← 返回 Skills 市场
ScienceClaw: Multi-Agent Investigation
作者
Fiona Wang
· GitHub ↗
· v1.0.2
· MIT-0
349
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install scienceclaw-investigate
功能描述
Run a multi-agent autonomous scientific investigation on any topic. Spawns specialized AI agents that use 300+ scientific tools (PubMed, BLAST, UniProt, PubC...
安全使用建议
This skill delegates work to a local ScienceClaw installation and asks for an Anthropic API key — that is reasonable for an LLM-driven multi-agent tool. Before installing/using it, verify the following: (1) inspect the actual code in your SCIENCECLAW_DIR (bin/scienceclaw-investigate and the repository) so you know what will run; (2) confirm how posting to Infinite is authenticated (do you have an Infinite token stored locally?) and whether that token will be used; (3) be aware the instructions ask the agent to read workspace memory.md and local attachment file paths — do not allow access to sensitive files you don't want the agent to read; (4) run a dry-run or sandboxed session first (use --dry-run) and restrict network access if possible; (5) consider limiting the Anthropic key's scope/quotas and rotate it if you decide to stop using the skill. If you cannot inspect or trust the local ScienceClaw code and you do not want the agent to access workspace files or post externally, do not enable this skill.
功能分析
Type: OpenClaw Skill
Name: scienceclaw-investigate
Version: 1.0.2
The scienceclaw-investigate skill acts as a wrapper for a scientific research framework, invoking a local Python script (bin/scienceclaw-investigate) to perform multi-agent analysis. It follows a transparent workflow, including reading workspace context from memory.md and reporting findings and post IDs back to the user. The behavior is consistent with its stated purpose of scientific investigation and lacks indicators of malicious intent, such as data exfiltration or unauthorized persistence.
能力评估
Purpose & Capability
Name/description (multi-agent scientific investigation) match required binaries (python3) and primary credential (ANTHROPIC_API_KEY) — an LLM API key is reasonable. However the skill claims posting to the Infinite platform but does not declare any Infinite posting credential or config; it also claims use of many external tools (PubMed, BLAST, UniProt, ChEMBL, etc.) but does not request any corresponding API keys or explain how those connectors are authenticated. These omissions could be legitimate if the local ScienceClaw install contains connectors and credentials, but the SKILL.md does not document that.
Instruction Scope
The runtime instructions tell the agent to cd into a user-owned directory (SCIENCECLAW_DIR), source a virtualenv and run a local python script (bin/scienceclaw-investigate). That means the agent will execute arbitrary code from the user's filesystem — the skill package provides no code or auditability. The instructions also explicitly tell the agent to read workspace memory (memory.md) and save file paths for attachments; that grants the agent access to potentially sensitive local project data. Reading workspace memory and accessing attachments may be reasonable for richer context, but this broad file access is not declared in the skill's required config paths and is a privacy risk.
Install Mechanism
No install spec and no code files (instruction-only) — this is low surface risk from the skill package itself. However, the skill instructs running a local installation (~/scienceclaw) that will be responsible for tool integrations and network calls; since the skill doesn't install or verify that code, the real runtime behavior depends entirely on whatever is present at SCIENCECLAW_DIR, which could be arbitrary and untrusted.
Credentials
PrimaryEnv is ANTHROPIC_API_KEY which aligns with multi-agent LLM-driven work. No other env vars are declared, which is good from a minimal-secrets perspective, but the SKILL.md expects posting to Infinite and calling many external tools without declaring credentials for those services — either those credentials are managed by the local ScienceClaw install (possible), or they are missing (incoherent). The instruction to read memory.md is an additional data-access requirement not represented in requires.config.
Persistence & Privilege
always is false and autonomous invocation is permitted (platform default). The skill does not request persistent/system-wide privileges nor declare modifications to other skills. There is no 'always:true' or other elevated persistence requested.
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 scienceclaw-investigate - 安装完成后，直接呼叫该 Skill 的名称或使用
/scienceclaw-investigate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
v1.0.2
Remove ~/LAMM from all default paths — SCIENCECLAW_DIR now defaults to ~/scienceclaw
v1.0.1
Add skillKey metadata so skills register as /scienceclaw:investigate, /scienceclaw:post, /scienceclaw:query, /scienceclaw:local-files, /scienceclaw:status, /scienceclaw:watch slash commands in OpenClaw
v1.0.0
Initial release
元数据
常见问题
ScienceClaw: Multi-Agent Investigation 是什么？
Run a multi-agent autonomous scientific investigation on any topic. Spawns specialized AI agents that use 300+ scientific tools (PubMed, BLAST, UniProt, PubC... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 349 次。
如何安装 ScienceClaw: Multi-Agent Investigation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install scienceclaw-investigate」即可一键安装，无需额外配置。
ScienceClaw: Multi-Agent Investigation 是免费的吗？
是的，ScienceClaw: Multi-Agent Investigation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
ScienceClaw: Multi-Agent Investigation 支持哪些平台？
ScienceClaw: Multi-Agent Investigation 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 ScienceClaw: Multi-Agent Investigation？
由 Fiona Wang（@fwang108）开发并维护，当前版本 v1.0.2。
推荐 Skills