← 返回 Skills 市场
216
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install source-research
功能描述
Build and maintain a reusable source-research system for discovering source pools, evaluating whether they are worth ongoing investment, defining efficient a...
安全使用建议
This skill appears internally consistent and does not request credentials or external network access. It will create and write files under a .source-research/ directory in the workspace (the bundled scripts simply copy provided templates). If you install it: - be aware it will persist artifacts to your workspace; review created files if you have sensitive data in the same repo. - the init script requires Python on PATH if the agent or you run it. - if you prefer manual control, run the initializer yourself rather than allowing autonomous agent invocation. Overall the package looks coherent for the stated purpose.
功能分析
Type: OpenClaw Skill
Name: source-research
Version: 1.0.0
The source-research skill bundle provides a structured framework for an AI agent to discover, evaluate, and document information sources. It includes a Python script (scripts/init_source_research.py) that safely initializes a local workspace directory (.source-research/) by copying a template from the assets folder. The instructions and methodology are consistent with the stated purpose of organizing research artifacts, and no indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
能力评估
Purpose & Capability
Name/description describe building a source-research system; the package contains framework references, templates, and a small initialization script which are all appropriate for that purpose. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to read bundled references and to store artifacts in a dedicated .source-research directory. It does not instruct the agent to read unrelated system files, environment variables, or transmit data to external endpoints. The guidance to record discovered pools during other tasks is part of the stated scope.
Install Mechanism
No install spec is provided (instruction-only). The only code file is a small Python script bundled with the skill; nothing is downloaded from external URLs and no archives are extracted.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The only runtime action that could require a binary is invoking Python to run the included init script; that is proportional to the script's purpose.
Persistence & Privilege
The skill will write a .source-research directory into the workspace (via the bundled init script or by the agent creating files). Autonomous invocation is allowed by default (normal for skills) — this increases the blast radius only in the sense that an agent could create or update files without manual steps, but that behavior is coherent with the skill's purpose.
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 source-research - 安装完成后，直接呼叫该 Skill 的名称或使用
/source-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
v1.0.0
- Initial release of the source-research skill with a reusable framework for discovering, evaluating, filtering, and managing information/source pools.
- Defines a structured storage standard in a canonical `.source-research/` directory, with clear categories for pools, acquisition, filtering, source lists, information, rejections, and programs.
- Outlines step-by-step workflows for discovering new pools, revisiting existing ones, manual vs. automated collection, and confirming pool value.
- Provides default operating rules to ensure efficient and non-redundant source research.
- Emphasizes creating and standardizing reusable artifacts for future agents, not just chat-based suggestions.
- Includes references to support methodology, artifacts, storage, and organization.
元数据
常见问题
Source Research 是什么？
Build and maintain a reusable source-research system for discovering source pools, evaluating whether they are worth ongoing investment, defining efficient a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 216 次。
如何安装 Source Research？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install source-research」即可一键安装，无需额外配置。
Source Research 是免费的吗？
是的，Source Research 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Source Research 支持哪些平台？
Source 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 Source Research？
由 kamael（@myvyang）开发并维护，当前版本 v1.0.0。
推荐 Skills