Autoresearch Run Isolation logo

Autoresearch Run Isolation

Community
bosprimigenious
autoresearch-run-isolation

为 AutoResearch 的双 Agent 轨迹、付费 GPU 长跑、Docker 执行、可信评测与恢复建立共享协议、成本决策和隔离边界。用于小时/包日选择、启动或恢复 campaign、设计证据与防止题目或轨迹串用;不替代具体任务算法或最终平台 QA。

Overview

Publisherbosprimigenious
Repositoryautoresearch-skills
Skill nameautoresearch-run-isolation
Stars
57
Forks
6
Bundled files
14
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bosprimigenious on GitHub. Read the source before you install it.

Installation

Install the Autoresearch Run Isolation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bosprimigenious/autoresearch-skills/tree/main/skills/autoresearch-run-isolation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bosprimigenious/autoresearch-skills.git /tmp/autoresearch-skills
mkdir -p .claude/skills
cp -r /tmp/autoresearch-skills/skills/autoresearch-run-isolation .claude/skills/autoresearch-run-isolation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Autoresearch Run Isolation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Autoresearch Run Isolation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Autoresearch Run Isolation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AutoResearch 运行协议与隔离

先读 协议与隔离不变量。涉及租卡先读 成本与容量;涉及容器或 Harbor 再读 Docker 执行与 Harness 边界;接管单卡 NVIDIA 虚机、排查长跑停滞、处理 GPU backend 或 CUDA 缓存问题时读 单卡 NVIDIA Docker 现场蒸馏;准备停机、释放实例或冻结最终包时再读 最终化与关机。优先复用成熟运行协议;每题只实现任务适配器与可信评测器。

运行前冻结任务树并计算逐文件哈希;两条 Agent 轨迹使用同一公共任务摘要,但使用独立 workspace、控制目录、端口、上下文、凭据和轨迹目录。候选进程只能看到 Starter 与公开资产,Reference、专家证据和另一条轨迹不得进入其挂载范围。模型名称与 provider 是任务参数,不写死为某一家服务。

把指标、阈值、随机性协议、两条轨迹、开发环境、目标 Harness、持久快照、停止条件、liveness 协议、provider 硬失败策略和 durable evaluator 重试规则写入 JSON 合同,并在租卡前运行 scripts/preflight.py。GPU 任务还必须记录目标 backend 当前版本的能力依据。

第三方服务器声称内置 Docker 时,先用 scripts/docker_host_preflight.py 检查 daemon、Compose、存储和可选 NVIDIA runtime;GPU 场景再用本地已有、digest 固定的镜像执行显式动态 probe。随后分别取得 Agent 镜像、Verifier 镜像和目标 backend 的真实 GPU Trial。宿主有 Docker、通用 CUDA 容器成功或 Harness dry-run 通过,都不能替代两条隔离 lane、双镜像构建或完整 reward 证据。

每轮保存原始 RPC、命令、评测摘要、receipt 和来源哈希。每个正式结果只绑定一个真实 run/trial;源码、配置、seed、receipt、artifact、checkpoint 与时间窗不得跨轮拼接。可用 scripts/verify_lineage.py 检查结构化索引。

有效时长以闭合 turn 窗口为基础,未闭合、排队、安装、阻塞、睡眠和故障不计。两条轨迹分别达门槛,不能相加。单 GPU 默认串行训练/评分;只有显式绑定不同设备且协议允许时才并行,避免资源竞争污染结果。

把外部模型数据流纳入隔离合同:明确会发送的 prompt、工具结果和评测摘要;子进程环境使用最小白名单,凭据只以显式环境变量注入。落盘前按真实 secret 值和通用 token 形态脱敏,但不得把脱敏当作零外发。公开轨迹只保留完成审计所需字段,不发布原始 RPC、作者路径、主机信息或 capability 链接。

恢复运行前比较任务摘要、driver capability、镜像 digest、已完成轮和远端 lease;不复用旧 PID 或不明控制目录。租赁实例不是唯一存储,关机前同步代码、轨迹、checkpoint、receipt 和成本台账,并至少做一次新容器或新实例恢复演练。

默认采用分阶段资源策略:本地/小卡清除功能问题,目标 GPU 按小时完成真实端到端 pilot,再按 scripts/plan_capacity.py 比较全小时、全包日和“小时 pilot + 包日正式窗口”。将关机后租不到、重建、延期和无法补测的期望损失纳入小时制;包日空闲是容量保险,不冒充计算利用率。模型 API 先检查模型、区域、配额周期和并发是否符合,再用 pilot 的真实用量比较套餐与按量价格。API、GPU 和存储分开记账,追加消费不能修复协议、血缘或 Harness 缺陷。

打包只从冻结源和显式白名单构建;构建后解压到新目录,比较完整路径集合与 SHA256,再交给 QA。主包、自检、轨迹和证据附件分别执行隐私检查,任一附件失败都不能发布。

本 skill 的 assets/compose.yaml 是普通 NVIDIA Docker 主机上的开发模板,不代表目标 Harbor backend 支持 GPU。目标平台能力以当前版本和真实运行证据为准;没有动态运行时只报告静态检查。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Autoresearch Run Isolation AI skill do?

为 AutoResearch 的双 Agent 轨迹、付费 GPU 长跑、Docker 执行、可信评测与恢复建立共享协议、成本决策和隔离边界。用于小时/包日选择、启动或恢复 campaign、设计证据与防止题目或轨迹串用;不替代具体任务算法或最终平台 QA。

Why use Autoresearch Run Isolation on TypingMind?

Because you install it once and use it with any model. Autoresearch Run Isolation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Autoresearch Run Isolation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bosprimigenious/autoresearch-skills/tree/main/skills/autoresearch-run-isolation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Autoresearch Run Isolation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Autoresearch Run Isolation?

As many as you like. As long as a model supports skills, you can use Autoresearch Run Isolation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Autoresearch Run Isolation AI skill free?

Yes. It is published on GitHub by bosprimigenious under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