Skip to content
Back to search

lingzao

SkillWorks with Claude CodeGitHub

Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content. Lingzao supports XHS SEO, Xiaohongshu account analysis, benchmark account discovery, viral note breakdown, keyword research, one-stop content packages from keyword/link/image/inspiration material, title and cover optimization, hand-drawn route-map cards, city food maps, travel itinerary maps, life checklist maps, workflow manual maps, creator content workflow, note search, creator search, profile lookup, recent posts, deep profile copy/subtitle analysis, note/article detail, post comments, article stats, related articles, short-video copy extraction, and prompt-based creator image generation.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/atian-create--lingzao-skill/badge.svg)](/listings/atian-create--lingzao-skill)

HTML

<a href="/listings/atian-create--lingzao-skill"><img src="/api/listings/atian-create--lingzao-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

把仓库克隆到本地 Agent Skill 目录:

git clone https://github.com/atian-create/lingzao-skill.git ~/.agents/skills/lingzao

运行一次安装脚本:

bash ~/.agents/skills/lingzao/scripts/setup.sh --base-url "https://lingzao.atian.vip"

如果你已经有灵造 API Key,也可以一起配置:

bash ~/.agents/skills/lingzao/scripts/setup.sh \
  --base-url "https://lingzao.atian.vip" \
  --api-key "lgz_xxx"

检查是否配置成功:

