Social Account Doctor
JuneYaooo/social-account-doctor
小红书 / 抖音 / 快手 / 视频号 自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环,另支持带货账号诊断、带货视频链接拆解和证据驱动的脚本生成(commerce)。给账号 / 平台视频链接 / 本地视频 / 商品详情、SKU…
A skill your agent uses when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy.
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install otter1101/blogger-distiller blogger-distiller --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .claude/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install otter1101/blogger-distiller blogger-distiller --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .agents/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install otter1101/blogger-distiller blogger-distiller --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .cursor/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install otter1101/blogger-distiller blogger-distiller --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .gemini/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install otter1101/blogger-distiller blogger-distillerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .github/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add otter1101/blogger-distiller --skill blogger-distiller -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install otter1101/blogger-distiller blogger-distiller --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "blogger-distiller" agent skill from https://github.com/otter1101/blogger-distiller/tree/main into .opencode/skills/blogger-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blogger-distiller", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
blogger-distillerA skill your agent uses when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy.
Blogger Distiller is an agent skill from otter1101/blogger-distiller. Use when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy. Trigger on requests such as “拆解博主””蒸馏博主””分析小红书博主””分析抖音博主” “诊断我的账号””对标账号””内容策略分析””小红书账号分析””抖音账号分析” “分析封面””关键词趋势””升级我的skill”.
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 46 other files, including scripts, reference files and assets (for example `DISCLAIMER.md`, `README.md` and `SECURITY.md`).
It sits in Writing & Content, covering Content strategy. It works with Xiaohongshu, Douyin and FFmpeg. The repository describes itself as: 【小红书抖音3万人看过的——博主蒸馏器】你研究了 N 个爆款博主,还是说不清任何一个的操作系统。输入博主的链接,直接蒸馏 TA 的认知和内容打法,装进你的 AI。Distill any blogger's mind into your AI. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 1d787e7. It shows what the files ask for, not the result of running them.
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.
Ships 6 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythongitpipbrewwingetchocoapt-getpython3From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
user.tikhub.ioFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
TIKHUB_API_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Blogger Distiller loads about 3.8k tokens when it runs, and up to ~9.5k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 1,133 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- Linux: `sudo apt-get install -y ffmpeg`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); the scripts in this folder are not scanned.
