orx-logs

Agent Skills › alphaXiv/OpenResearch › orx-logs

orx-logs

GitHub

用于定位和读取实验运行日志，支持检查进度、调试失败及获取配置测量数据。

agent-skills/orx-logs/SKILL.md alphaXiv/OpenResearch

Trigger Scenarios

检查实验运行进度调试实验运行失败检索记录的配置和测量值

Install

npx skills add alphaXiv/OpenResearch --skill orx-logs -g -y

More Options

Non-standard path

npx skills add https://github.com/alphaXiv/OpenResearch/tree/main/agent-skills/orx-logs -g -y

Use without installing

npx skills use alphaXiv/OpenResearch@orx-logs

指定 Agent (Claude Code)

npx skills add alphaXiv/OpenResearch --skill orx-logs -a claude-code -g -y

安装 repo 全部 skill

npx skills add alphaXiv/OpenResearch --all -g -y

预览 repo 内 skill

npx skills add alphaXiv/OpenResearch --list

SKILL.md

Frontmatter

{
    "name": "orx-logs",
    "description": "Locate and read persisted experiment output with `orx logs`. Invoke when inspecting run progress, debugging a run failure, or retrieving recorded configuration and measurements; use `orx-results` to interpret the findings."
}

Reading run logs — `orx logs`

A run's terminal output is kept on this computer when the run finishes. While it runs, engine-owned output stays on its compute host; supervised runs also stream it into a local log.

orx logs <runId>                    # local path, byte size, and last ~500 characters
rg -n 'metric|summary' <log-path>   # search the file for relevant evidence

For a finished run the command prints the local log path, exact byte size, a short preview of the end, and a search hint. For a run still in flight it prints the size so far and the end of the available log. The preview is not the complete result.
Use native file tools on the printed path to search or read the portions you need. Cite the lines supporting each claim.
<runId> comes from orx runs <projectId>.

Truncated output is not evidence of absence. Search or read the reported file until the relevant portion has been found.