aws-wechat-article-writing

github:aiworkskills/wechat-article-skills · first committed 2026-04-06 · source · badge

公众号写稿|长文写作|文章润色|改写续写 — 公众号长文 AI 写作,从话题或提纲生成完整初稿,支持改写、续写、润色、开头结尾优化,可调 DeepSeek / GPT / Claude 或由 Agent 代写。面向自媒体作者、公众号运营、品牌文案。触发词(**单独触发仅限对已有稿子的修改**):「改写」「润色」「续写」「ç

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

20 commits to this file on GitHub (newest first).

2026-09-11 · commit becf19d · fix(writing): 加粗密度改按字数算;偏长阈值 8→12
2026-09-11 · commit 773f716 · refactor(writing): SKILL.md 只留主路径,分支挪进 branches.md;加粗规则收成一份
2026-09-11 · commit 1a7fdc6 · refactor(main): SKILL.md 只留主路径,配置检查回归首次引导,分支移入 branches.md
2026-09-10 · commit 90eae5f · feat(writing): 产出配额做成能跑的检查;加粗验收标准改为「串起来像不像提要」
2026-09-10 · commit 1dac256 · fix(writing,images): 加粗要挑对东西;导语与摘要字段分工;取证说明不许当生图 prompt
2026-09-10 · commit 3ac2d21 · fix(main,writing,images): 补上三篇实测暴露的四个执行缺口
2026-09-10 · commit a9db206 · fix(writing,images): 配图数量、产出配额与媒介选法
2026-09-07 · commit 2032fb8 · feat(formatting): 带破折号出处的引用排成金句卡,不用扩展 markdown 标记
2026-09-07 · commit 2907e15 · fix(formatting/writing): 渲染器补齐标准 markdown;语法要求写进写作提示词
2026-09-05 · commit f7318e8 · fix(skills): 统一 Python 解释器为 {python} 占位符,补 Windows 探测
2026-05-06 · commit 14844e3 · 给审稿流程补上必须用 write.py strip-citations 去掉正文里「资料路径」标注再定稿 article.md,并把写作 skill 限定为只出带溯源的 draft.md,同时删了首次配置文档里 aiworkskills 预设「快速通道」那段说明。
2026-04-24 · commit 01e45ee · docs: 引入 products/{产品名}/ 业务资料库的读+写双向规则
2026-04-23 · commit c11a670 · clawhub 所有安全检查全绿
2026-04-22 · commit 476236b · 优化触发词的撞车问题
2026-04-22 · commit 5d33fd0 · chore: 强化 skill 描述与套件完整性校验;支持 .aws URL 导入
2026-04-10 · commit 1ff7788 · chore: 更新各 skill 文档与脚本;新增排版 skill 包与封面预设参考
2026-04-08 · commit 3a5e55f · chore: 更新技能文档、write.py 与 .gitignore(忽略 .workbuddy)
2026-04-06 · commit 454c18c · chore: 更新多子技能 SKILL 与 write.py
2026-04-06 · commit 3c5840e · chore: 更新各子技能脚本、SKILL 与配置示例(排版/写作/生图/发布/校验)
2026-04-06 · commit b9fc4ac · Initial commit

Archived snapshots