soia-media-publish-rednote-card

soia-media-publish-rednote-card

Rewrite compose the finished draft produced by into note copy suitable for rednote (Xiaohongshu). By default, deliver Markdown text in the reply for the client to copy and publish manually; this skill does not call the rednote API, does not send automatically, and does not modify the original draft.

Client-readable description

What this skill can do

Extract one clear sharing angle from the article and organize it into a note suited for quick mobile reading: a title with an informational promise, 3–5 short paragraphs, relevant topic hashtags, and image suggestions that match the content.

The client wants	The skill will do	The client can see
Post an article as a Xiaohongshu note	Extract the angle, rewrite the title and short paragraphs, add hashtags	A copy-ready rednote Markdown text
Needs visual asset direction	Give suggestions for the subject, composition, text, and aspect ratio of the cover/image	Actionable image suggestions; can connect to soia-media-generate-article-image
Publish to rednote	Generate publishable text only	"Produce text, publish manually"; will not call an API or publish content

How the client uses it

1. Say "post to Xiaohongshu", "Xiaohongshu note", or "rednote this", and provide the finished draft, file content, or path.
2. If requested, also specify the target readers, account tone, prohibited words in the title, whether to highlight method/checklist/story, and the desired image style.
3. The Agent first determines a single sharing angle, then outputs the title, body, hashtags, and image suggestions; by default it does not overwrite the original draft, and saves separately only when the client specifies a path.
4. The client manually copies the copy, prepares images, and publishes to rednote; this skill does not operate the platform backend on their behalf.

Dependencies and installation

Installation (recommended: install the entire domain plugin to install all skills in this repo at once):

claude plugin marketplace add soia-team/soia-open-skills

claude plugin install soia-media-content@soia

If you only want this one skill, you can use the npx route. Note that the skill will land in the shared source of truth ~/.agents/skills; if the plugin is also installed, the same skill will appear in two indexes and they will drift separately, so it is recommended to choose one:

npx skills add soia-team/soia-open-media-content-skills -g -a '*' -s soia-media-publish-rednote-card -y

• This skill is a pure LLM rewriting process, with no scripts, no private configuration, no account credentials, and no rednote API dependency.
• soia-media-generate-article-image is an optional connecting skill: if you need to generate a cover or inline bitmap, install and run it first; this skill only provides image direction and does not generate or upload images for the client.
• soia-media-compose-article-draft is a common upstream artifact, but it is not an installation-level hard dependency; you can also directly provide any finished draft.
• Currently no rednote API integration. Any "publish" only means generating text, and manual publishing is done by the client.

WorkBuddy The loading unit of is a role-based expert rather than a plugin,npx skills add -a '*' cannot cover it, and it needs to be installed separately, see docs/install/workbuddy.md。

Logs and completion receipt

Every execution must report the actual processing scope, the number of titles/paragraphs/hashtags, and the manual publishing boundary, and must not describe "generated" as "published". Minimum format:

完成：已将 <输入范围> 改写为 rednote 笔记文本，未调用平台 API。

日志摘要：
- started: <输入来源、目标读者与分享角度>
- processed: <标题 1 个、正文 3–5 段、标签数量、配图建议数量>
- created/updated: <回复文本或客户指定的输出位置>
- skipped/failed: <未处理内容及原因；没有则写“无”>

验证：
- <标题吸引力与事实一致性、段落数量、标签相关性、配图建议核对结果>

问题与下一步：
- 请客户人工复制文案并准备图片后发布；<其它问题，没有则写“无”>

Rewriting rules

1. First define one sharing angle

• Choose an angle from the original draft that readers can immediately understand: solve a problem, avoid a pitfall, review an experience, or provide a set of methods.
• The title, body, tags, and accompanying images must revolve around the same angle; do not compress the entire article into a list of unrelated viewpoints.
• Preserve the original draft's facts, qualifying conditions, and verifiable sources; do not add numbers, cases, citations, or effect promises that are not supported by the input.
• If the original draft has multiple equally important themes, first ask the client to choose; when risk is low, choose the clearest main line and explain it in the receipt.

2. Title

• Generate 1 main title, and if necessary attach 2 alternative titles for the client to choose from; the main title must have a specific information promise or scenario conflict, avoiding vague "sharing useful tips."
• A small number of semantically relevant emoji may be used, but emoji cannot replace keywords, nor can exclamation marks, exaggerated benefits, or false authority be stacked.
• The title accurately reflects the body, not clickbait-style promises of results the body does not provide; comply with the client-provided platform prohibited words and brand restrictions.

3. Body and Tags

• Keep the body to 3–5 short paragraphs, with each paragraph expressing only one information point; at the beginning, explain the scenario/pain point as soon as possible, in the middle provide methods or evidence, and at the end conclude and guide interaction.
• Use short sentences that are easy to read on mobile, moderate line breaks, and specific examples; retain necessary technical terms, but explain terms the first time they appear.
• Place topic tags after the body, usually giving 5–10 tags directly related to the theme; gradually narrow from broad topics to specific questions, and do not add irrelevant trending tags to chase traffic.
• If the user does not provide an account tone, adopt a sincere, specific, and verifiable sharing tone; do not impersonate personal experience, and do not claim to have personally used products or methods that were not provided.

4. Image Suggestions

• Give at least 1 cover suggestion, explaining the main visual subject, composition, primary color, text hierarchy, and recommended ratio; suggestions may be made for a 1:1 Xiaohongshu square-image scenario.
• When the article has steps, comparisons, or checklists, add 1–3 inner-page card suggestions, stating the single piece of information each card carries.
• The titles, numbers, and sources in the suggestions must be consistent with the copy; do not place unverified facts in image text.
• When the client needs actual images, explain that the suggestions can be handed to soia-media-generate-article-image, but do not claim that images have been generated, uploaded, or published.

Output Format

The default output is Markdown:

## 标题
<吸睛标题，可带少量 emoji>

## 正文
<第 1 段>

<第 2 段>

<第 3–5 段>

## 话题标签
#主题标签 #具体问题 #方法标签

## 配图建议
- 封面：<主体 / 构图 / 配色 / 文字 / 比例>
- 内页 1：<单一信息点；没有则省略>

Outside the list, you may attach explanations of factual trade-offs, prohibited words, or image-text connections. When the client does not specify a save location, produce only the reply text; when a location is specified, then write to a separate draft file, and never overwrite the source file. Do not output fake "published" links or API results.