Skip to content
Automation
Skill

/analyze-traj

Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants to understand agent performance on OSWorld tasks — including analyzing trajectories, reviewing task results, finding error patterns, comparing code vs

Boost this skill
@amap-mlamap-ml@amap-ml
From plugin
longhorizon-harness
1.5k5 skills
Install
$ npx -y skills add AMAP-ML/LongHorizon-Harness --skill analyze-traj --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/analyze-traj

Context preview

The summary Claude sees to decide when to auto-load this skill.

Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants to understand agent performance on OSWorld tasks — including analyzing trajectories, reviewing task results, finding error patterns, comparing code vs

SKILL.md

analyze-traj.SKILL.md
name: analyze-traj
description: "Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants to understand agent performance on OSWorld tasks — including analyzing trajectories, reviewing task results, finding error patterns, comparing code vs GUI strategies, identifying which tools/commands the agent used, or deciding which task types to scale up in the benchmark."

If only one task is issued, analyze it directly with instruction: [analyze-single-traj.md](prompts/analyze-single-traj.md).

If multiple tasks or a whole results directory are issued, use subagents to analyze them in parallel (one agent for each task). 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-traj`) to do the analysis. Pass any user instructions to every subagent.

After the per-task reports are ready:

  • Do nothing but report to the user that the analysis is done and where to find the reports.
  • Ask user if they want to synthesize a run-level summary, if yes use: [analyze-full-run.md](prompts/analyze-full-run.md).
Read it on GitHub ↗
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.

Get the whole plugin
Stats
PythonJavaScriptNodeReactBash
+7 tags
DockerLinuxGitHubAnthropicOpenAIHugging FaceMCP
1,565
Stars
173
Forks
Active
Maintenance
Python
Language
MIT
License
27d ago
Last commit
1mo ago
Created

Repo: AMAP-ML/LongHorizon-Harness

In this plugin
5 skills
See everything inside

Other skills on longhorizon-harness.