the repo-facing interfaces:
5. Add a matching multi-env Python runner under `scripts/python/run_multienv_<agent>.py`.
6. Add a small shell entrypoint under `scripts/bash/`.
7. Keep unrelated agents, scripts, results, and local dirty files out of the change.
Run fast checks first.
Then run one small real smoke test.
Before opening a PR, stage only the migration files and re-run the fast checks.
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.
Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and…
Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants…
Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding,…
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…