← 返回 Skills 市场
本地研究资料查询
作者
clawdbotrr
· GitHub ↗
· v0.1.1
· MIT-0
231
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install research-archive-query
功能描述
统一查询本地研究资料库，默认同时搜索 AlphaPai 归档和 knowledge_bases，支持精确检索、向量检索和混合检索，并默认排除 private 资料库如 personal。
安全使用建议
This skill appears to do what it says (query local AlphaPai and knowledge_bases archives) but it executes and imports other local scripts that are not part of the published files. Before installing or enabling: 1) Inspect the referenced scripts (skills/alphapai-scraper/scripts/* and knowledge_bases/kb_engine.py and analyze.py) for network calls, credential use, or data exfiltration. 2) Confirm whether those modules read API keys or config files (e.g., OpenAI keys) — the skill does not declare required env vars. 3) Test the skill in a sandbox account or environment first, and ensure private scopes are correctly excluded by default. 4) Correct the hard-coded example path in SKILL.md if needed. If you cannot review the referenced code or do not trust the other workspace components, treat this skill as potentially risky.
功能分析
Type: OpenClaw Skill
Name: research-archive-query
Version: 0.1.1
The research-archive-query skill provides a unified interface for searching local research archives (AlphaPai and knowledge_bases). It functions as a wrapper that executes local scripts (e.g., query_comments.py and kb_engine.py) via subprocess calls using a list-based argument format, which mitigates shell injection risks. The skill includes logic for merging results, generating local Markdown reports, and utilizing an AI agent for summarization, all of which are consistent with its stated purpose and lack any indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
Name/description (unified local archive query) aligns with the code: unified_query.py builds and runs per-source query commands for alphapai and knowledge_bases and merges results. Requiring local archive scripts (alphapai-scraper, knowledge_bases) is coherent with the stated purpose.
Instruction Scope
SKILL.md and unified_query.py instruct running local Python scripts and will import/execute code from other workspace locations (e.g., skills/alphapai-scraper/scripts/query_comments.py, knowledge_bases/kb_engine.py and analyze.run_ai_analysis). Those external scripts can read any local files, environment variables, or network endpoints; the skill text does not list or limit what those scripts may access. SKILL.md also includes a hard-coded example path (/Users/bot/.openclaw/...), which may be inaccurate and indicates assumptions about the runtime environment.
Install Mechanism
No install spec (instruction-only with bundled scripts) — nothing is downloaded from the network during install. The code does execute local scripts via subprocess.run, which is expected for a query aggregator but increases runtime risk because it delegates work to other local code.
Credentials
The skill declares no required env vars, yet it imports analyze.run_ai_analysis and common.load_settings from the alphapai scripts and invokes other engine scripts; those modules commonly require API keys or configuration. Because required credentials are not declared, the skill may rely on (or leak to) existing environment secrets without warning. The skill can also read/write under ~/.openclaw/data, which is logical but gives it write access to user data.
Persistence & Privilege
always is false and there is no install script that modifies other skills or global agent settings. The skill will run locally and can be invoked; autonomous invocation is allowed by platform default but is not combined with an elevated 'always' flag here.
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 research-archive-query - 安装完成后，直接呼叫该 Skill 的名称或使用
/research-archive-query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
v0.1.1
Add adapter template for future archive sources
v0.1.0
Initial public release
元数据
常见问题
本地研究资料查询 是什么？
统一查询本地研究资料库，默认同时搜索 AlphaPai 归档和 knowledge_bases，支持精确检索、向量检索和混合检索，并默认排除 private 资料库如 personal。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 231 次。
如何安装 本地研究资料查询？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install research-archive-query」即可一键安装，无需额外配置。
本地研究资料查询 是免费的吗？
是的，本地研究资料查询 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
本地研究资料查询 支持哪些平台？
本地研究资料查询 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 本地研究资料查询？
由 clawdbotrr（@clawdbotrr）开发并维护，当前版本 v0.1.1。
推荐 Skills