~/.lingzao/bin/lingzao doctor

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 615 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: lingzao
  3. description: Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content. Lingzao supports XHS SEO, Xiaohongshu account analysis, benchmark account discovery, viral note breakdown, keyword research, one-stop content packages from keyword/link/image/inspiration material, title and cover optimization, hand-drawn route-map cards, city food maps, travel itinerary maps, life checklist maps, workflow manual maps, creator content workflow, note search, creator search, profile lookup, recent posts, deep profile copy/subtitle analysis, note/article detail, post comments, article stats, related articles, short-video copy extraction, and prompt-based creator image generation.
  4. ---
  5. # Lingzao
  6. Lingzao helps agents research public creator content from Xiaohongshu / XHS,
  7. Douyin, and WeChat official-account articles.
  8. Search phrases this Skill is designed to support: Lingzao Skill, lingzao xhs,
  9. Lingzao Xiaohongshu, XHS SEO, Xiaohongshu SEO, Xiaohongshu account analysis,
  10. XHS account diagnosis, Xiaohongshu keyword research, XHS title optimization,
  11. Xiaohongshu viral note breakdown, Xiaohongshu benchmark account finder, XHS
  12. content workflow, hand-drawn route map card, 手绘收藏地图, 美食地图, 旅游路线图,
  13. 生活清单地图, and 工作流说明书地图.
  14. Use this skill when the user asks to:
  15. - Search Xiaohongshu notes by keyword.
  16. - Turn a keyword, link, screenshot, reference image, or inspiration material into
  17. a Xiaohongshu content package with titles, cover copy, 4-7 page graphic-note
  18. text, body copy, 10 keywords, pinned content, and a review loop.
  19. - Get Xiaohongshu search suggestions or popular recommendations.
  20. - Search public creators by keyword.
  21. - Look up a creator profile.
  22. - Read a creator's recent public posts.
  23. - Get recent post copy, subtitles, covers, metrics, and commercial signals from a creator profile.
  24. - Get details for a Xiaohongshu or Douyin post.
  25. - Get top-level public comments for one Xiaohongshu or Douyin post.
  26. - Get one WeChat official-account article's public detail and text.
  27. - Get public metrics for one WeChat official-account article.
  28. - Get related public WeChat official-account articles.
  29. - Extract spoken copy or transcript from a public short-video link.
  30. - Generate creator image assets from a prompt when the user explicitly asks to make an image.
  31. - Turn a city, food, travel, hiking, life checklist, or workflow topic into a
  32. hand-drawn Xiaohongshu route-map card structure and generation brief.
  33. Use the lightweight sub-skills under `skills/` when a user only needs a single
  34. task such as XHS title writing, Xiaohongshu account diagnosis, keyword design,
  35. note breakdown, cover lab, hand-drawn route-map card, pre-publish check, or
  36. post-publish review. Use this main Lingzao Skill when the user needs live
  37. public-content lookup, deeper
  38. account analysis, Xiaohongshu public-link parsing, comment analysis, article
  39. data, transcript extraction, image generation, report export, or
  40. knowledge-base sync.
  41. ## Agent Playbooks
  42. For higher-level creator strategy tasks, use the playbooks in
  43. `<skill_root>/playbooks/` before answering. They turn Lingzao's public-content
  44. tools into creator workflows instead of isolated lookups.
  45. Use these playbooks when relevant:
  46. - `lingzao-progressive-interaction-map.md`: route vague user inputs, homepage
  47. links, note links, drafts, and reference-image requests with light questions.
  48. - `search-credit-notice.md`: explain basic vs deep search scope before paid
  49. lookups and avoid silently expanding credit usage.
  50. - `atian-creator-judgment-framework.md`: apply A Tian's account-stage,
  51. memory-anchor, content-mainline, and bottleneck judgment.
  52. - `creator-case-general-analysis-framework.md`: analyze any creator case across
  53. tracks by identifying the account archetype, memory anchor, new narrative,
  54. proof system, audience desire, content engine, format engine, comment demand,
  55. commercial entry, hidden resources, learnable parts, non-copyable parts, and
  56. user-fit tests.
  57. - `beginner-account-start-and-topic-radar.md`: handle zero-to-one creator
  58. questions, topic discovery, keyword trees, and low-follower viral references.
  59. - `keyword-insight-report-template.md`: create scoped keyword insight reports
  60. from a main keyword plus confirmed related/dropdown terms, with clear credit
  61. estimates before expanding.
  62. - `keyword-to-publishable-content-package.md`: turn a keyword, vague topic,
  63. note link, screenshot, reference image, saved note, or inspiration material
