Agent skill

Skill Content Gap Analysis

by ZJU-REAL in ZJU-REAL/Easel

分析社媒赛道的内容空白,发现高需求低竞争的蓝海选题机会. An agent skill from ZJU-REAL/Easel.

Apache-2.0Auto-check passedMarketing & SEO

Install Skill Content Gap Analysis

skills CLI
$ npx skills add ZJU-REAL/Easel --skill skill-content-gap-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel skill-content-gap-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/skill-content-gap-analysis .claude/skills/skill-content-gap-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-content-gap-analysis
GitHub stars
3.3k
Token cost
~948 tokens
SKILL.md length
212 words
Files
4 (incl. references)
Skills in repo
113
Repo updated
First seen
Licence
Apache-2.0

At a glance

分析社媒赛道的内容空白,发现高需求低竞争的蓝海选题机会. An agent skill from ZJU-REAL/Easel.

  • Works in 8 steps: 采集平台实时热点 → 挖掘搜索联想词 → 扫描评论区未满足需求 → …
  • Tasks that involve Competitor analysis
  • SKILL.md covers 输入, 输出, 执行步骤 and 重要原则, plus 1 more section
  • Reaches 60s.viki.moe and v2.xxapi.cn

What it does

Skill Content Gap Analysis is an agent skill from ZJU-REAL/Easel. 分析社媒赛道的内容空白,发现高需求低竞争的蓝海选题机会。 当用户说"蓝海选题""内容空白""没人做的选题""选题机会""高需求低竞争""差异化选题""内容缺口"时使用。 和 skill-competitor-analysis 的区别:本 SKILL 从赛道供需交叉验证找蓝海选题空白; competitor-analysis 拆解具体竞品账号的内容策略。

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `EASEL-META.md`, `references/demand-signals.md` and `references/scoring-model.md`).

It sits in Marketing & SEO, covering Competitor analysis. The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Competitor analysis

Example prompts

  • “没人做的选题”
  • “高需求低竞争”
  • “/skill-content-gap-analysis”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 采集平台实时热点
  2. 挖掘搜索联想词
  3. 扫描评论区未满足需求
  4. 分析竞品账号覆盖
  5. 评估竞争程度
  6. 匹配内容形式
  7. 优先级排序
  8. 生成选题清单

What it can do on your machine

Read from SKILL.md and the folder at commit 5e0ccc1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • 60s.viki.moe
    • v2.xxapi.cn

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Content Gap Analysis loads about 948 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 212 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~948
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 5e0ccc1, republished under its Apache-2.0 licence (© ZJU-REAL). 212 words, ~948 tokens.

Download SKILL.mdSave it as .claude/skills/skill-content-gap-analysis/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
skill-content-gap-analysis
description
分析社媒赛道的内容空白,发现高需求低竞争的蓝海选题机会。 当用户说"蓝海选题""内容空白""没人做的选题""选题机会""高需求低竞争""差异化选题""内容缺口"时使用。 和 skill-competitor-analysis 的区别:本 SKILL 从赛道供需交叉验证找蓝海选题空白; competitor-analysis 拆解具体竞品账号的内容策略。
layer
discover

蓝海选题发现

扫描目标赛道在社媒平台上的内容供给与用户需求,找出"需求旺但好内容少"的蓝海选题,输出带优先级的选题清单。

输入

用户 prompt 中提供以下信息(部分可选):

  • 必需:赛道/领域(如"家居收纳"、"Python 教学"、"母婴辅食")
  • 可选:目标平台(小红书、抖音、B站、微博等,默认全平台扫描)
  • 可选:竞品账号列表(2–5 个同赛道博主)
  • 可选:自己已发布的内容方向(用于差距对比)

输出

markdown
# 蓝海选题发现: {赛道}
日期: {date}
目标平台: {平台列表}
扫描竞品: {账号列表}
发现蓝海选题数: {count}

## 摘要
{2-3 句概括最大机会方向}

## 蓝海选题清单

### 🔵 高优先(需求强 + 竞争弱)
| 选题方向 | 需求信号 | 竞争程度 | 建议平台 | 建议内容形式 | 时效性 |
|---------|---------|---------|---------|-------------|--------|

### 🟢 中优先(需求明确 + 竞争适中)
| 选题方向 | 需求信号 | 竞争程度 | 建议平台 | 建议内容形式 | 时效性 |

### ⚪ 观察池(潜在趋势 + 尚需验证)
| 选题方向 | 需求信号 | 竞争程度 | 建议平台 | 建议内容形式 | 时效性 |

## 需求信号来源
{每个选题的需求证据:热搜词、搜索联想词、评论区高频问题等}

## 竞品覆盖盲区
{竞品账号未覆盖但用户有需求的方向}

## 内容形式建议
{针对不同选题推荐的最佳内容形式:图文笔记、短视频、中长视频、直播、合集等}

## 速赢清单
{3-5 个本周可立即动手的选题 + 具体内容角度}

执行步骤

需求信号的三个来源(平台搜索联想词 / 平台热搜 / 评论区未满足需求)及其采法与降级方案,参照 demand-signals.md。三类信号交叉验证,缺一不可。

