Agent skill

Xhs Comment Insight

by Jamailar in Jamailar/Beav

小红书评论区洞察选题技能,用于从单条笔记的评论区统计和分析追问、反驳、补充、情绪和未满足需求,生成 1 个可继续创作的小红书选题。

Custom licenceAuto-check passedMedia & Creative

Install Xhs Comment Insight

skills CLI
$ npx skills add Jamailar/Beav --skill xhs-comment-insight -a claude-code

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

GitHub CLI
$ gh skill install Jamailar/Beav xhs-comment-insight --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/Jamailar/Beav.git skills-src && mkdir -p .claude/skills && cp -r skills-src/desktop/builtin-skills/xhs-comment-insight .claude/skills/xhs-comment-insight && 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
xhs-comment-insight
GitHub stars
1.8k
Token cost
~945 tokens
SKILL.md length
131 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

小红书评论区洞察选题技能,用于从单条笔记的评论区统计和分析追问、反驳、补充、情绪和未满足需求,生成 1 个可继续创作的小红书选题。

  • Works in 6 steps: 先统计这条笔记评论区的信号:看高赞评论、回复数、追问密度、反驳点、补充信息和具体行… → 从评论里提取 2-4… → 选择一个最小切口并输出 1… → …
  • Media & Creative work in your project
  • SKILL.md covers 输入边界, 评论价值类型, 思考流程 and 质量标准, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Xhs Comment Insight is an agent skill from Jamailar/Beav. 小红书评论区洞察选题技能,用于从单条笔记的评论区统计和分析追问、反驳、补充、情绪和未满足需求,生成 1 个可继续创作的小红书选题。

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative. It works with Xiaohongshu. The repository describes itself as: 小红书 AI 运营工作台|小红书采集、评论区下载、素材库、选题、AI写作、小红书全域解决方案,开箱即用,一键安装,小红书AI工作台,自媒体素材库,AI写作+图片自动编排,小红书版OpenClaw、自媒体资产底座+AI工作台,支持小红书图文+小红书评论区下载、小红书AI创作工具、自媒体版WorkBuddy、抖音、小红书爬虫数据采集.

When your agent uses it

  • Media & Creative work in your project

Example prompts

  • “/xhs-comment-insight”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先统计这条笔记评论区的信号:看高赞评论、回复数、追问密度、反驳点、补充信息和具体行动诉求,不只看评论总数。
  2. 从评论里提取 2-4 个真实需求或矛盾:用户到底还缺什么信息、哪里不信、哪里有误解、哪里想继续行动。
  3. 选择一个最小切口并输出 1 个潜在选题:优先选具体问题、具体场景、具体人群,不要做“评论区都在问什么”这种大题。
  4. 让原笔记退到背景位:content_direction 必须说明“评论区里哪个信号触发了选题”,而不是只说原文主题。
  5. 不跨素材组合,不输出多个方向。
  6. 标题先按 xhs-title 的小红书标题逻辑内部筛选,最终 JSON 只输出一个 20 字以内标题。

What it can do on your machine

Read from SKILL.md and the folder at commit f35befd. 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 json).

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

  • Network

    No URLs in SKILL.md.

    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

Xhs Comment Insight loads about 945 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 131 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~945

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 131 words (~945 tokens).

“用于选题中心和 AI 聊天的评论区洞察,也可作为 AI 对话选题编排器的一种方法。选题中心宿主负责随机提供本轮 1 条带评论的小红书素材和评论摘录;AI 聊天中,用户可以直接提供或指定 1 条小红书笔记及评论素材,外层编排器也可以先从知识库选择一条带评论素材。本技能负责统计、分析这条笔记评论里真正值得二次创作的内容机会。”

— opening of SKILL.md by Jamailar, Custom licence
name
xhs-comment-insight
allowedRuntimeModes
[wander, redclaw, chatroom]
hookMode
inline
autoActivate
false
activationScope
session
activationHint
当选题中心随机挑取一条小红书笔记,并要求分析这条笔记评论区后产出潜在选题时,加载本技能;在 AI 聊天中,当用户明确要求“评论区洞察”、分析一条小红书笔记的评论、从评论里找选题、或 content-topic-miner 需要使用“评论需求洞察”作为一种选题方法时,也可调用…
contextNote
评论区洞察是统一选题系统里的一个方法。方法内部只处理本轮提供的 1 条笔记与评论摘录;AI 聊天中如果用户没有提供笔记和评论内容,应先要求用户提供评论素材或由外层 topic orchestrator 从知识库选择一条带评论素材,不要在方法内部读取长期记忆、账号定位或未提供素材。
promptPrefix
你当前已加载 xhs-comment-insight。评论区洞察流程固定为:1 条小红书笔记 -> 统计和分析该笔记评论区 -> 输出 1 个潜在选题。选题中心会随机提供 1 条带评论笔记;AI 聊天中则使用用户本轮提供或指定的 1…
promptSuffix
完成前执行 xhs-comment-insight 输出自检。如果本技能是本轮唯一的选题方法,最终只能输出一个 JSON 对象,不要 Markdown、代码块或解释;topic.title、content_direction、direction_frame 四字段必须完整;topic.connections 必须是…
maxPromptChars
3600

Read the full SKILL.md on GitHub

Files

Just SKILL.md in desktop/builtin-skills/xhs-comment-insight of Jamailar/Beav.

Open the folder on GitHubat commit f35befd

Compare with similar skills

Xhs Comment Insight 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.