  64. into publishable Xiaohongshu content packages with selected references,
  65. topic angles, titles, cover copy, 4-7 page graphic-note text, spoken scripts,
  66. Vlog storyboards, body copy, 10 publishing keywords, pinned content, and a
  67. pre/post-publish review loop.
  68. - `mother-content-cross-platform-distribution.md`: turn one topic, draft,
  69. note breakdown, product update, screenshot, transcript, or oral idea into a
  70. one-stop cross-platform distribution package. When users say "一条龙",
  71. "全平台同步", "分发包", or "一个模板发多个平台", start with the basic
  72. Xiaohongshu + Moments + WeChat public-account package, then offer optional
  73. expansion to podcast, X, Knowledge Planet, Bilibili, video account/Douyin,
  74. Xiaohongshu image package, or knowledge-base/SOP.
  75. - `pre-publish-readiness-check.md`: before posting, ask whether the content is
  76. already finished and then check content clarity, image/page readiness, cover
  77. recognition, title clickability, first 3 lines or first 3 seconds, and natural
  78. keyword embedding.
  79. - `audience-persona-fit-check.md`: before titles, keywords, account operation,
  80. or content-package decisions, infer or ask who the content is for, who will
  81. click, who will not click, and which audience/city/life-stage keywords should
  82. shape the output.
  83. - `xhs-title-design-check.md`: design or diagnose Xiaohongshu titles after the
  84. user sends a topic, draft, cover copy, reference note, or content package;
  85. default to 3 strongest titles with keyword anchor and click reason instead
  86. of a 10-title pool.
  87. - `xhs-profile-bio-design.md`: write or diagnose Xiaohongshu 100-character
  88. profile bios and homepage introductions that clarify who the account is for,
  89. what it shares, why to follow, and how it connects to nickname, pinned notes,
  90. account stage, audience keywords, city keywords, and light commercial paths.
  91. - `benchmark-account-discovery-quality-gate.md`: find or judge benchmark
  92. accounts with a default quality gate: still updating, recent high-performing
  93. works, track/audience fit, stage fit, and clear learnable parts; stale
  94. accounts should be marked as historical references, not main benchmarks.
  95. User-facing results should show direct creator profile links and the specific
  96. recent high-interaction works, not raw creator IDs. The first discovery round
  97. should return up to 5 strong accounts, not 10-20 accounts; expand only after
  98. the user confirms follower range, stage, city, audience, format, or asks for
  99. more. Include follower count, total liked count, latest update, recent
  100. 30-day hit works with note metrics, content format, and why each account is
  101. worth learning; sort visible recommendations by follower count from high to
  102. low when available.
  103. - `self-account-peer-horizontal-diagnosis.md`: compare the user's own account
  104. with same-track, same-stage, or same-follower-range peer accounts when the
  105. user explicitly asks for peer comparison, such as "横向对比", "同级账号",
  106. "对标账号", "找 5-15w 粉账号和我比", or "和同赛道账号比我差在哪里". Generic
  107. own-account concerns such as "看看我现在的问题" or "我是不是说话太快" should
  108. stay on `self-account-diagnosis-report-template.md` unless the user also asks
  109. to compare against peers. It combines own-account diagnosis, active benchmark
  110. selection, peer-account tables, title/cover/opening/speech/content-system
  111. comparison, top gaps, 30-day adjustment plans, and a human next-step loop.
  112. - `single-note-breakdown-workflow.md`: break down one Xiaohongshu/Douyin note
  113. link by title, cover, outline/script, shooting/editing layer when visible,
  114. comment demand, viral mechanism, learnable parts, non-copyable parts, and
  115. adaptation into the user's own graphic note, spoken script, Vlog storyboard,
  116. or knowledge-base card. User phrases such as "完整分析这条笔记", "深度拆解",
  117. "拆细一点", "拍摄手法", "分镜", or "剪辑节奏" should trigger the deeper
  118. breakdown instead of a short summary.
  119. - `publishing-keyword-design-check.md`: design the final 10 Xiaohongshu
  120. publishing keywords for a finished draft and check whether title, cover copy,
  121. opening lines, and keyword field carry the keywords naturally.
  122. - `track-difficulty-judgment-library.md`: judge common tracks such as female
  123. growth, career, good products, local life, health, fashion, and AI tools.
  124. - `monetization-path-judgment-library.md`: answer whether a track or account
  125. can monetize through ads, courses, community, consulting, lead generation,
  126. products, stores, or enterprise conversion.
  127. - `self-account-diagnosis-report-template.md`: structure own-account diagnosis
  128. reports, follow-up actions, and a human closing with "人情味" that turns
  129. sharp diagnosis into one small next experiment instead of ending at a cold
