Skill

Open-source Deep Research framework. Autonomously searches, extracts, and synthesizes information from the web.

Security Scan

The skill's code, declared requirements, and runtime instructions generally match its stated purpose as a web research framework, with a few minor inconsistencies to verify before installing.

Purpose & Capability

The skill is a research/search/LLM orchestration tool and requires Python and various optional LLM/search API keys — this aligns with its purpose. Minor inconsistency: the registry metadata marks OPENCLAW_API_KEY as the required/primary credential while the code and README primarily reference provider API keys (DEEPSEEK_API_KEY, GLM_API_KEY, BING_API_KEY, etc.). That primaryEnv choice is unusual but could reflect platform integration rather than core functionality.

Instruction Scope

SKILL.md and the examples instruct normal operations (pip install, run scripts, use /research /search /llm commands). The instructions do not ask the agent to read unrelated system files or exfiltrate data. The code performs network operations (search, fetch, LLM API calls) which are appropriate for a research tool.

Install Mechanism

There is no formal install spec in the registry, but SKILL.md recommends pip install from the GitHub repo (git+https://github.com/liantian-cn/researchclaw.git). Installing code from a GitHub repo is common but will execute arbitrary code from that repository on install — review the upstream repository before installing. requirements.txt includes optional heavy dependencies (weasyprint, fastapi/uvicorn) which are reasonable for optional features but increase surface area.

Credentials

The declared required env var is OPENCLAW_API_KEY (primaryEnv), but SKILL.md lists several provider API keys (DEEPSEEK_API_KEY, GLM_API_KEY, BING_API_KEY, etc.) as optional. The provider keys are justifiable for LLM/search integration. The mismatch between 'required' OPENCLAW_API_KEY and the provider keys used in code is a small red flag to confirm what OPENCLAW_API_KEY is used for and whether it's strictly necessary.

Persistence & Privilege

always:false and default autonomous invocation are standard. The skill creates a local cache directory and may write output files when requested, but it does not request system-wide configuration changes or access other skills' credentials.

Assessment

This skill appears to do what it says: web search, extraction, and synthesis using optional LLM/search provider APIs. Before installing, verify the upstream GitHub repository and review the code for network endpoints you trust, since pip install from a GitHub URL will execute repository code locally. Confirm why OPENCLAW_API_KEY is marked as the primary required credential (is it a platform integration token?), and only provide provider API keys (BING, DEEPSEEK, GLM, etc.) if you trust those services. Because the package may pull in optional heavy dependencies, consider installing in a sandboxed virtual environment. If you need higher assurance, ask the publisher for an explanation of OPENCLAW_API_KEY usage and for a minimal install option that excludes optional servers/frameworks.

ResearchClaw 🦁

Open-source Deep Research framework based on OpenClaw. An intelligent research assistant that autonomously searches, extracts, and synthesizes information from the web.

Installation

# Install from GitHub
pip install git+https://github.com/liantian-cn/researchclaw.git

# Or install locally
cd researchclaw
pip install -e .

OpenClaw Commands

/research

Research a topic deeply and generate a comprehensive report.

/research <topic> [--depth=3] [--engine=duckduckgo] [--output=path] [--format=markdown]

Examples:

/research AI trends 2026
/research quantum computing --depth=5
/research machine learning --engine=bing --output=./report.md

/search

Search for information on the web.

/search <query> [--limit=10] [--engine=duckduckgo]

Examples:

/search machine learning
/search neural networks --limit=20

/llm

Chat with LLM providers.

/llm <prompt> [--provider=deepseek] [--model=...] [--temperature=0.7]

Examples:

/llm What is Python?
/llm Explain quantum computing --provider=glm

/health

Check ResearchClaw skill health status.

/help

Show available commands.

Standalone Scripts

You can also use the standalone scripts:

python {baseDir}/scripts/research.py "artificial intelligence trends 2026"
python {baseDir}/scripts/search.py "machine learning"
python {baseDir}/scripts/llm.py "What is Python?"

Options

• --depth, -d: Research depth level (default: 3)
• --engine, -e: Search engine to use (duckduckgo, bing)
• --output, -o: Output file path
• --format, -f: Output format (markdown, html, json)
• --lang, -l: Language (en, zh)

Requirements

• Python 3.10+
• Optional: API keys for search engines (Bing) and LLM providers (DeepSeek, GLM, etc.)

Environment Variables

• DEEPSEEK_API_KEY: DeepSeek API key
• GLM_API_KEY: GLM API key
• MINIMAX_API_KEY: MiniMax API key
• KIMI_API_KEY: Kimi API key
• QWEN_API_KEY: Qwen API key
• BING_API_KEY: Bing Search API key

Notes:

• Uses DuckDuckGo by default (no API key required)
• Supports multiple LLM providers for synthesis
• Generates comprehensive research reports in multiple formats