The full file from otter1101/blogger-distiller at commit 1d787e7, republished under its MIT licence (© otter1101). 1,133 words, ~3,764 tokens.
.claude/skills/blogger-distiller/SKILL.md (or your agent's skills folder). This skill also uses 43 other files; get the full folder from GitHub.⚠️ 使用前必读:本工具仅供学习研究使用,通过 TikHub 公开 REST API 获取公开数据(不模拟登录、不注入 Cookie)。评论者身份默认脱敏(读者1 / 读者2 / 作者),评论正文保留用于研究。完整条款见 DISCLAIMER.md · 安全策略见 SECURITY.md。
触发蒸馏任务前,以下三项必须由用户明确说出,缺一不可:
博主名不等于平台选择。 即使用户提到了"影视飓风""李子柒"等明显关联某平台的博主名,也不得自行推断平台,必须明确询问。
「跑/分析/拆解 博主X」不等于模式 A。 即使用户分析的是他人账号,也必须询问模式,不得推断。
用户已明确说出的项可直接采用,未说出的必须逐一询问后再执行。
自动化的多平台博主蒸馏工具(小红书 + 抖音)。输入一个博主名字,输出两样最终产物:
模式 A 用来拆解对标博主(学 TA),模式 B 用来诊断自己的账号(看自己)。
核心理念:脚本保下限,AI 冲上限。 脚本负责数据采集和确定性分析,AI 负责蒸馏洞察和生成最终产物。
采集目标博主笔记数据(支持 30 / 50 / 80 三档),三层蒸馏产出:
| 层级 | 回答什么 | 举例 |
|---|---|---|
| 认知层 | TA 怎么想? | 核心信念 / 观点张力 / 价值立场 / 思维模式 |
| 策略层 | TA 怎么运营? | 系列规划 / 蹭热点方式 / 运营习惯 / 发布节奏 |
| 内容层 | TA 怎么写? | 标题公式 / 开头模板 / 正文公式 / 情感节奏 / 语言DNA / CTA / 视觉风格 / 标签策略 |
{博主名}_创作指南.skill/SKILL.md{用户名}_创作基因.skill/SKILL.md脚本做 30%(保下限):
AI 做 70%(冲上限):
不安装不影响使用,照常分析博主简介、笔记标题、正文、点赞收藏、评论。 安装后可额外提取视频里说了什么(口播文字),蒸馏结论有更多内容依据。
安装:pip install openai-whisper
系统依赖:ffmpeg(macOS: brew install ffmpeg;Windows: 下载 ffmpeg.org)
模型:在 ~/.xiaohongshu/tikhub_config.json 中设置 whisper_model 字段切换,支持以下档位:
| 模型 | 文件大小 | 每条视频耗时(约2分钟视频) | 适用场景 |
|---|---|---|---|
tiny | 39MB | 3-5s(CPU)/ 1-2s(M芯片) | 极低配机器,质量较差 |
base | 74MB | 8-12s(CPU)/ 4-6s(M芯片) | 默认,够用 |
small | 244MB | 20-35s(CPU)/ 8-15s(M芯片) | 推荐升级点,中文准确率明显提升 |
medium | 769MB | 60-120s(CPU)/ 25-50s(M芯片) | 需 8GB+ 内存,50条笔记约需 1-1.5小时 |
large-v3 | 1.5GB | 150-300s(CPU)/ 60-120s(M芯片) | 需 16GB+ 内存,轻薄本不建议,中文相比 medium 提升有限 |
代价:每条视频额外消耗转写时间(见上表)+ 蒸馏时消耗更多 AI Token
超过 10 分钟的视频自动跳过(ffprobe 预检)
⚠️ 首次运行时,必须在进入 Phase 0.5 前提醒用户:
本工具需要 TikHub API Token 才能运行。如果你还没有,请按以下步骤操作:
- 访问 https://user.tikhub.io 注册账号
- 充值(按量付费即可)
- 在控制台 → API 权限中,一键勾选全部小红书(xiaohongshu)相关端点(开得越全,自动容错能力越强)
- 生成 API Token
密钥存储: 用户提供 Token 后,系统会自动保存到 ~/.xiaohongshu/tikhub_config.json,下次运行无需重复输入。Token 三级加载优先级:
TIKHUB_API_TOKEN~/.xiaohongshu/tikhub_config.json(自动保存)设置方式(三选一):
set TIKHUB_API_TOKEN=你的token(Windows)/ export TIKHUB_API_TOKEN=你的token(macOS/Linux)check_env.py 时会交互式引导,自动保存python run.py "博主名" --token 你的token如需通过代理访问 TikHub API,设置环境变量:
# Windows
$env:HTTP_PROXY="http://127.0.0.1:7890"
$env:HTTPS_PROXY="http://127.0.0.1:7890"
# macOS/Linux
export HTTP_PROXY="http://127.0.0.1:7890"
export HTTPS_PROXY="http://127.0.0.1:7890"Step 0-A:代码自动更新(必须最先执行)
在 skill 所在目录执行以下命令,拉取最新版本代码:
git pull origin mainStep 0-B:环境检查
运行 python scripts/check_env.py
自动检查并修复以下依赖:
pip install~/.xiaohongshu/tikhub_config.json⚠️ AI 执行注意:
check_env.py中 Whisper 安装步骤是交互式的(需要回答 y/N)。在 AI 环境中无法自动交互,因此 不要依赖脚本的交互提示来完成 Whisper 安装。改为在 Phase 0.5 对话中询问用户,再根据用户回答手动执行安装命令。运行check_env.py时如果遇到 Whisper 相关交互提示,输入N跳过即可。
💡 额度提示:每次完整蒸馏约消耗 ¥1~8(取决于笔记数量),可在 https://user.tikhub.io 查看剩余额度。
⚠️ 两条铁律,违反则整个流程无效:
whisper_available 的值,再进入 Phase 0.5。不得跳过 Phase 0 直接进入交互。⚠️ 缺失信息必须明确询问:以下四项信息,用户未在触发指令中明确提供的,必须逐一询问,不得自行推断:
用户已明确提供的信息可以直接采用,无需重复询问。
未提供的信息,参照以下交互文案询问:
─────────────────────────────────────
欢迎使用博主蒸馏器!
