Skip to content
cccskills
FreePublished on GitHub

social-content

Draft posts for multiple social platforms with opening lines, body text, hashtags, and prompts for audience responses. Get platform-specific variations, visual suggestions, and follow-up ideas tailored to the topic, audience, and account style.

OriginalShow the original description

通用多平台社媒内容(单条/兜底):钩子文案、正文、标签策略和互动引导,主打**涨粉/互动/内容运营**, 支持微博/抖音/B站/知乎/公众号/X 等;平台不确定或要多平台一次成稿时的默认选择。当用户说"写条微博""发个帖子""社媒文案""发什么内容""帮我写个帖""涨粉内容""互动内容"时使用。

边界:**小红书整套笔记/图文/种草**找 xhs-note-creator;**带货转化/卖点/详情页**找 copywriting; **严格套 PAS/AIDA 框架排版**找 post-formatter。

Works withLinkedIn
See how to install

Good for

  • Adapt one topic into posts for multiple platforms
  • Draft posts that invite comments and responses
  • Compare alternative versions of a post
  • Plan visuals and follow-up actions alongside post copy

Files included (5)

  • SKILL.md5.8 KB
  • EASEL-META.md2.2 KB
  • references/content-formats.md3.1 KB
  • references/hashtag-strategy.md2.0 KB
  • references/platform-specs.md4.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

社媒内容创作

跨平台通用/兜底的社媒内容生成器。为国内平台(小红书 / 抖音 / B站 / 微博 / 公众号 / 知乎)为主、出海平台(X、LinkedIn)为辅,生成原生格式的钩子文案、正文、标签策略和互动引导。

职责边界

本 SKILL 定位是跨平台通用/兜底:多平台一次成稿、快速起草、平台不确定时的默认选择。遇到下列专精场景,交给下游 SKILL 出精品:

场景交给
小红书整套笔记(多卡片 + 去 AI 化 + caption + hashtags 全流程)xhs-note-creator
具体某条视频的分镜/口播脚本(Hook 评分、分秒计时、留存优化)video-script
落地页 / 产品页 / 详情页 / 信息流等带货转化文案(种草卖点、标题/正文/CTA + 备选)copywriting
严格套 PAS/AIDA/BAB 等框架的结构化帖子post-formatter

本 SKILL 保留完整通用能力:用户直接调它做任意平台内容都成立,不强制转下游。

输入

用户 prompt 中提供以下信息(部分可省略,SKILL 自动补全默认值):

字段说明示例
平台目标平台,可多选小红书、抖音、B站、微博、公众号、知乎(出海兜底:X、LinkedIn)
内容类型图文笔记、短视频脚本、长文、微博短博、thread、carousel图文笔记
主题帖子主题或素材一段文本或一篇文章的 URL
目标互动、引流、品牌、获客、种草、社区互动
受众关注者画像一二线城市职场女性
调性专业、轻松、犀利、种草、教育、励志种草
素材可用的图片、视频、数据无

输出

为每个目标平台输出以下结构:

1. 平台帖子正文

[钩子首行]

[正文内容]

[CTA 行动引导]

[标签]

字符数:N / 平台上限

2. 互动策略

  • 最佳发布时间
  • 发布后跟进动作(回复评论、转发等)
  • 跨平台联动计划

3. 视觉方向

  • 配图/封面/配视频描述
  • 小红书图文卡片组大纲(如适用)
  • 短视频脚本钩子(如适用)

4. 变体

  • 每个平台 2-3 个帖子变体,用于 A/B 测试或分日发布。

执行步骤

  1. 收集需求 — 从用户 prompt 提取上述输入字段。缺失字段时:有 Profile 则从中补全,无 Profile 则用通用默认值。

  2. 加载平台规范 — 根据目标平台,参照 platform-specs.md 获取字符限制、图片尺寸、发布时间、平台规则。

  3. 撰写钩子 — 参照公共源 skills/shared/references/hook-title-formulas.md,为每个平台选合适的钩子公式,写出首行。钩子决定 90% 的表现。