1. 采集平台实时热点

用 web_fetch 调用热搜 API(参照 hotlist-apis.md),获取各平台当前热门话题:

  • 抖音热搜:web_fetch https://60s.viki.moe/v2/douyin
  • B站热门:web_fetch https://60s.viki.moe/v2/bili(⚠️ 常 500 不稳定,挂时改用备用源 web_fetch https://v2.xxapi.cn/api/bilibilihot)
  • 微博热搜:web_fetch https://60s.viki.moe/v2/weibo
  • 知乎热榜:web_fetch https://60s.viki.moe/v2/zhihu
  • 头条热榜:web_fetch https://60s.viki.moe/v2/toutiao

从热搜列表中筛选与用户赛道相关的话题,记录热度值,作为时效性选题的候选池。

2. 挖掘搜索联想词

用 web_search 搜索赛道核心关键词,收集搜索引擎和平台的联想词(长尾需求):

  • 搜索 {赛道} site:xiaohongshu.com、{赛道} site:bilibili.com 等,观察搜索建议
  • 搜索 {赛道} + 怎么/如何/推荐/避坑/对比/教程 等需求词,发现具体用户问题
  • 收集"相关搜索"中出现的长尾词 — 这些代表真实用户需求

将搜索联想词按意图分类:学习型、决策型、问题解决型、种草型。

3. 扫描评论区未满足需求

用 web_search 找到赛道内的热门内容,用 web_fetch 抓取页面,重点分析评论区:

  • 高赞评论中反复出现的追问("求出个 XX 教程"、"能不能讲讲 XX")
  • 用户吐槽现有内容的痛点("说了等于没说"、"根本没讲到重点")
  • 提问类评论的点赞数 — 点赞越高说明需求越普遍
  • 收藏/转发远高于点赞的内容 — 说明实用但表达不够好,可以做得更好
4. 分析竞品账号覆盖

如果用户提供了竞品账号:

  • 用 web_search 搜索 site:xiaohongshu.com {竞品昵称} 或 {竞品昵称} {平台} 获取其内容列表
  • 按主题分类竞品已发布内容,画出覆盖地图
  • 找出覆盖盲区:竞品未做但用户有需求的方向
  • 找出质量洼地:竞品做了但质量差(评论区负面反馈多)的方向

如果用户未提供竞品账号:

  • 用 web_search 搜索 {赛道} 博主推荐 或 {赛道} 账号 找到头部账号
  • 抽样分析 2-3 个头部账号的内容覆盖
5. 评估竞争程度

对每个候选选题评估内容供给情况:

  • 用 web_search 搜索该选题,观察结果数量和质量
  • 蓝海信号:搜索结果少于 10 条相关内容、结果质量参差不齐、没有头部博主覆盖、内容陈旧(半年以上未更新)
  • 红海信号:大量高质量内容、多个头部博主已覆盖、内容更新频繁
  • 伪蓝海:搜索结果少但用户需求也弱 — 需要交叉验证需求信号
6. 匹配内容形式

根据选题特征和平台属性推荐最佳内容形式:

选题类型小红书抖音B站微博
教程/攻略图文合集短视频中长视频长图文
测评/对比图文笔记短视频中长视频投票+图文
避坑/经验图文笔记口播短视频中长视频话题帖
种草/推荐图文笔记好物分享合集视频九宫格图文
热点解读图文笔记短视频时评视频评论/转发
7. 优先级排序

按加权评分排列每个选题,参照 scoring-model.md:

因素权重评估方法
需求强度30%搜索联想频次、评论区追问数、热搜相关度
竞争空白25%现有内容数量少、质量差、更新慢
赛道匹配20%与用户定位和受众的契合度
制作成本15%能否用现有素材和能力快速产出
时效价值10%是否有热点借势窗口或季节性机会
8. 生成选题清单

输出按优先级分级的蓝海选题清单 + 3-5 个速赢行动项。每个速赢必须包含:具体选题、目标平台、内容形式、核心角度。

重要原则

  • 需求验证优先 — 蓝海选题必须有真实需求信号支撑,不是"没人做"就等于"蓝海"
  • 竞争弱 ≠ 没人做 — 有人做但做得不好,比完全没人做更好,说明需求已验证
  • 平台差异化 — 同一选题在不同平台的竞争程度可能完全不同,逐平台评估
  • 避免伪蓝海 — 搜索结果少 + 评论区无相关讨论 = 可能根本没需求
  • 先速赢后深耕 — 优先推荐制作成本低、见效快的选题,建立正反馈
  • 不追所有热点 — 热点只有与赛道契合时才有价值,硬蹭热点不可持续

Profile 感知

  • 有 Profile 时:
    • 读取 platforms.md,聚焦用户实际运营的平台,优先分析这些平台的内容空白
    • 读取 identity.md,匹配用户的内容定位和专业优势,过滤超出能力范围的选题
    • 读取 audience.md,锁定目标受众的需求场景,在评论区分析中重点关注该人群的追问
    • 结合 Profile 中的内容风格偏好,在内容形式建议中优先推荐用户擅长的形式
  • 无 Profile 时:
    • 退回通用模式,要求用户提供赛道信息
    • 全平台扫描,不做平台特化分析
    • 附注"如提供账号 Profile 可获得更精准的选题方向和平台匹配"

