Token导航 LogoToken导航

Agent Skill · 研究检索

atlas-tracker(阿特拉斯追踪器)

atlas-tracker 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

atlas-tracker 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 9,078。

总安装 14,976周安装 624GitHub Stars 公开资料未说明下载 4,992核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.5

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:atlas-tracker(阿特拉斯追踪器)
来源仓库:https://github.com/didro/atlas-tracker
安装命令:
openclaw skills install atlas-tracker
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install atlas-tracker

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

atlas-tracker 用于在 OpenClaw 中查找、检索和筛选相关信息,适合根据关键词或任务场景快速定位候选结果。适用于需要构建知识图谱、梳理信息关联或追踪复杂线索链路的场景。通过 MCP 工具操作 Atlas Tracker 思维导图,支持节点与分支的读取、创建和更新。

安装命令为 openclaw skills install atlas-tracker,需确认权限范围和维护状态。使用前应核实是否会触发联网、命令执行或文件读写等敏感操作。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install atlas-tracker;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

atlas-tracker 怎么安装?

在终端执行 openclaw skills install atlas-tracker。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

atlas-tracker 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

atlas-tracker 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

atlas-tracker 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

atlas-tracker 用的人多吗?

公开数据是累计安装 14,976 次,近一周安装 624 次,下载 4,992 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

atlas-tracker 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
atlas-tracker

阿特拉斯追踪器 · 本页

14,976—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
atlas-tracker
description
Work with Atlas Tracker (RedForester) mindmaps via MCP tools. Use when reading, creating, or updating nodes and branches in Atlas Tracker maps — including navigating map structure, creating solution trees, updating node properties, managing typed nodes, creating link nodes, uploading files to nodes, and working with node comments. Requires at_read_branch, at_create_branch, at_update_branch, at_get_node_types, at_read_attachments, at_create_link_node, at_upload_file, at_get_comments, at_add_comment, at_delete_comment, at_update_comment tools (provided by the Atlas Tracker OpenClaw plugin).

Atlas Tracker Skill

Atlas Tracker (app.redforester.com) is a graph-based knowledge system combining mindmaps, Kanban, and structured properties. This skill covers working with it via the OpenClaw AT plugin tools.

Setup

This skill requires two components to be installed and running:

1. AT MCP Server

A local Node.js server that proxies requests to the Atlas Tracker REST API.

The AT MCP server is maintained by the Atlas Tracker / RedForester team. Contact @gmdidro (Telegram) or visit app.redforester.com to request access.

Once you have the server files:

cd at-mcp/
yarn install
yarn build

# Run directly
node build/index.js

# Or run as a systemd user service (recommended)
cp at-mcp.service ~/.config/systemd/user/
systemctl --user daemon-reload
systemctl --user enable --now at-mcp

The server listens on http://localhost:3222 by default.

Required environment variables (set in the service file or .env):

AT_BASE_URL=https://app.redforester.com/api
AUTH_HEADER=Basic <base64(username:md5(password))>
API_KEY=<your-local-api-key>
PORT=3222

2. OpenClaw Plugin

Copy the plugin file to your OpenClaw extensions directory:

mkdir -p ~/.openclaw/extensions/atlas-tracker/
cp index.ts ~/.openclaw/extensions/atlas-tracker/
cp openclaw.plugin.json ~/.openclaw/extensions/atlas-tracker/

Then configure the plugin in your openclaw.json:

{
  "plugins": {
    "atlas-tracker": {
      "serverUrl": "http://localhost:3222",
      "apiKey": "<your-local-api-key>"
    }
  }
}

OpenClaw will hot-reload the plugin automatically. Verify with:

openclaw status

You should see at_read_branch, at_create_branch, at_update_branch, at_get_node_types, at_read_attachments listed as available tools.