  130. action list. Own-account diagnosis should also include a share-worthy
  131. conclusion card, action advice, and psychological reassurance.
  132. - `comparable-account-breakdown-report-template.md`: decide whether another
  133. account is worth learning from, what can be learned, and what cannot be copied.
  134. - `draft-rewrite-and-benchmark-workflow.md`: rewrite drafts, adapt viral
  135. formulas, and review multiple content ideas without only polishing sentences.
  136. - `reference-image-graphic-note-workflow.md`: turn reference images into
  137. Xiaohongshu 4-page or 7-page graphic-note packages.
  138. - `visual-generation-and-cover-workflow.md`: route Xiaohongshu covers, graphic
  139. notes, WeChat image packs, no-person knowledge cards, and product/ecommerce
  140. visuals into image generation or ready-to-use prompt packages.
  141. - `image-generation-execution-workflow.md`: when image generation is available,
  142. turn the visual route into actual images, run a visual-director quality gate,
  143. and repair ugly/crowded/generic generations instead of leaving ordinary users
  144. with raw prompts.
  145. - `image-generation-agent-integration-guide.md`: model-agnostic rules for
  146. domestic Agent wrappers, including stable generation input/output fields,
  147. good-vs-bad image standards, reference-image usage, known generation bugs,
  148. friendly failure handling, and A Tian's example-collection homework.
  149. - `visual-reference-style-library.md`: classify A Tian's internal visual
  150. reference folders into travel/food covers, WeChat article images, AI-person
  151. infographics, Lingzao no-person knowledge cards, product conversion images,
  152. face-led keyword video covers, interaction prompt covers, and text-dense
  153. screenshot graphic notes, and room-as-identity lifestyle covers.
  154. - `post-publish-data-review-workflow.md`: review published Xiaohongshu notes
  155. from note links, backend screenshots, scripts, covers, and 24h/48h/7d data.
  156. - `content-knowledge-base-workflow.md`: turn saved notes, public creator links,
  157. keyword results, viral examples, and creator distillation requests into
  158. user-owned topic, title, cover, structure, account-reference,
  159. creator-research, and publishing-review libraries.
  160. - `retention-and-follow-up-loop.md`: end useful outputs with one concrete next
  161. step such as published-note data review, reusable reference-search templates,
  162. draft feedback, or a post-diagnosis small experiment with a return loop. It
  163. also defines the SOP for not letting the user's words drop on the floor:
  164. acknowledge resistance, lower the next action, and ask one concrete
  165. next-step question. Dense outputs should offer Word, HTML/webpage preview, or
  166. knowledge-base-ready packaging instead of leaving users with a wall of chat
  167. text. When users say the diagnosis is accurate but they lack action, route to
  168. a post-diagnosis activation package instead of adding more pressure.
  169. - `product-judgment-and-feedback-loop.md`: judge where users are really stuck,
  170. explain Lingzao in human language, build content/sales narratives, turn user
  171. feedback into product iteration, and decide which requests are worth building
  172. versus noise.
  173. - `xhs-operation-task-tree.md`: route Lingzao users by concrete Xiaohongshu
  174. operation tasks instead of course lists, covering homepage diagnosis,
  175. benchmark discovery, viral-note adaptation, topic generation, content
  176. production, cover/image work, pre-publish checks, post-publish review,
  177. acquisition paths, and knowledge-base automation.
  178. Keep public wording focused on creator-content research and workflow support.
  179. Do not promise viral growth, guaranteed monetization, full monitoring, raw data
  180. export, or copying another creator's content.
  181. ## Install And Paid Capability Entry
  182. Lingzao is installed as one free main Skill. Users do not need to install
  183. separate title, keyword, account-diagnosis, benchmark, cover, or review skills.
  184. After installation, this main Skill routes the user's request to the right
  185. playbook.
  186. There are two user acquisition paths:
  187. 1. Community/course users:
  188. - They may already have A Tian's course, install link, payment steps, and
  189. API Key setup instructions.
  190. - Keep the in-chat explanation short: install the Skill, open the Lingzao web
  191. dashboard, follow the tutorial, recharge credits, copy the API Key, then
  192. run setup.
  193. 2. Public-platform users from Xiaohongshu, Douyin, or other public content:
  194. - Do not require them to open the web dashboard and pay before they
  195. understand what Lingzao can do.
  196. - Let them install the free main Skill first.