请选择分析平台:
1 — 小红书
2 — 抖音
请选择分析模式:
A — 拆解对标博主
采集 TA 的笔记 → 提炼内容公式和思维方式
→ 生成「TA的名字_创作指南.skill/」
B — 诊断我的账号
采集你的笔记 → 找到内容基因和增长瓶颈
→ 生成「你的名字_创作基因.skill/」
采集数量(推荐 50 条):
① 30 条 — 快速扫描(约 15-25 分钟)
② 50 条 — 推荐档位(约 30-45 分钟)
③ 80 条 — 深度分析(约 45-65 分钟)
【whisper_available = true 时】
是否提取视频口播内容?
当前已分析:博主简介、笔记标题、正文、点赞收藏、评论
开启后额外提取:视频里说了什么(口播文字)
代价:每条视频多消耗约 8-12s + 蒸馏时消耗更多 AI Token
【whisper_available = false 或字段不存在时】
当前环境还没有安装视频口播提取功能(Whisper)。
不影响本次蒸馏——标题、正文、评论等文本数据照常分析。
但如果开启,蒸馏时还能额外提取视频里说了什么,
分析出正文公式、情感弧线、语言DNA等更多维度,蒸馏质量会显著提升。
要不要我现在帮你安装?大约需要 2-5 分钟。
y — 帮我装(自动安装 Whisper + ffmpeg)
N — 跳过,先不装(默认)
【安装成功后追加提示】
✅ Whisper 已安装完成(默认使用 base 模型,适合大多数场景)。
如需了解其他模型档位(tiny/small/medium/large),回复「1」查看对比表。
1 — 查看模型对比表,自行选择
回车/其他 — 使用默认 base,继续蒸馏
─────────────────────────────────────Whisper 可用性判断与安装流程:
~/.xiaohongshu/tikhub_config.json 里的 whisper_available 字段路径A:whisper_available = true
⚠️ 必须用工具提问,选项固定为以下三个,不得减少:
→ 用户选选项3 → 展示前置要求中的模型档位表格,用户选择后更新 whisper_model;再回到此问题重新询问
→ 用户选选项1 → transcript_enabled = true
→ 用户选选项2 → transcript_enabled = false
路径B:whisper_available = false 或字段不存在
→ 告知用户口播功能未安装,并询问"要不要我帮你安装"(上方交互文案中的"未安装"版本)
→ 用户选 y → 依次执行:
pip install openai-whisper(安装 Whisper)brew install ffmpegwinget install Gyan.FFmpeg(或 choco install ffmpeg)sudo apt-get install -y ffmpegwhisper_available 写为 true,whisper_model 写为 "base"whisper_model;用户不回复/回复其他 → 保持 base,继续transcript_enabled = true
→ 用户选 N → transcript_enabled = false(主流程不受影响)记录四个变量供后续流程使用:
platform:xhs 或 douyinuser_mode:A 或 Bmax_notes:30 / 50 / 80transcript_enabled:true 或 false若 transcript_enabled = true,运行:
python scripts/crawl_blogger.py <博主名> -o ./data --max-notes <max_notes> --platform <platform> --transcript
否则运行:
python scripts/crawl_blogger.py <博主名> -o ./data --max-notes <max_notes> --platform <platform>
其中 --platform 取值 xhs 或 douyin,对应用户在 Phase 0.5 选择的平台。
⚠️ 重要约束(不得违反):
fetch_note_detail 获取笔记正文。仅有标题和互动数字的列表数据不足以做深度分析,正文、评论、标签都只能从 detail 接口获得。scripts/crawl_blogger.py,必须调用现有脚本。--max-notes 参数的值,必须沿用用户在 Phase 0.5 选定的数量。⚠️ 端点全部失败时的处理: 如果采集过程中出现"所有端点均失败"错误(尤其是 HTTP 402/403),必须立即暂停并提醒用户:
⚠️ 所有 API 端点均返回失败。最常见的原因是 TikHub 控制台的 API 权限未全部开通。 请登录 https://user.tikhub.io,进入控制台 → API 权限,一键勾选全部小红书相关端点,然后重新运行。 如果权限已全部开通,请检查账户余额是否充足。
自动完成:
search_users 精准匹配 → 兜底 search_notes 交叉定位)fetch_user_info)fetch_user_notes)--keywords 指定领域词(search_notes)fetch_note_detail)输出文件(JSON):
{博主名}_profile.json — 主页信息{博主名}_notes_list.json — 笔记列表(按赞数排序){博主名}_notes_details.json — 全量笔记详情(含评论)运行 python scripts/analyze.py ./data/<博主名>_notes_details.json -o ./data
自动完成:
# 话题标签,按频次排序 TOP20输出文件:
{博主名}_analysis.json — 结构化分析数据(含完整笔记列表、分类、观点句候选、高频价值词等)运行:
python scripts/deep_analyze.py ./data/<博主名>_analysis.json "<博主名>" \
-o ./output --details ./data/<博主名>_notes_details.json --mode <user_mode>脚本自动完成:
脚本产出:
{博主名}_数据底稿.md{博主名}_AI蒸馏任务.mdAI 必须读取 AI蒸馏任务.md,按以下顺序生成最终交付物,每完成一个立即写入磁盘,不等另一个完成:
Skill 文件夹(先)
{博主名}_创作指南.skill/SKILL.md{用户名}_创作基因.skill/SKILL.mdHTML 报告(后)
{博主名}_蒸馏报告.html<details><summary> 原生 HTML;响应式,移动端断点 768pxAI蒸馏任务.md 的"技术要求"章节⚠️ 关键契约:
.skill.md 文件SKILL.mdSkill 第三章(内容层)结构要求:
⚠️ 3.3-3.5 数据来源分支:有 Whisper 逐字稿时从逐字稿提取,无逐字稿时从笔记正文提取。所有博主均生成完整结构,不跳过章节。
运行校验时,最终产物应按以下口径验收:
{博主名}_蒸馏报告.html{博主名}_创作指南.skill/SKILL.md模式 B 时,将第二项替换为:
{用户名}_创作基因.skill/SKILL.md如果最终产物缺失、为空、或 AI 仍输出成单个 .skill.md 文件,都视为不合格。
使用 HTTP REST API,Bearer Token 认证:
from scripts.utils.tikhub_client import TikHubClient
client = TikHubClient() # 自动从环境变量/配置文件读取 Token
data = client.search_notes("博主名")| 方法 | 用途 | 关键参数 |
|---|---|---|
search_users(keyword) | 搜索用户(精准匹配博主) | keyword |
search_notes(keyword) | 搜索笔记 | keyword, page, sort |
fetch_user_info(user_id) | 获取用户主页信息 | user_id |
fetch_user_notes(user_id) | 获取用户笔记列表 | user_id, cursor |
fetch_note_detail(note_id) | 获取笔记详情+评论 | note_id |
xiaohongshu 相关端点。解决方法:登录 TikHub 控制台 → API 权限,一键勾选全部小红书端点~/.xiaohongshu/tikhub_config.json,下次运行自动读取,无需重复输入blogger-distiller/
├── SKILL.md # 你现在看的这个文件
├── run.py # 一键运行入口(串联 Phase 0→4)
├── install.py # 自动安装脚本
├── scripts/
│ ├── check_env.py # Phase 0: 环境自动准备(TikHub Token 检查)
│ ├── crawl_blogger.py # Phase 1: 数据采集(TikHub API)
│ ├── analyze.py # Phase 2: 数据分析 + 认知层粗提取
│ ├── deep_analyze.py # Phase 3: 数据底稿 + AI 蒸馏任务
│ ├── verify.py # Phase 4: 数据校验模块
│ └── utils/
│ ├── tikhub_client.py # TikHub REST API 客户端(限速+多端点降级)
│ ├── endpoint_router.py # 端点池路由 + 自动降级引擎
│ ├── endpoints.json # 端点池配置(4组×7类 = 28 个端点)
│ ├── adapters.py # 响应数据归一化适配器
│ ├── common.py # 共用工具函数
│ └── quality.py # 数据质量检查工具
└── references/
└── 张咋啦_创作指南.md直接对 AI 说:
拆解博主 <目标博主名>AI 必须先执行 Phase 0.5 前置交互,再继续后面的流程。
cd blogger-distiller/
python run.py "<博主名>"运行后必须先完成:
然后再进入采集、分析、蒸馏。
cd blogger-distiller/
# Phase 0: 环境自动准备(检查 Python + python-docx + TikHub Token)
python scripts/check_env.py
# Phase 1: 采集博主数据
python scripts/crawl_blogger.py "<博主名>" -o ./data --max-notes 50
# Phase 2: 数据分析
python scripts/analyze.py ./data/<博主名>_notes_details.json -o ./data
# Phase 3 Step A: 生成数据底稿和 AI 蒸馏任务
python scripts/deep_analyze.py ./data/<博主名>_analysis.json "<博主名>" \
-o ./output --details ./data/<博主名>_notes_details.json --mode A注意:
crawl_blogger.py 和 analyze.py 不要自行改写,直接调用现有脚本。deep_analyze.py 只负责生成数据底稿和 AI 蒸馏任务;最终 HTML 和 Skill 文件夹由宿主 AI 继续完成。| 平台 | 本机运行 | HTTP API | Python | 文件读写 | 测试状态 |
|---|---|---|---|---|---|
| CodeBuddy (WorkBuddy) | ✅ | ✅ | ✅ | ✅ | ✅ 已验证 |
| Claude Code | ✅ | ✅ | ✅ | ✅ | ✅ 已验证 |
| OpenClaw (本地) | ✅ | ✅ | ✅ | ✅ | 待测试 |
| OpenClaw (云端) | ✅ | ✅ | ✅ | ✅ | 待测试(不再需要桌面环境) |
| Codex | ✅ | ✅ | ✅ | ✅ | ✅ 已验证 |
SKILL.md 兼容 WorkBuddy / Claude Code / OpenClaw / Codexutils/common.py 共用urllib)避免外部依赖遇到以下报错时,不要直接告知用户"采集失败",按对应步骤处理后重试:
[需要更新]触发条件:
处理步骤:
git pull origin main请重新运行 python install.py 更新 skill 文件后重试余额不足 或 请充值(429)处理步骤:
处理步骤:
git pull origin main 确保代码最新找不到 ffmpeg 警告触发条件:开启了视频转写(--transcript),但 ffmpeg 工具未就绪。
处理步骤:
python3 scripts/check_env.pyreferences/张咋啦_创作指南.md — 可作为创作指南类产出结构参考;若与当前 HTML / Skill 文件夹契约冲突,以本文件和操作手册为准蒸馏完成后,以下进阶分析可按需触发,说出触发词即可执行:
| 玩法 | 触发词 | 说明 |
|---|---|---|
| 🎨 封面视觉风格分析 | 「分析封面」 | 分析封面色彩、构图、文字风格,给出优化建议(双平台,零额外 API) |
| 📈 关键词趋势洞察 | 「关键词趋势」 | 抖音:Index API 完整趋势+画像;小红书:热搜匹配+联想词方向 |
| 🔄 已有蒸馏升级 | 「升级我的 skill」 | 在已有蒸馏基础上追加新维度,无需重新采集 |
© otter1101, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 43 other files (scripts, references, assets) in the repository root of otter1101/blogger-distiller.