Core Concepts

  • Map — a mindmap, identified by mapId (full UUID)
  • Node — a single item in the map; has id, title (HTML), optional typeId, typeProperties, children[]
  • Branch — a node + all its descendants
  • Node type — a schema defining available properties (enum, text, htmltext, file, user, date, etc.)
  • Title format — always HTML: <p>My title</p>, never plain text

Tool URLs

All tools take a nodeUrl in format:

https://app.redforester.com/mindmap?mapid=<UUID>&nodeid=<UUID>

Both mapid and nodeid must be full UUIDs (e.g. 3d7340e8-c763-4c9e-b049-4e900b7cf565), never partial.

Workflow

Reading a branch

Always read before modifying — never assume structure:

at_read_branch(nodeUrl) → returns node tree with children, types, properties

Finding the right node

If you don't know a nodeId, search via AT REST API:

POST /api/search  body: {"query": "...", "map_ids": ["<mapId>"]}
# Returns hits[].id — then at_read_branch each candidate to verify title

Creating branches

at_create_branch(parentNodeUrl, data)

data must include children: [] even for leaf nodes — required field.

Updating branches

at_update_branch(nodeUrl, delete[], update[], create[])
  • create items: {parentNodeId, data: {title, typeId?, typeProperties?, children: []}}
  • update items: {id, title?, typeProperties?, customProperties?}
  • All three arrays required (pass [] if unused)

Node Types

Call at_get_node_types(nodeUrl) once per map session — types vary per map. Common types: Идея, Задача, Заметка, Категория, Проект, Этап, Заявка, Лид.

For typed nodes, typeProperties keys must exactly match the property names from at_get_node_types.

Critical Rules

  1. Full UUIDs only — partial IDs (e.g. b319f356) will return 404
  2. children: [] required — omitting it causes validation error on create
  3. HTML titles — wrap in <p>...</p>; use <ul><li>...</li></ul> for lists
  4. Read before write — always at_read_branch first to get current state and node IDs
  5. 403 = permission denied — you can only write nodes owned by your AT account; read access may be broader
  6. Large maps are slow — avoid full subtree reads on large maps; use search + targeted node reads instead

Common Patterns

Add children to existing node

  1. at_read_branch to get parent nodeId and confirm it exists
  2. at_update_branch with create: [{parentNodeId: "<id>", data: {..., children: []}}]

Batch create a solution tree

Use at_create_branch with nested children[] to create the full tree in one call.

Update node content

  1. at_read_branch to get current node id and properties
  2. at_update_branch with update: [{id, typeProperties: {key: "<html_value>"}}]

Create a link node (shortcut/reference)

A link node is a reference to an existing node — it appears in the map as a shortcut to the original. Useful for showing the same node in multiple places without duplicating it.

at_create_link_node(nodeUrl, originalNodeId)
  • nodeUrl — URL of the parent where the link node should appear
  • originalNodeId — UUID of the existing node to reference

Example: place a reference to node abc-123 under parent node def-456:

at_create_link_node(
  "https://app.redforester.com/mindmap?mapid=<mapId>&nodeid=def-456",
  "abc-123"
)

Upload a file to a node

Attach any file (PDF, Excel, Word, image) to an AT node:

at_upload_file(nodeUrl, filePath)
  • filePath — absolute local path to the file
  • Uploads via PUT /api/files, then attaches as a type_id=10 property
  • Adds to existing files — does not overwrite

Work with comments

at_get_comments(nodeUrl)           → list all comments (with thread structure)
at_add_comment(nodeUrl, text, replyToCommentId?)  → add comment or reply to thread
at_update_comment(nodeUrl, commentId, text)       → edit comment text
at_delete_comment(nodeUrl, commentId)             → delete comment

Reference Files

  • api-patterns.md — REST API search, auth, node fetch patterns (read when you need to search nodes or call AT API directly)
  • node-types-guide.md — property type reference (htmltext, enum, file, user, date, etc.) and how to set them (read when creating/updating typed nodes)

平台分布

OpenClaw

95.79%
按下载量换算4,782

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills