wangzhuc
25d6a44082
feat: add article content extraction with anti-scraping fallback
...
- New `scripts/fetch_article.py`: extract WeChat article content as Markdown
with three-level fetch strategy (requests → Playwright → manual HTML)
- Refactor `learn_theme.py` to reuse `fetch_article.fetch_html()`, removing
duplicate fetch logic
- Update SKILL.md: add "学习这篇文章/导入范文" auxiliary function
- Update README.md: add article extraction to feature table and directory tree
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 16:34:13 +00:00
ystyleb
6e0ff85f30
feat: add Gemini image generation support
2026-04-01 13:05:13 +08:00
wangzhuc
62d7af9d7c
docs: add learn-theme to README
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 12:37:47 +08:00
wangzhuc
09f7034794
refactor: align README and SKILL.md, add self-check feature
...
- Add article self-check ("检查一下"): generation report + quality advice
- Record enhance_strategy in history.yaml
- Replace Zhuque test data with persona style descriptions in README
- Update descriptions: anti-AI focus → content quality focus
- Remove stale parameter optimization references
- Sync all trigger words across README, auxiliary functions, and Step 8.3
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 16:20:17 +08:00
wangzhuc
45c020727b
feat: add content enhancement strategies and 2 new frameworks
...
- Add content-enhance.md with 4 strategies matched by framework type:
angle discovery (hot-take/opinion), density boost (pain-point/list),
detail anchoring (story/retro), real-feel injection (comparison)
- Add 2 new frameworks: pure-opinion (F) and retrospective (G), now 7 total
- Integrate Step 3.3 content enhancement into SKILL.md pipeline
- Remove parameter optimization loop (low ROI, deprioritized)
- Update README: reframe from anti-AI detection to content quality
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 16:20:17 +08:00
wangzhuc
85efd10fa8
fix: sync README and SKILL.md after session changes
...
- README: remove hardcoded line count, add Step 4.6 快速自检 to workflow,
update humanness_score description with calibration layer
- SKILL.md: fix closing_style → closing_tendency in diagnostic check,
fix error handling table to match Step 5's 2-round limit
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 00:14:31 +08:00
wangzhuc
15a5adbd48
chore: update README with exemplar system docs, bump VERSION to 1.3.2
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 22:59:14 +08:00
wangzhuc
70bfca61b0
docs: sync README with restructured writing-guide and new features
...
Update references from "7层去AI" to "3层反检测", "9项自检" to "14项",
add diagnose.py to directory tree, add "优化参数" to quick start.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 20:11:01 +08:00
wangzhuc
5fb20083af
refactor: remove optimize_loop.py, replace with agent-driven optimization
...
optimize_loop.py was framework-only (needed external LLM API). The
optimization is now an auxiliary function in SKILL.md driven by the
already-running agent. All references updated across README, CLAUDE.md,
diagnose.py, and writing-config.example.yaml.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 19:58:20 +08:00
wangzhuc
f1e9c084d9
feat: add version tracking and update mechanism
...
- Add VERSION file (1.2.0)
- SKILL.md Step 1: auto-check for updates on each run
- SKILL.md: add "更新" auxiliary function (git pull)
- README: install via git clone instead of cp/ln
- build_openclaw.py: include VERSION in dist
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 15:20:44 +08:00
wangzhuc
c7701a8733
docs: add diagnose command to README
2026-03-30 14:46:59 +08:00
wangzhuc
4c842c4a08
README 更新:OpenClaw 安装方式 + 目录结构补充 build_openclaw
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 13:07:48 +08:00
wangzhuc
7c2dc4adc9
README 更新:新增小绿书、预检、image-post 命令
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 01:36:10 +08:00
wangzhuc
d87897288d
README 新增写作人格系统 + 朱雀 benchmark 数据
...
- 新增"写作人格"章节:5 个人格 + 朱雀实测结果表
- 更新"关于 AI 检测":展示 100% AI → 10% AI 的优化路径
- 目录结构新增 personas/ 目录
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 01:00:44 +08:00
wangzhuc
eef748f9c3
README 全面更新:反映结构重构 + 素材采集 + 编辑锚点 + 优化循环
...
- 顶部流程图新增素材采集和编辑锚点环节
- 新增"关于 AI 检测"章节:诚实定位为高质量初稿生成器
- 核心能力表新增素材采集、效果复盘、风格飞轮
- 目录结构反映重构后的 references/(新增 onboard/learn-edits/effect-review)
- 目录结构新增 humanness_score.py 和 optimize_loop.py
- 工作流程图与 SKILL.md Step 1-8 对齐(去掉 .5/.75 编号)
- 新增"优化循环"章节介绍 autoresearch 风格调优
- 快速开始新增"学习我的修改"示例
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 00:04:15 +08:00
wangzhuc
40bc8a1ceb
修复排版升级与 workflow 的兼容问题 + 更新 README
...
兼容修复:
- style-template.md 主题列表从 4 → 16,新增 gallery 提示
- writing-guide.md "客户" → "用户"(单用户模式残留措辞)
- SKILL.md description 新增主题画廊/容器语法触发词
- SKILL.md Step 4 新增容器语法说明(:::dialogue/timeline/callout/quote)
- SKILL.md Step 7 新增 converter 自动修复说明(CJK/脚注/暗黑/列表)
- SKILL.md Step 8 新增"看看有什么主题"/"换主题"用户操作
- SKILL.md Onboard 主题选问新增 gallery 命令提示
- wechat-constraints.md 新增第 8 节"WeWrite 自动修复"
- README 完整更新:排版引擎章节、16 主题分类表、容器语法示例、gallery 命令
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 22:58:32 +08:00
wangzhuc
d4ca5ba9ef
更新 README:反映单用户模式重构 + 7层去AI体系 + OpenClaw 兼容
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 22:39:19 +08:00
wangzhuc
ec4a646359
Rename media-agent → WeWrite
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 22:18:38 +08:00
wangzhuc
1ab34fa450
Initial release — 公众号文章全流程 AI Skill
...
热点抓取 → 选题 → 框架 → 写作 → SEO → 视觉AI → 排版 → 微信草稿箱,
一句话触发完整流程。适用于 Claude Code skill 格式。
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 22:16:18 +08:00