# Annotate Classical Chinese corpora with HanLP

> Produce reviewable token, lemma, POS and dependency annotations for Classical Chinese passages with HanLP’s dedicated Ancient Chinese model.

- Skill: `agentskillexchange/annotate-classical-chinese-corpora-with-hanlp` (Agent Skill)
- Install (CLI): `npx get-skill add agentskillexchange/annotate-classical-chinese-corpora-with-hanlp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/annotate-classical-chinese-corpora-with-hanlp/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/agentskillexchange/annotate-classical-chinese-corpora-with-hanlp

---


# Annotate Classical Chinese corpora with HanLP

Produce reviewable token, lemma, POS and dependency annotations for Classical Chinese passages with HanLP’s dedicated Ancient Chinese model.

## Prerequisites

Python, pip, HanLP 2.1.1, compatible PyTorch environment, upstream Ancient Chinese model resources; optional GPU

## Installation

Install or set up from the source-backed instructions:

Create an isolated Python environment; run python -m pip install hanlp==2.1.1 with a compatible PyTorch stack. Load hanlp.pretrained.mtl.KYOTO_EVAHAN_TOK_LEM_POS_UDEP_LZH; first load downloads model resources. Check model licensing before use and run the upstream two-sentence demo before processing operator data. No MCP server or hosted API is required.

- Source: https://github.com/hankcs/HanLP

## Documentation

- https://hanlp.hankcs.com/docs/api/hanlp/pretrained/mtl.html#hanlp.pretrained.mtl.KYOTO_EVAHAN_TOK_LEM_POS_UDEP_LZH

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/annotate-classical-chinese-corpora-with-hanlp/)

