← 返回 Skills 市场
Research
作者
BrennerSpear
· GitHub ↗
· v1.1.0
4981
总下载
0
收藏
28
当前安装
2
版本数
在 OpenClaw 中安装
/install parallel-ai-research
功能描述
Conduct open-ended research on a topic, building a living markdown document. Supports interactive and deep research modes.
安全使用建议
Use the interactive note-taking part only if you are comfortable with research prompts and findings being saved locally. Before enabling deep research or PDF export, verify the actual parallel-research and export-pdf scripts from a trusted source, avoid system-wide symlinks unless needed, prefer a safer uv install method than curl | sh, and use a scoped or revocable Parallel AI API key.
功能分析
Type: OpenClaw Skill
Name: parallel-ai-research
Version: 1.1.0
The skill is classified as suspicious due to a significant shell injection vulnerability. Instructions in `SKILL.md` and `OPENCLAW.md` direct the OpenClaw agent to execute external CLI tools like `parallel-research` and `export-pdf` with arguments derived from user input (e.g., 'research question', 'topic-slug', 'run_id'). Without robust input sanitization by the agent or platform, these commands are susceptible to arbitrary command execution. Additionally, `SETUP.md` instructs users to install a dependency via `curl | sh`, which carries a supply chain risk, though this is a setup instruction for the user, not a runtime action by the agent.
能力评估
Purpose & Capability
The stated purpose, creating persistent research notes and optionally using Parallel AI for deep research, matches the runtime instructions.
Instruction Scope
The skill asks the agent to search, fetch sources, write research files, export PDFs, and optionally schedule follow-up checks; these are mostly disclosed and purpose-aligned, but activation language is broad for a workflow that writes persistent files.
Install Mechanism
SETUP.md instructs users to symlink parallel-research and export-pdf from a scripts directory, but the reviewed artifact contains only markdown files and no scripts, leaving the actual commands absent or unreviewed. It also includes a curl-to-sh uv install step.
Credentials
Deep research requires PARALLEL_API_KEY and sends research prompts to Parallel AI; this fits the feature but should be treated as external provider and account access.
Persistence & Privilege
The skill intentionally stores prompts, notes, reports, and PDFs under ~/.openclaw/workspace/research and can schedule future cron-based agent turns to poll results. This is disclosed, but persistent storage plus delayed agent activity needs clear user control.
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 parallel-ai-research - 安装完成后，直接呼叫该 Skill 的名称或使用
/parallel-ai-research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
v1.1.0
Updated from agent-skills repo
v1.0.0
Initial release of the research skill for open-ended, structured investigations.
- Supports interactive (real-time) and deep (async, Parallel AI-powered) research modes.
- Automatically creates organized research folders with prompt, findings, and exportable PDF.
- Guides workflow: questioning, note-taking, synthesis checkpoints, and completion/archival.
- Includes robust command triggers (new, deep, export PDF, show, graduate, archive).
- Emphasizes documentation best practices: source linking, context, and uncertainty notes.
元数据
常见问题
Research 是什么？
Conduct open-ended research on a topic, building a living markdown document. Supports interactive and deep research modes. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4981 次。
如何安装 Research？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install parallel-ai-research」即可一键安装，无需额外配置。
Research 是免费的吗？
是的，Research 完全免费（开源免费），可自由下载、安装和使用。
Research 支持哪些平台？
Research 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 Research？
由 BrennerSpear（@brennerspear）开发并维护，当前版本 v1.1.0。
推荐 Skills