← Back to Skills Marketplace
1538
Downloads
2
Stars
6
Active Installs
1
Versions
Install in OpenClaw
/install science
Description
Guide scientific understanding from childhood wonder to research precision.
Usage Guidance
This skill appears coherent and low-risk: it's a set of teaching guidelines and asks for nothing sensitive. Before enabling, consider: 1) test with a few prompts to confirm the agent does not invent citations — the SKILL.md explicitly warns against fabricating references but the agent can still hallucinate; ask for real source links. 2) when the skill suggests demos or experiments, verify it provides clear safety/hazard guidance before acting on them. 3) because it is instruction-only, there is no install risk, but if you combine this skill with other skills that can access the network or your files, watch for possible data leakage (not an issue from this skill alone).
Capability Analysis
Type: OpenClaw Skill
Name: science
Version: 1.0.0
The OpenClaw skill bundle contains only metadata (`_meta.json`) and instructional markdown (`SKILL.md`). The `SKILL.md` file provides detailed pedagogical guidance for an AI agent on how to teach and explain scientific concepts across different audience levels, emphasizing accuracy, honesty, and critical thinking. There are no executable scripts, no instructions for prompt injection, no attempts to access sensitive data, perform network requests, or execute arbitrary commands. The content is entirely focused on guiding the agent's conversational style and knowledge delivery, with no high-risk behaviors or malicious intent detected.
Capability Assessment
Purpose & Capability
Name and description (teaching/science guidance) align with the SKILL.md, which contains pedagogical guidance for children, students, researchers, and teachers. No unrelated services, binaries, or credentials are requested.
Instruction Scope
The runtime instructions are pedagogical rules and checklists; they do not direct reading of system files, access to environment variables, or posting to external endpoints. They do tell the agent to encourage verification via Scholar/PubMed and to state knowledge cutoff, which is appropriate for a teaching skill.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — minimal risk and nothing is written to disk.
Credentials
The skill requires no environment variables, credentials, or config paths. Requested capabilities are proportional to the teaching purpose.
Persistence & Privilege
always is false and the skill is user-invocable; autonomous invocation is allowed (the platform default) but this skill does not request elevated persistence or modify other skills/configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install science - After installation, invoke the skill by name or use
/science - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Science?
Guide scientific understanding from childhood wonder to research precision. It is an AI Agent Skill for Claude Code / OpenClaw, with 1538 downloads so far.
How do I install Science?
Run "/install science" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Science free?
Yes, Science is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Science support?
Science is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Science?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.
More Skills