  4. 编排内容格式 — 参照 content-formats.md,按内容类型组织正文:

    • 小红书图文笔记 → 封面钩子 + 卡片组大纲 + 正文
    • 短视频脚本(抖音/B站/视频号)→ 钩子 + 正文 + CTA
    • 公众号/知乎长文 → 标题 + 开头 + 分段主体 + 收尾
    • 微博短博 → 140 字精华 + 话题
    • 内容复用 → 从一稿拆解为多平台素材
    • (出海兜底)X thread / LinkedIn carousel
  5. 添加标签 — 参照 hashtag-strategy.md,按平台规则选择话题层级和数量。

  6. 检查合规 — 字数用脚本校验,不靠肉眼数:把每个平台的正文喂给 python3 skills/shared/scripts/wordcount.py count(stdin 传入),读 social_count (社媒计数口径 = 中文字符 + 英文单词 + 数字串 + 标点),与 platform-specs.md 的字符上限比对,超限就据结果压缩后重数(可交给 text-condenser)。再规避违禁/限流词 (小红书/抖音尤其重要),确认话题数量符合平台规范,外链放置符合平台习惯。

  7. 去 AI + 质量门(强制,不可跳过) — 每个平台正文按 text-polisher 权威源过两道门,不达标先改再交付:

    • 去 AI 味:按 ../text-polisher/references/zh-ai-markers.md(中文,含小红书特化)+ ../text-polisher/references/phrases-to-remove.md + structures-to-avoid.md 扫描重写;AI 味自检 ≥45/50。
    • 综合质量:按 text-polisher 通用五维(清晰/节奏/真实/价值密度/语气匹配)自评 ≥35/50。
    • 两门都过才进下一步;这是本 SKILL 唯一的内容质量闸,别省。
  8. 生成变体 — 为每个平台输出 2-3 个帖子变体。

  9. 输出 — 按「输出」章节的格式交付全部内容,写入 outputs/ 目录。

Profile 感知

有 Profile 时

从 === EASEL ACCOUNT PROFILE === 上下文中提取:

  • platform — 锁定目标平台,加载对应规范
  • audience — 用于调整用语和深度
  • tone / style — 匹配账号一贯风格
  • hashtag_sets — 优先使用账号常用标签
  • posting_schedule — 用于推荐发布时间

无 Profile 时

  • 退回通用模式:询问用户目标平台,使用通用最佳实践
  • 在输出末尾附注:"如提供账号 Profile 可获得更精准的平台适配和风格匹配"

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ai-image-gen

FreeSummary

Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.

  • Generating an illustration from a written description
  • Changing an image's background using instructions
  • Creating several variations of an existing image
ZJU-REAL/Easel4KUpdated Oct 21, 2026

ai-music

FreeSummary

Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.

  • Generating background music for a vlog intro
  • Creating instrumental music to match a social post
  • Generating a sung track from supplied lyrics
ZJU-REAL/Easel4KUpdated Oct 21, 2026

ai-video-gen

FreeSummary

Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.

  • Generate a short video from a scene description
  • Animate a still image
  • Create character motion from a starting image
ZJU-REAL/Easel4KUpdated Oct 21, 2026

asset-manager

FreeSummary

Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.

  • Organizing generated assets by date, platform, and type
  • Finding past content through keywords and tags
  • Listing assets for a specific account or platform
ZJU-REAL/Easel4KUpdated Oct 21, 2026

audio-denoise

FreeSummary

Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.

  • Reducing fan or air conditioner noise in recordings
  • Cleaning speech in podcasts and interviews
  • Reducing noise in a video's audio track
ZJU-REAL/Easel4KUpdated Oct 21, 2026

audio-editing

FreeSummary

Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.

  • Trim a recording to the section you need
  • Convert audio formats and match loudness
  • Extract audio from a video
ZJU-REAL/Easel4KUpdated Oct 21, 2026

See all skills by ZJU-REAL

Report a problem with this skill