← Back to Skills Marketplace
ScienceClaw: Agent Status
by
Fiona Wang
· GitHub ↗
· v1.0.2
· MIT-0
300
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install scienceclaw-status
Description
Check the status of a ScienceClaw agent — journal stats, recent investigations, knowledge graph size, and activity summary.
Usage Guidance
Do not provide your ANTHROPIC_API_KEY to this skill without confirming why it is needed. Before installing or granting access: (1) Inspect the local memory_cli program (location and source) to see whether it actually uses Anthropic or other network services. (2) Manually run the example commands in a terminal to see what files are read and whether any network calls occur. (3) Check the contents and permissions of ~/.scienceclaw and ~/.scienceclaw/agent_profile.json to ensure no sensitive secrets would be exposed. (4) Ask the skill publisher why ANTHROPIC_API_KEY is declared — it may be a metadata mistake or indicate hidden network behavior. If you can’t verify the CLI’s behavior, run it in an isolated environment (container or VM) or mark the skill as untrusted.
Capability Analysis
Type: OpenClaw Skill
Name: scienceclaw-status
Version: 1.0.2
The skill is designed to monitor the status and activity of a 'ScienceClaw' agent by executing a local CLI tool (memory_cli) and reading configuration data from the user's home directory (~/.scienceclaw/agent_profile.json). The operations are consistent with the stated purpose, and there is no evidence of data exfiltration, malicious execution, or prompt injection attacks.
Capability Assessment
Purpose & Capability
The name/description indicate a local agent-status inspector and the required binary (python3) aligns with that. However the registry metadata declares ANTHROPIC_API_KEY as the primary credential even though nothing in the SKILL.md uses or needs an external LLM API key for the described status checks. That credential requirement is disproportionate to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to read ~/.scienceclaw/agent_profile.json, use SCIENCECLAW_DIR (defaulting to ~/scienceclaw or ~/.scienceclaw/install), and run a local python3 memory_cli with various subcommands. Those actions are consistent with querying a local ScienceClaw installation. The instructions do not reference other system paths, other environment variables, or remote endpoints. Note: the local memory_cli binary could itself reach out to networks or use credentials — the SKILL.md does not document memory_cli behavior.
Install Mechanism
This is an instruction-only skill with no install spec and no code files; it does not write or download artifacts, which is the lowest install risk.
Credentials
The skill metadata lists ANTHROPIC_API_KEY as the primaryEnv, but the runtime instructions never reference or require that environment variable. Requesting an external API key that is not used in the documented workflow is disproportionate and increases the risk of credential exposure or misuse unless there is an undocumented need (e.g., memory_cli internally calling Anthropic).
Persistence & Privilege
The skill is not always-enabled, is user-invocable, and has no install steps that modify system or other skills' configuration. It does not request elevated or persistent platform privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install scienceclaw-status - After installation, invoke the skill by name or use
/scienceclaw-status - Provide required inputs per the skill's parameter spec and get structured output
Version History
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 of ScienceClaw skill pack
Metadata
Frequently Asked Questions
What is ScienceClaw: Agent Status?
Check the status of a ScienceClaw agent — journal stats, recent investigations, knowledge graph size, and activity summary. It is an AI Agent Skill for Claude Code / OpenClaw, with 300 downloads so far.
How do I install ScienceClaw: Agent Status?
Run "/install scienceclaw-status" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ScienceClaw: Agent Status free?
Yes, ScienceClaw: Agent Status is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ScienceClaw: Agent Status support?
ScienceClaw: Agent Status is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ScienceClaw: Agent Status?
It is built and maintained by Fiona Wang (@fwang108); the current version is v1.0.2.
More Skills