Open the folder on GitHubat commit 1d787e7
Blogger Distiller 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 | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Blogger Distiller this skillotter1101/blogger-distiller | 701 | — | ~3.8k | Automated safety check: Notes | MIT | |
| Social Account DoctorJuneYaooo/social-account-doctor | 281 | — | ~8.3k | Automated safety check: Notes | MIT | |
| Wb Xhs Schedule Reviewwenziai/wenzi-xhs-agent-skills | 168 | — | ~816 | Automated safety check: Pass | None | |
| Xhs Keyword To Content Packageatian-create/lingzao-skill | 296 | — | ~722 | Automated safety check: Pass | MIT-0 | |
| Xhs Content Planautoclaw-cc/xiaohongshu-mcp-skills | 272 | — | ~141 | Automated safety check: Pass | MIT | |
| Content Calendarvivy-yi/xiaohongshu-skills | 481 | — | ~854 | Automated safety check: Pass | None |
JuneYaooo/social-account-doctor
小红书 / 抖音 / 快手 / 视频号 自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环,另支持带货账号诊断、带货视频链接拆解和证据驱动的脚本生成(commerce)。给账号 / 平台视频链接 / 本地视频 / 商品详情、SKU…
wenziai/wenzi-xhs-agent-skills
A skill your agent uses when the user wants a Xiaohongshu posting calendar, weekly review board, first-10-post launch plan, 10-20-post positioning test, or data-based next-step plan.
atian-create/lingzao-skill
Lingzao lightweight XHS content workflow Skill that turns a Xiaohongshu keyword, topic, link, screenshot, reference image, saved notes, or inspiration material into a publishable one-stop content…
autoclaw-cc/xiaohongshu-mcp-skills
小红书内容策划助手:搜索分析热门内容和竞品,帮助规划内容方向、选题、标签策略. An agent skill from autoclaw-cc/xiaohongshu-mcp-skills.
vivy-yi/xiaohongshu-skills
A skill your agent uses when scheduling Xiaohongshu posts, maintaining consistent posting frequency, planning content around events or seasons, or organizing content production workflow
vivy-yi/xiaohongshu-skills
A skill your agent uses when managing multiple Xiaohongshu accounts strategically, coordinating content across different accounts, implementing account matrix strategy, or leveraging multiple…
Works with
Categories
A skill your agent uses when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy. Blogger Distiller is an agent skill from otter1101/blogger-distiller. Use when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy.
Blogger Distiller fits situations like: the user wants to analyze; distill a blogger/account on Xiaohongshu; benchmark a target creator; diagnose their own content strategy.
Run `npx skills add otter1101/blogger-distiller --skill blogger-distiller -a claude-code`. Or copy the skill folder (the otter1101/blogger-distiller repository) into .claude/skills/blogger-distiller in your project. Claude Code loads it when a task matches its description.
Run `npx skills add otter1101/blogger-distiller --skill blogger-distiller -a codex`. Or copy the skill folder (the otter1101/blogger-distiller repository) into .agents/skills/blogger-distiller in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add otter1101/blogger-distiller --skill blogger-distiller -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blogger-distiller, .gemini/skills/blogger-distiller, .github/skills/blogger-distiller and .opencode/skills/blogger-distiller in your project.
Going by SKILL.md and its folder, Blogger Distiller needs Python for the scripts in its folder, the command-line tools its instructions call (python, git, pip, brew, winget and choco) and credentials named TIKHUB_API_TOKEN. Our summary lists: Python 3; A credential in TIKHUB_API_TOKEN.
SKILL.md names 1 domain. As links in the text: user.tikhub.io. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Blogger Distiller is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.8k tokens (SKILL.md is roughly 15k 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 5.7k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Blogger Distiller: Social Account Doctor (JuneYaooo/social-account-doctor, 281 stars), Wb Xhs Schedule Review (wenziai/wenzi-xhs-agent-skills, 168 stars), Xhs Keyword To Content Package (atian-create/lingzao-skill, 296 stars) and Xhs Content Plan (autoclaw-cc/xiaohongshu-mcp-skills, 272 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
otter1101 (a GitHub user) maintains it in otter1101/blogger-distiller, which has 701 GitHub stars. The repository was last updated on September 23, 2026.
Source: otter1101/blogger-distiller on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.