Skip to main content
ClaudeWave
Skill1.4k repo starsupdated 16d ago

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.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/AMAP-ML/LongHorizon-Harness /tmp/analyze-task && cp -r /tmp/analyze-task/eval/OSWorldv2-harness/OSWorld-V2/.codex/skills/analyze-task ~/.claude/skills/analyze-task
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

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.