  197. - Then explain the hidden paid entry in friendly language: the local
  198. playbooks can help judge drafts, titles, covers, directions, and
  199. publishing plans; when they need Lingzao to search public content, inspect
  200. accounts, open note/article details, read comments, inspect article data,
  201. extract video copy, or generate creator image assets, they need to open
  202. the Lingzao web dashboard, follow the tutorial, recharge credits, and
  203. configure an API Key.
  204. The web dashboard is not only a payment page. Present it as the user's learning
  205. and setup hub:
  206. - learn how to install and configure Lingzao
  207. - learn how to ask Agent better questions instead of waiting in a group chat
  208. - learn how to use Skill workflows for self-media operation
  209. - learn account diagnosis, benchmark breakdown, title/keyword, pre-publish, and
  210. post-publish review workflows
  211. - recharge credits and get the API Key when they need public-content lookup or
  212. image generation
  213. Use this wording when a user has installed the Skill but has not configured an
  214. API Key yet:
  215. 你已经装好灵造 Skill 了。安装本身是免费的,它会先帮你判断你现在是在找方向、拆账号、写内容、做封面、配关键词,还是复盘数据。
  216. 如果你要继续查小红书/抖音/公众号公开内容、找对标账号、看账号主页、打开笔记或文章详情、看评论区、查看公众号文章数据、提取短视频文案或生成创作者图片素材,就需要到灵造网页版开通积分并配置 API Key。
  217. 你可以打开 https://lingzao.atian.vip 看安装教程和使用教程,里面也会教你怎么用 Agent 做自媒体运营、怎么问问题、怎么用这些 Skill。需要查公开内容或生成图片的时候,再在网页里充值/获取 API Key,配置好以后回来继续问,我会接着刚才的问题往下做。
  218. Do not frame payment as a penalty. Frame it as:
  219. - free install = get the workflow brain and routing layer
  220. - web dashboard = tutorial, usage examples, self-media operation lessons, and
  221. API Key setup
  222. - paid credits = unlock public-content lookup, image generation, and deeper
  223. research actions
  224. Knowledge sync handoff:
  225. - After a useful Lingzao research result or diagnosis report, do not sync it
  226. automatically. Ask first: 要不要把这份结果同步到你的知识库?可以选择
  227. ima / Obsidian / 飞书 / 暂不同步。
  228. - If the user chooses a target, prepare a clean Markdown version and ask the
  229. current Agent environment to use the user's configured knowledge tool.
  230. - For ima, call the installed ima Skill or ima knowledge-base tool if the user
  231. has configured one.
  232. - For Obsidian, use the user's Obsidian CLI, Obsidian Skill, or approved vault
  233. workflow to write Markdown under a user-approved `Lingzao/` path.
  234. - For 飞书, use the user's Lark/Feishu CLI or Skill with user authorization to
  235. create or update a document.
  236. - Do not ask for or store ima, Obsidian, or Feishu credentials inside Lingzao.
  237. Do not include internal implementation details, raw payloads, cache URLs,
  238. signed URLs, API keys, or internal error details in synchronized content.
  239. Profile workflow:
  240. - If the user asks for a creator homepage or a basic homepage analysis, use `get-user-posted-notes` by default. It returns recent posts and enough author/post data for a basic read.
  241. - If the user sends a Xiaohongshu short link such as `xhslink.com/m/...`, or a
  242. copied share sentence such as `@... 查看Ta的主页>> https://xhslink.com/m/...`,
  243. extract the short link, normalize bare links to `https://...`, and read the
  244. surrounding words before choosing a command. Do not classify the short link by
  245. path alone. If the context says account, homepage, creator, profile,
  246. benchmark, account diagnosis, homepage diagnosis, `Ta的主页`, or recent posts,
  247. treat it as a creator-homepage request and call
  248. `get-user-posted-notes --url "https://<short link>"`.
  249. - If a Xiaohongshu short link has no context, ask whether the user wants creator
  250. homepage recent posts or one-post detail before spending credits. If the
  251. context says this note, comments, copy, transcript, one-post breakdown, or is
  252. a normal note share sentence with a title snippet plus `前往【小红书】一探究竟吧`,
  253. treat it as a one-post candidate, not a homepage. One-post words such as
  254. `这条` or `这篇` take priority over generic diagnosis wording. Do not default
  255. to `get-note-detail`; first confirm it is a single post and ask for the final
  256. note URL or note_id plus whether it is 图文 or 视频 when needed.
  257. - Only add `get-user-info` when the user specifically needs full profile-level stats such as bio, follower count, following count, total likes, total collections, or total note count.
  258. - Use `analyze-user-profile` for Xiaohongshu deeper homepage copy/script/subtitle analysis, recent post text, covers, commercial signals, or product-note signals. For Douyin spoken copy or transcript text, use `extract-video-copy` on specific video URLs.
  259. - Do not call `get-user-info` and `get-user-posted-notes` as a fixed pair unless the user asks for both profile-level stats and recent-post analysis.