Xhs Comment Insight compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xhs Comment Insight this skillJamailar/Beav1.8k—~945Automated safety check: PassCustom licence
Lingzaoatian-create/lingzao-skill2961 repos~8.8kAutomated safety check: PassMIT
Xiaohongshu Ingestchubbyguan/chubbyskills1.2k—~613Automated safety check: NotesMIT
Xiaohongshu Expertokooo5km/Skills4U183—~931Automated safety check: PassMIT
Video To ArticleZJU-REAL/Easel3.3k—~585Automated safety check: PassApache-2.0
Xhs CarouselCatCatUncle/openworkbuddy278—~505Automated safety check: PassCustom licence

Similar skills

  • Lingzao

    atian-create/lingzao-skill

    Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content.

    296 GitHub starsUsed in 1 repo~8.8k tokens
    Media & CreativeAuto-check passed
  • Xiaohongshu Ingest

    chubbyguan/chubbyskills

    小红书笔记采集 → 统一 frontmatter Markdown → 爆款拆解 + 衍生选题. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~613 tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • Xiaohongshu Expert

    okooo5km/Skills4U

    小红书运营专家——从0到1全流程指导。覆盖账号定位、内容创作、标题优化、封面设计、SEO搜索优化、推荐算法拆解、涨粉策略、变现路径、数据分析、平台规则合规、内容发布前审核、账号健康度诊断等全维度。

    183 GitHub stars~931 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Video To Article

    ZJU-REAL/Easel

    把口播、讲座、直播或 Vlog 转录并改写成小红书笔记、公众号文章或知乎内容,同时抽帧配图。当用户说“视频转图文/文章/笔记、视频扒文案、口播转文章、视频内容复用”时使用。只生成字幕文件用 auto-subtitle;翻译已有字幕用 subtitle-translate。

    3.3k GitHub stars~585 tokensUpdated today
    Media & CreativeAuto-check passed
  • Xhs Carousel

    CatCatUncle/openworkbuddy

    小红书图文 6–9 张:开头一张表单定张数风格,出一组 3:4 卡片、3 封面、3 标题和正文标签. An agent skill from CatCatUncle/openworkbuddy.

    278 GitHub stars~505 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Canva

    vivy-yi/xiaohongshu-skills

    A skill your agent uses when creating professional graphics, designs, and visual content for Xiaohongshu posts, stories, banners, or marketing materials without advanced design skills

    478 GitHub stars~7.7k tokensUpdated 8 mo ago
    Media & CreativeAuto-check passed

More from Jamailar/Beav

All 11 skills in this repo
  • Wwud

    Jamailar/Beav

    What Would User Do for RedConvert. An agent skill from Jamailar/Beav.

    1.8k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • App Feedback Admin

    Jamailar/Beav

    Read platform-admin feedback issues through the trusted HTTP admin API, summarize user reports, and turn them into RedBox/RedConvert repair and iteration plans.

    1.8k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Image Director

    Jamailar/Beav

    A skill your agent uses when the user wants to做一整套图片、组图、卡片图、轮播图、配图包或电商套图.

    1.8k GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • Tts Director

    Jamailar/Beav

    A skill your agent uses when generating expressive TTS, short-video voiceover, self-media narration, product explanation, ads, livestream clips, character speech, podcast-style voiceover, or any…

    1.8k GitHub stars~4.2k tokensUpdated yesterday
    Auto-check passed
  • A skill your agent uses when the user wants to plan or generate a social media cover image for a Xiaohongshu note, Douyin/TikTok photo post, Reels/Shorts cover, WeChat/Video Account post…

    1.8k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check: warnings
  • Xhs Title

    Jamailar/Beav

    小红书标题公式工具。从 75 个验证过的爆款公式中,帮你挑对的、用对的、理解为什么用这个. An agent skill from Jamailar/Beav.

    1.8k GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Xhs Comment Insight

What does Xhs Comment Insight do?

小红书评论区洞察选题技能,用于从单条笔记的评论区统计和分析追问、反驳、补充、情绪和未满足需求,生成 1 个可继续创作的小红书选题。. Xhs Comment Insight is an agent skill from Jamailar/Beav.

When should I use Xhs Comment Insight?

Xhs Comment Insight fits situations like: media & Creative work in your project.

How do I install Xhs Comment Insight in Claude Code?

Run `npx skills add Jamailar/Beav --skill xhs-comment-insight -a claude-code`. Or copy the skill folder (desktop/builtin-skills/xhs-comment-insight in Jamailar/Beav) into .claude/skills/xhs-comment-insight in your project. Claude Code loads it when a task matches its description.

How do I install Xhs Comment Insight in Codex?

Run `npx skills add Jamailar/Beav --skill xhs-comment-insight -a codex`. Or copy the skill folder (desktop/builtin-skills/xhs-comment-insight in Jamailar/Beav) into .agents/skills/xhs-comment-insight in your project. Codex loads it when a task matches its description.

Can I use Xhs Comment Insight 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 Jamailar/Beav --skill xhs-comment-insight -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xhs-comment-insight, .gemini/skills/xhs-comment-insight, .github/skills/xhs-comment-insight and .opencode/skills/xhs-comment-insight in your project.

What does Xhs Comment Insight need to run?

SKILL.md names no scripts, command-line tools or credentials: Xhs Comment Insight is instructions for the agent only.

Does Xhs Comment Insight access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Xhs Comment Insight 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 Xhs Comment Insight use?

Xhs Comment Insight has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Xhs Comment Insight use?

About 945 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.

What are the alternatives to Xhs Comment Insight?

Skills that share tags, products or a category with Xhs Comment Insight: Lingzao (atian-create/lingzao-skill, 296 stars), Xiaohongshu Ingest (chubbyguan/chubbyskills, 1.2k stars), Xiaohongshu Expert (okooo5km/Skills4U, 183 stars) and Video To Article (ZJU-REAL/Easel, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xhs Comment Insight?

Jamailar (a GitHub user) maintains it in Jamailar/Beav, which has 1,830 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.

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