# imraywang/wewrite

公众号内容全流程 Skill，从热点抓取到微信草稿箱，一句话跑完整条内容管道

Repository: https://github.com/imraywang/wewrite
Canonical: https://ross.abutalabs.com/products/wewrite
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-24T03:18:32+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 93, longevity 11
- inputs: {"age_days": 160, "days_push": 9, "days_rel": 48, "gap_med": 1.0, "n_releases_24m": 3}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3182, forks 511 (observed 2026-08-28T04:07:47.817174+00:00)

## What it is
WeWrite is a Python-based AI agent skill that automates the full WeChat Official Account content pipeline: topic selection from trending news, research gathering, style-persona-driven drafting, editorial review, optional AI image generation, WeChat-compatible HTML formatting with 18 themes, and pushing to the WeChat draft box. It works with agents like Claude Code and Codex via a main entry skill plus nine modular sub-skills.

## Use cases
- write a WeChat official account article from one prompt
- automate topic selection and research for公众号 posts
- format articles into WeChat-compatible HTML themes
- push finished articles to the WeChat draft box
- rewrite one article for Xiaohongshu or Douyin
- learn my writing style from my edits
- generate cover images for WeChat articles

## When to choose
- you publish regularly on WeChat Official Accounts and want an end-to-end AI content pipeline
- you use an AI agent like Claude Code and want modular topic/writing/formatting/publishing skills
- you want consistent personal writing style that improves from your edits
- you need WeChat-compatible inline-styled HTML formatting with multiple themes

## When to avoid
- you don't publish to WeChat Official Accounts or Chinese social platforms
- you need fully manual editorial control over every step
- you can't grant API access to WeChat draft publishing
- you want a general-purpose blog or CMS rather than a WeChat-focused pipeline

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, web-scraping, nlp, templating, workflow-automation, image-processing
- domain: large-language-models, media, social-media, developer-tools
- platform: python, cli, cross-platform
- tags: wechat-official-account, content-pipeline, ai-writing, claude-code-skill, draft-publishing, style-learning, multi-platform-rewriting, ai-agents, natural-language-processing, automation

## Member repositories
- imraywang/wewrite (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.817174+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:25:03.219799+00:00, confidence not recorded.
  - readme: https://github.com/imraywang/wewrite (fetched 2026-08-28T04:07:47.817174+00:00, sha ed6030240bfa)
  - registry_pypi: https://pypi.org/pypi/wewrite/json (fetched 2026-08-29T09:39:05.774041+00:00, sha 21c99ec9b282)
- Data as of 2026-08-30T08:39:29.467469+00:00.