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/openclaw/skill-content-gap-analysis of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md
  • references/demand-signals.md
  • references/scoring-model.md

Open the folder on GitHubat commit 5e0ccc1

Compare with similar skills

Skill Content Gap Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Content Gap Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Content Gap Analysis this skillZJU-REAL/Easel3.3k—~948Automated safety check: PassApache-2.0
SEO Content Brief GeneratorAgriciDaniel/claude-seo19k2 repos~2.6kAutomated safety check: PassMIT
SEO DataforseoAgriciDaniel/codex-seo7972 repos~4.6kAutomated safety check: PassMIT
Competitor ProfilingNexus-JPF/note-companion8704 repos~3.5kAutomated safety check: PassMIT
Startup Competitorsferdinandobons/startup-skill1.2k—~4.1kAutomated safety check: PassMIT
Amazon Listing Competitor Analysisbrowser-act/skills6.1k1 repos~3.2kAutomated safety check: PassMIT

Similar skills

  • SEO Content Brief Generator

    AgriciDaniel/claude-seo

    Builds research-backed SEO content briefs with competitor scoring, per-section word counts and page-type templates, for new pages or improving existing ones.

    19k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed
  • SEO Dataforseo

    AgriciDaniel/codex-seo

    Live SEO data via DataForSEO MCP server. An agent skill from AgriciDaniel/codex-seo.

    797 GitHub starsUsed in 2 repos~4.6k tokens
    Marketing & SEOAuto-check passed
  • Competitor Profiling

    Nexus-JPF/note-companion

    When the user wants to research, profile, or analyze competitors from their URLs.

    870 GitHub starsUsed in 4 repos~3.5k tokens
    Marketing & SEOAuto-check passed
  • Startup Competitors

    ferdinandobons/startup-skill

    Deep competitive intelligence for any market. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~4.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Analyzes a competitor's Amazon listing by ASIN with BrowserAct data extraction, then reports what it does well, where the market has gaps and opportunity points for your own listing.

    6.1k GitHub starsUsed in 1 repo~3.2k tokens
    Marketing & SEOAuto-check passed
  • SEO Competitor Comparison Pages

    AgriciDaniel/claude-seo

    Generates X vs Y comparison pages, alternatives-to-X pages, best-tools roundups and feature-matrix tables, with schema markup and verifiable data rules.

    19k GitHub starsUsed in 5 repos~1.9k tokens
    Marketing & SEOAuto-check passed

More from ZJU-REAL/Easel

All 113 skills in this repo
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.3k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.3k GitHub stars~657 tokensUpdated today
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.3k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.3k GitHub stars~643 tokensUpdated today
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Paper Explainer

    ZJU-REAL/Easel

    科研论文解读:解析 arXiv/PDF 的公式与图表,提炼问题、贡献、方法、关键图和结论,再产出 B站/视频号解读视频或知乎/公众号图文。

    3.3k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Skill Content Gap Analysis

What does Skill Content Gap Analysis do?

分析社媒赛道的内容空白,发现高需求低竞争的蓝海选题机会. An agent skill from ZJU-REAL/Easel. Skill Content Gap Analysis is an agent skill from ZJU-REAL/Easel.

When should I use Skill Content Gap Analysis?

Skill Content Gap Analysis fits situations like: tasks that involve Competitor analysis.

How do I install Skill Content Gap Analysis in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill skill-content-gap-analysis -a claude-code`. Or copy the skill folder (skills/openclaw/skill-content-gap-analysis in ZJU-REAL/Easel) into .claude/skills/skill-content-gap-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Skill Content Gap Analysis in Codex?

Run `npx skills add ZJU-REAL/Easel --skill skill-content-gap-analysis -a codex`. Or copy the skill folder (skills/openclaw/skill-content-gap-analysis in ZJU-REAL/Easel) into .agents/skills/skill-content-gap-analysis in your project. Codex loads it when a task matches its description.

Can I use Skill Content Gap Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill skill-content-gap-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-content-gap-analysis, .gemini/skills/skill-content-gap-analysis, .github/skills/skill-content-gap-analysis and .opencode/skills/skill-content-gap-analysis in your project.

What does Skill Content Gap Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Content Gap Analysis is instructions for the agent only. Our summary lists: Python 3.

Does Skill Content Gap Analysis access the network?

SKILL.md names 2 domains. In commands or code: 60s.viki.moe and v2.xxapi.cn; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Skill Content Gap Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Content Gap Analysis use?

Skill Content Gap Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Content Gap Analysis use?

About 948 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Skill Content Gap Analysis?

Skills that share tags, products or a category with Skill Content Gap Analysis: SEO Content Brief Generator (AgriciDaniel/claude-seo, 19k stars), SEO Dataforseo (AgriciDaniel/codex-seo, 797 stars), Competitor Profiling (Nexus-JPF/note-companion, 870 stars) and Startup Competitors (ferdinandobons/startup-skill, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Content Gap Analysis?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,310 GitHub stars. The repository holds 113 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.