analyze-traj
Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants…
@amap-mlInstall SkillAutomation
Skill
/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 artifacts when needed, and produce both markdown and structured JSON reports.
Claude Code
$ npx -y skills add AMAP-ML/LongHorizon-Harness --skill analyze-task --agent claude-code
Codex
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a codex -y
Cursor
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a cursor -y
Gemini CLI
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a gemini-cli -y
GitHub Copilot
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a github-copilot -y
OpenCode
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a opencode -y
Windsurf
$ npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task -a windsurf -y
SKILL.md
analyze-task.SKILL.mdname: analyze-task description: "Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and agent-visible files, inspect setup artifacts when needed, and produce both markdown and structured JSON reports."
If only one task is issued, analyze it directly with instruction: [analyze-single-task.md](prompts/analyze-single-task.md).
If multiple tasks are issued, use subagents to analyze them in parallel (one agent for each task) and save reports under `check/<task_id>/`. Do not analyze them sequentially by yourself. DO NOT tell it what to do. Just ask the subagent to analyze the task in target directory and use this skill (analyze-task) to do the analysis. Pass any user instructions to every subagent.
After the subagents finish, do nothing but report to user that the check is done and where to find the reports.
Stats
1,867
Stars
196
Forks
Active
Maintenance
Python
Language
MIT
License
Last commit
Created
Ships withlonghorizon-harness
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.
1.8k5 skills
Stars on GitHub
Momentum
- stars in total
- 1.8k
Other skills on longhorizon-harness.
@amap-mlInstall Skillmigrate-osworld-agent
Migrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the…
@amap-mlInstall Skillsetup-osworld
Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding,…
@amap-mlInstall Skillweavebench-cua-reprodu…
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up…
@amap-mlInstall SkillMore skills from other plugins.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
@browser-useInstall Skillagent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…
@vercel-labs-2Install Skill
Questions about analyze-task.
- Which coding agents can use analyze-task?
- analyze-task installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.