← 返回 Skills 市场
desearch-skill
作者
angelandpeiqi
· GitHub ↗
· v1.0.0
399
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install desearch-skill
功能描述
调用Zeelin Deep Research API进行深度研究任务。完全异步处理:提交任务后立即返回,后台进程自动确认大纲并定时检查任务状态,任务完成后自动保存md文件。自动配置定时通知(每2分钟检查),任务完成后主动通知用户。使用前必须先询问用户思考模式和搜索范围。
使用说明 (SKILL.md)
Zeelin Deep Research Skill
本skill用于调用Zeelin Deep Research API执行深度研究任务,采用完全异步处理模式。
⚠️ 重要:使用前必须先询问用户
当用户要求进行研究任务时,必须先询问以下信息:
-
思考模式(必选):
模式 说明 适用场景 smart 普通模式 快速简单的问题 deep 深度模式 (~5000字) 论文、竞品调研、中度报告 major 专家模式 (~10000+字) 深度研究报告 -
搜索范围(必选):
范围 说明 web 全网搜索 academic 学术搜索 selected 精选 -
研究主题(必选):用户想要研究的具体问题
配置 API Key
方式1:命令行设置(推荐)
python3 scripts/async_runner.py --set-key "YOUR_API_KEY"
方式2:配置文件
echo '{"api_key": "YOUR_API_KEY"}' > ~/.openclaw/zeelin-config.json
获取 API Key:https://desearch.zeelin.cn
使用方法
1. 检查 API Key
python3 scripts/async_runner.py --check-key
2. 提交任务
cd ~/.openclaw/workspace/skills/zeelin-deep-research
python3 scripts/async_runner.py -q "研究主题" -t deep -sr web
功能特性
- 异步提交:提交任务后立即返回,不阻塞
- 自动确认大纲:后台进程自动调用 confirmOutline
- 定时检查:每30秒检查一次任务状态
- 自动通知:cron 定时(每2分钟)检查任务完成状态,任务完成后主动通知用户
- 自动保存:完成后自动保存 md 文件到 /tmp/
结果文件
任务完成后,md 文件自动保存到:
~/.openclaw/workspace/skills/zeelin-deep-research/reports/zeelin_主题_时间戳.md
Cron 定时器
- 间隔:每1分钟
- 功能:检查任务完成状态
- 通知:任务完成后主动发送消息给用户
安全使用建议
This skill appears to implement the advertised async Zeelin research flow, but several red flags deserve action before installing: 1) The metadata claims no credentials, but the scripts require a Zeelin API key (via ZEELIN_API_KEY or ~/.openclaw/zeelin-config.json). Expect to provide that key and store it securely (prefer the local config file with restrictive permissions). 2) Inspect and remove or change the hard-coded notification recipient in async_runner.py (the openclaw cron add call uses channel 'dingtalk' and --to '0211560138072828'). That behavior could send notifications or commands to a third-party account you do not control — replace with your own destination or remove automatic outbound notifications. 3) Verify how your OpenClaw 'cron' subsystem behaves: what content is sent when cron triggers, who receives it, and whether cron execution will expose full report contents externally. 4) Note the docs/instruction inconsistencies (cron interval and save paths); test in a safe environment first (use a dummy API key and run locally) to confirm where files are saved and what is transmitted. 5) If you plan to use this skill, run the scripts under a limited user account, inspect logs/reports directory (~/.openclaw/.../reports) for unexpected files, and avoid setting ZEELIN_API_KEY as a global environment variable on multi-user systems. If you cannot confirm or remove the hard-coded notification target and are uncomfortable with automatic outbound notifications, do not install or run the cron-creation portions of the skill.
