Humanize (Chinese copy optimizer)

What it does

Humanize is a focused optimization pipeline that takes a Chinese communication task or draft and iteratively improves it to sound more natural and human. It bootstraps a local runtime, generates baseline and challenger drafts, scores candidates with a local reranker, and produces a visible report with scores and decisions.

When to use it

Use when you need to improve Chinese copy for customer messages, social media posts, emails, WeChat replies, or other short-form communications and want a defensible, scored rewrite rather than a single manual edit. Trigger examples: "make this message sound more human in Chinese", "rewrite my WeChat reply to sound natural".

What's included

• Scripts: multiple helper scripts and a main entrypoint (humanize.py) for running end-to-end optimization, plus bootstrap and scoring scripts as documented in SKILL.md.
• References: scoring presets and strategy files are referenced in the documentation.
• Instructions: SKILL.md provides strict invocation rules, the preferred one-line CLI (python3 humanize.py --text "..." --output-root ./runs), and non-negotiable behavior for relaying final outputs and handling timeouts. It documents inputs, default assumptions, and how to interpret the generated reports.

Compatible agents

Intended for local execution with Python (requires python3) but callable by agents that can run shell commands; suitable for CoPaw/OpenClaw, Claude Code, or any agent that can run the documented CLI.