ResearchClaw (Chinese)

What it does

ResearchClaw (Chinese) is a localisation and orchestration wrapper around AutoResearchClaw that exposes a 23-stage autonomous research pipeline in Chinese. Given a research topic it helps set up prerequisites, run staged experiments (simulated or sandboxed), gather and analyze results, generate paper drafts, run multi-agent peer review, and verify citations. The skill provides CLI helpers for setup, configuration, run monitoring, diagnosis, and recovery — and is explicit about what it cannot do (e.g., start system Docker daemon or provide LLM API keys).

When to use it

Use this skill when you want an agent to run an end-to-end research workflow in Chinese: setting up environment dependencies, interactively creating a config.yaml, executing the 23-stage pipeline, monitoring progress, diagnosing failures, and exporting papers. It supports simulated runs for quick iteration or sandbox/remote execution for real experiments.

What's included

• Scripts: Yes — prerequisite checks and run helpers under scripts/ (has_scripts=true).
• References: No separate references/ directory in this skill.
• Instructions: Detailed command list (/researchclaw:setup, /researchclaw:config, /researchclaw:run, /researchclaw:status, /researchclaw:diagnose, /researchclaw:resume, /researchclaw:validate) and explicit guidance on validation, recovery, and common failure modes.

Compatible agents

This skill targets coding-capable agents and CLI-execution environments (Claude Code, Copilot-like agents, Cursor, Codex, and other agents able to run bash/python helpers). It assumes Python 3.11+, Docker and LaTeX availability for full functionality.