功能分析
Type: OpenClaw Skill
Name: desearch-skill
Version: 1.0.0
The skill bundle contains a significant privacy risk and potential data exfiltration vector. In `scripts/async_runner.py`, the `add_cron_job` function hardcodes a specific DingTalk recipient ID (`0211560138072828`) for task notifications. This causes the system to send research topics and local file paths to an external party whenever a research task completes, bypassing user configuration. Additionally, the script uses `subprocess` to persistently modify the system's cron jobs and launches background daemon processes. While these behaviors align with the stated 'asynchronous research' purpose, the hardcoded notification recipient is a major security flaw that leaks user activity to a third party (IOC: desearch.zeelin.cn).
能力评估
Purpose & Capability
Name/description state it calls Zeelin Deep Research API — the code does call desearch.zeelin.cn which matches the purpose. However the skill metadata declares no required environment variables/credentials while every script expects an API key (ZEELIN_API_KEY or ~/.openclaw/zeelin-config.json). That mismatch between declared requirements and actual runtime needs is incoherent and could surprise users. Also the scripts use the OpenClaw 'cron' CLI to create scheduled jobs and send notifications to a hard-coded dingtalk recipient ID (0211560138072828) which is not explained in the description and is unexpected for a research-only skill.
Instruction Scope
SKILL.md instructs asynchronous submission and periodic checks — consistent with the code. But there are contradictions: SKILL.md says it will check every 30s and cron every 2 minutes / every 1 minute in different places; it claims results are saved to /tmp/ while code writes to the skill's reports directory (~/.openclaw/.../reports). The SKILL.md also promises automatic 'active' notifications; the code implements this by creating an openclaw cron job that targets a specific dingtalk channel/recipient. Creating persistent scheduled jobs and sending outbound notifications is within the broad stated purpose, but the act of pushing notifications to a hard-coded external recipient is not documented in the skill metadata or given as a configurable option — that's scope creep and privacy/exfiltration risk.
Install Mechanism
No remote install/downloads or extract operations are present; source is included as local scripts and INSTALL.md describes manual copy. There is no install spec that fetches arbitrary code from external URLs. From an installation perspective this is low risk — but because code is shipped with the skill, users should still inspect it before running.
Credentials
Registry metadata lists no required env vars or primary credential, but the code requires an API key (reads ZEELIN_API_KEY or ~/.openclaw/zeelin-config.json). That is a substantive credential requirement that wasn't declared. Additionally, the add_cron_job call hard-codes a notification channel ('dingtalk') and a recipient ID, which is unrelated to the declared purpose and could result in automatic outbound notifications (and potentially data leakage) to an external account.
Persistence & Privilege
The skill will create a persistent cron job through the openclaw CLI (openclaw cron add) to perform periodic checks and send notifications. It also writes status, PID, logs, report files, and may remove its cron job later. 'always' is false, and autonomous invocation is default (not grounds for flagging alone), but creation of scheduled jobs and hard-coded outbound notification targets increases persistence and blast radius — especially given the unexplained external recipient.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install desearch-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/desearch-skill触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
zeelin-deep-research skill v1.0.0 - Initial Release
- Asynchronous deep research tasks using Zeelin Deep Research API.
- Tasks are submitted and processed in the background; immediate response on submission.
- Automatic outline confirmation and periodic (every 30–60 seconds) status checks.
- Results automatically saved as markdown files; users receive proactive completion notifications.
- Before starting any research, the skill prompts users for required thinking mode, search range, and research topic.
- Easy API key setup via CLI or config file.
元数据
常见问题
desearch-skill 是什么?
调用Zeelin Deep Research API进行深度研究任务。完全异步处理:提交任务后立即返回,后台进程自动确认大纲并定时检查任务状态,任务完成后自动保存md文件。自动配置定时通知(每2分钟检查),任务完成后主动通知用户。使用前必须先询问用户思考模式和搜索范围。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 399 次。
如何安装 desearch-skill?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install desearch-skill」即可一键安装,无需额外配置。
desearch-skill 是免费的吗?
是的,desearch-skill 完全免费(开源免费),可自由下载、安装和使用。
desearch-skill 支持哪些平台?
desearch-skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 desearch-skill?
由 angelandpeiqi(@angelandpeiqi)开发并维护,当前版本 v1.0.0。
推荐 Skills