360 Secure SkillHub
360 安全技能中心

ScienceClaw: Agent Status

核心功能：查看ScienceClaw代理的日志统计、近期日志、活跃调查、所有研究主题，搜索记忆内容，检查安装健康。典型场景：了解代理工作内容、回溯研究主题、搜索特定记忆、排查安装问题。通过bash调用带参数的memory_cli命令执行，支持自动解析或指定代理名，输出对应状态统计与数据。

fwang108
fwang108
热度 54.99
最近更新 2026-05-11 17:32:53
分类：数据依赖：代码执行 / 读写文件应用场景：数据处理 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add scienceclaw-status
Metadata
name
scienceclaw-status
description
Check the status of a ScienceClaw agent — journal stats, recent investigations, knowledge graph size, and activity summary.
metadata
{"openclaw":{"emoji":"📊","skillKey":"scienceclaw:status","requires":{"bins":["python3"]},"primaryEnv":"ANTHROPIC_API_KEY"}}

ScienceClaw: Agent Status

Inspect the memory, activity, and health of a ScienceClaw agent.

When to use

Use this skill when the user asks to:

  • Check what a ScienceClaw agent has been working on
  • See recent investigations or journal entries
  • Review agent activity stats (topics explored, tools used, post count)
  • Search an agent's memory for a specific topic
  • Get a health check on the ScienceClaw installation

How to run

Use bash to invoke the memory CLI. SCIENCECLAW_DIR defaults to ~/scienceclaw or ~/.scienceclaw/install.

SCIENCECLAW_DIR="${SCIENCECLAW_DIR:-$HOME/scienceclaw}"
AGENT=$(python3 -c "import json,pathlib; p=pathlib.Path.home()/'.scienceclaw'/'agent_profile.json'; print(json.loads(p.read_text()).get('name','ScienceAgent'))" 2>/dev/null || echo "ScienceAgent")
cd "$SCIENCECLAW_DIR"
python3 memory_cli stats --agent "$AGENT"

Subcommands

Journal stats (default status view)

python3 memory_cli journal --agent "$AGENT"

Recent journal entries

python3 memory_cli journal --agent "$AGENT" --recent 10

Active investigations

python3 memory_cli investigations --agent "$AGENT" --active

All investigated topics

python3 memory_cli journal --agent "$AGENT" --topics

Search memory for a topic

python3 memory_cli graph --agent "$AGENT" --search "CRISPR"

Full stats summary

python3 memory_cli stats --agent "$AGENT"

Parameters

  • --agent — agent name (auto-resolved from ~/.scienceclaw/agent_profile.json if not provided)
  • --recent N — show last N journal entries
  • --active — show only in-progress investigations
  • --search TERM — search knowledge graph for a term
  • --topics — list all topics ever investigated

Resolving the agent name

Always auto-resolve the agent name from the profile before running:

AGENT=$(python3 -c "
import json, pathlib
p = pathlib.Path.home() / '.scienceclaw' / 'agent_profile.json'
print(json.loads(p.read_text()).get('name', 'ScienceAgent'))
" 2>/dev/null || echo "ScienceAgent")

If the user specifies an agent name explicitly, use that instead.

Workspace context

If the workspace memory (memory.md) contains a preferred agent name, use that as the default --agent value.

After running

Report back to the user:

  • Agent name and total journal entries
  • Number of topics investigated
  • Most recent 3–5 topics (if available)
  • Any active/in-progress investigations
  • Offer to run a deeper search with scienceclaw-investigate on any of the listed topics