skills/full/xhs-longform-private-publisher/SKILL.md
This skill should be used when the user wants to publish an existing Markdown article to Xiaohongshu as a private longform post, keep the original wording and structure, insert inline images in order, use one-click layout, and verify the result in note manager.
npx skillsauth add cnfjlhj/ai-collab-playbook xhs-longform-private-publisherInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
这个 skill 面向“已有原文、已有配图、不要改写、直接发布”的场景。
它的核心目标不是重新创作小红书文案,而是把现成的 Markdown 长文尽量无损地搬到小红书长文编辑器里,按图片占位顺序插图,使用“一键排版”,并默认以“仅自己可见”的方式发布,再做一次可视化验收。
如果用户要的是“帮我改写成更像小红书的风格”“帮我做封面卡片”“帮我生成图文卡片”,优先使用 xhs-note-creator;这个 skill 更适合“忠实发布现有长文”。
Markdown 文件而不是最终可直接上传的图片卡片最少需要以下输入:
<markdown_path>:原文 Markdown 文件<image_dir> 或 <image_paths...>:正文插图,顺序与文中的图片占位一致常见可选项:
https://creator.xiaohongshu.com/publish/publish?target=article优先使用内置脚本把 Markdown 转成一个稳定的 JSON 载荷:
python scripts/build_payload.py <markdown_path> --image-dir <image_dir> --output /tmp/xhs_payload.json
这个脚本会做几件事:
图片数 + 1 段1.png、2.png、10.png如果用户是显式给定图片路径列表,也可以改用:
python scripts/build_payload.py <markdown_path> --images <img1> <img2> <img3>
加载 references/xhs-longform-workflow.md 获取最新页面选择器、按钮回退策略和验收方法。
优先使用自动化脚本:
python scripts/publish_longform.py --payload /tmp/xhs_payload.json --validate-only
python scripts/publish_longform.py --payload /tmp/xhs_payload.json --publish
脚本默认行为:
仅自己可见--publish 时只走到发布前页面,便于人工验收--publish 后会在发布后自动跳转笔记管理页并截图留证核心要求:
part1 -> image1 -> part2 -> image2 -> ... -> partN如果直接贴 Markdown 导致页面出现 #、-、> 等原始符号,说明插入方式错了,应改为先转换成 HTML 再插入。
如果用脚本执行,可通过以下参数显式控制:
python scripts/publish_longform.py \
--payload /tmp/xhs_payload.json \
--visibility private \
--publish
除非用户明确要求公开,否则不要切成公开发布。
发布后回到笔记管理页,至少确认以下几点:
仅自己可见审核中 或 已发布至少保留一张截图;有条件的话,再补一张编辑页或预览页截图。
允许最多 3 次完整重试。
每次重试都要说明新的判断依据,例如:
满足以下四点才算交付:
仅自己可见scripts/build_payload.py:把 Markdown 和图片整理成稳定 JSON 载荷scripts/publish_longform.py:自动打开长文编辑器、插入正文与图片、执行一键排版、切换私密并做发布后验收references/xhs-longform-workflow.md:记录长文编辑器的实际流程、选择器经验和排错点外部检索:默认不需要;这个 skill 主要基于本地上下文和实际浏览器页面工作。
tools
小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含:根据用户的需求和提供的资料,撰写小红书笔记内容(标题+正文),生成图片卡片(封面+正文卡片),以及发布小红书笔记。
testing
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.
development
Generate a detailed, professional video content summary from timestamped subtitles/transcripts (e.g., lines starting with 00:00 / 1:23:45). Enforce strict per-segment structure (timestamp range + bold segment title + 2-paragraph body: first-person creator summary + expert 【导师评注】 critique with uncertainty handling). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless explicitly requested).
development
Use when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or archive across Codex and adjacent agent skill directories.