← Back to Skills Marketplace
Simple CSC
by
Jacob-Zhou
· GitHub ↗
· v1.0.1
· MIT-0
142
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install simple-csc
Description
Use the simple-csc repository to perform Chinese Spelling Correction (CSC) and Chinese Character Error Correction (C2EC) using large language models in a tra...
Usage Guidance
This skill is a usage guide that expects you to clone and run the external simple-csc repository. Before installing or running anything: (1) review the GitHub repository (https://github.com/Jacob-Zhou/simple-csc) yourself — this skill only points to that code; (2) expect large model downloads (HuggingFace) and significant GPU/VRAM use; (3) pip-installing native libs (e.g., flash-attn) will compile code on your machine—review and build in a controlled environment if concerned; (4) the API server examples bind to localhost (127.0.0.1) which is safe for local use, but avoid exposing the server to the public internet without proper access controls; and (5) if you must use alternative model mirrors (MODELSCOPE_CACHE), ensure you trust the mirror source. Overall the instructions are coherent with the skill's purpose, but the real code and runtime behavior live in the external repository — inspect that repo before running.
Capability Analysis
Type: OpenClaw Skill
Name: simple-csc
Version: 1.0.1
The skill bundle provides a comprehensive guide and API reference for the 'simple-csc' Chinese Spelling Correction tool. It includes instructions for environment setup, model usage, and running evaluation experiments. While it involves executing shell scripts and cloning a GitHub repository (Jacob-Zhou/simple-csc), these actions are standard for the tool's stated purpose and no evidence of malicious intent or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the instructions. All requested actions (clone repo, install Python deps, download LLMs from HuggingFace, run scripts and an API server) are exactly what a CSC/C2EC toolkit would need.
Instruction Scope
SKILL.md restricts itself to repository-relative paths, model/dataset download and running provided scripts/APIs. It does not instruct reading unrelated system files or harvesting credentials. It does recommend setting MODELSCOPE_CACHE (optional) and shows how to run a local API server bound to 127.0.0.1.
Install Mechanism
This is an instruction-only skill (no install spec). The instructions clone a public GitHub repo and use pip for dependencies (including compiling native packages such as flash-attn). That is standard for ML projects; there are no opaque download URLs or archive extracts in the skill content itself.
Credentials
The skill declares no required environment variables or credentials. It optionally references MODELSCOPE_CACHE to change model mirror location and notes that models auto-download from HuggingFace. Network access to download models/datasets is expected for this purpose.
Persistence & Privilege
always is false and the skill is user-invocable. There is no instruction to modify other skills or system-wide agent configs. No elevated or persistent privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install simple-csc - After installation, invoke the skill by name or use
/simple-csc - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Version 1.0.1 of simple-csc
- Added explicit compatibility and prerequisite instructions, including GPU, Python version, and VRAM requirements.
- Clarified that this skill is a usage guide and that the simple-csc repository must be cloned locally before use.
- Noted that all file paths are relative to the repository root, improving user guidance.
- No changes to features, APIs, or behavior were made; this is a documentation update for improved clarity and onboarding.
v1.0.0
Initial release – simple-csc 1.0.0
- Provides training-free Chinese Spelling Correction (CSC) and Character Error Correction (C2EC) using large language models.
- Supports both Python API and RESTful API server for correction tasks.
- Includes configurable correction behaviors (substitution-only or full C2EC with insert/delete/reorder).
- Compatible with popular open-source LLMs (Qwen/Qwen2.5, Baichuan2).
- Offers environment setup scripts and performance optimization recommendations.
- Documentation covers quick start, configuration, recommended models, and API reference.
Metadata
Frequently Asked Questions
What is Simple CSC?
Use the simple-csc repository to perform Chinese Spelling Correction (CSC) and Chinese Character Error Correction (C2EC) using large language models in a tra... It is an AI Agent Skill for Claude Code / OpenClaw, with 142 downloads so far.
How do I install Simple CSC?
Run "/install simple-csc" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Simple CSC free?
Yes, Simple CSC is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Simple CSC support?
Simple CSC is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Simple CSC?
It is built and maintained by Jacob-Zhou (@jacob-zhou); the current version is v1.0.1.
More Skills