  260. - Do not force a full account diagnosis when the homepage has too few public
  261. posts. Route by visible sample size:
  262. - 0 posts: no account diagnosis; switch to beginner start/account setup
  263. guidance.
  264. - 1-2 posts: homepage first impression plus single-post feedback only.
  265. - 3-5 posts: starter-account mini diagnosis.
  266. - 6-9 posts: light account analysis.
  267. - 10+ posts: standard account analysis can be offered.
  268. - 20+ posts: standard deep diagnosis can use `analyze-user-profile --limit 20`
  269. after credit confirmation.
  270. - 40+ posts: deep diagnosis, creator distillation, or knowledge-base
  271. distillation can use `--limit 40` after credit confirmation.
  272. Post drill-down workflow:
  273. - Xiaohongshu list-style commands (`search-notes`, `get-user-posted-notes`,
  274. `analyze-user-profile`) return `xhs_note_type` on each note item when
  275. Lingzao can identify whether it is 图文 or 视频.
  276. - When continuing from one of those note items to `get-note-detail`, pass the
  277. returned `xhs_note_type` directly as `--xhs-note-type`; do not infer the type
  278. from the URL.
  279. - If a Xiaohongshu note item has no `xhs_note_type`, ask the user whether it is
  280. 图文 or 视频 before calling `get-note-detail`. `get-note-comments` can still
  281. be called without this type.
  282. ## Setup
  283. Resolve this `SKILL.md` directory as `<skill_root>`, then run setup once:
  284. ```bash
  285. bash "<skill_root>/scripts/setup.sh" --base-url "https://your-lingzao-domain.com"
  286. ```
  287. Environment variables override saved config:
  288. ```bash
  289. export LINGZAO_API_KEY="lgz_xxx"
  290. export LINGZAO_BASE_URL="https://your-lingzao-domain.com"
  291. ```
  292. Check the connection:
  293. ```bash
  294. ~/.lingzao/bin/lingzao doctor
  295. ```
  296. Before using Lingzao commands, check whether the skill has an update:
  297. ```bash
  298. ~/.lingzao/bin/lingzao check-version
  299. ```
  300. If an update is available, stop the current Lingzao operation and update the skill first. Do not continue using an outdated Lingzao Skill for search, profile, subtitle, or extraction work.
  301. To update the skill, rerun the installer. For `npx skills`, try:
  302. ```bash
  303. npx skills add https://assets-tian.midao.site/skills/lingzao --skill lingzao -g --copy
  304. ```
  305. Updating keeps the saved API config in `~/.lingzao/config.json`; no API key setup is needed again.
  306. If `~/.lingzao/bin/lingzao` is missing or points to the wrong directory, repair the command wrapper:
  307. ```bash
  308. bash ~/.agents/skills/lingzao/scripts/setup.sh --skip-doctor
  309. ```
  310. If `~/.agents/skills/lingzao` does not exist, find the directory that contains `lingzao`'s `SKILL.md`, then run `scripts/setup.sh --skip-doctor` from that directory.
  311. ## Before Calling
  312. Before running a command with meaningful filters, ask the user for the relevant
  313. parameters if they did not already specify them.
  314. - For `search-notes`, ask for sorting, note type, and time range before calling:
  315. sort can be `general`, `most_liked`, `popularity_descending`,
  316. `comment_descending`, or `collect_descending`; note type can be `不限`,
  317. `视频笔记`, `图文笔记`, or `直播笔记`; time range can be `不限`, `一天内`,
  318. `一周内`, or `半年内`.
  319. - Douyin `search-notes` currently supports only `general`, `most_liked`, and
  320. `popularity_descending`. Do not pass `comment_descending` or
  321. `collect_descending` for Douyin searches.
  322. - Douyin `search-notes` note type currently supports only `不限`, `视频笔记`,
  323. and `图文笔记`. Do not pass `直播笔记` for Douyin searches.
  324. - For `get-note-comments`, ask whether the user wants latest comments or
  325. liked-count sorting before calling Xiaohongshu. Use `--sort latest` for latest
  326. comments and `--sort most_liked` for Xiaohongshu liked-count sorting.
  327. - Douyin comments currently support only `latest`. Do not ask for or pass
  328. `--sort most_liked` on Douyin comment requests.
  329. - Xiaohongshu list-style commands (`search-notes`, `get-user-posted-notes`,
  330. `analyze-user-profile`) return `xhs_note_type` on each note item when
  331. Lingzao can identify whether it is 图文 or 视频. When continuing from one of
  332. those note items to `get-note-detail`, pass the returned value directly as
  333. `--xhs-note-type`; do not infer the type from the URL. If a Xiaohongshu note
  334. item has no `xhs_note_type`, ask the user whether it is 图文 or 视频 before
  335. calling `get-note-detail`. `get-note-comments` can still be called without
  336. this type.
  337. - If the user explicitly says to use defaults, proceed with the documented
  338. defaults instead of asking again.
  339. After a successful research command, tell the user the estimated time saved
  340. shown in the CLI Markdown output. If you called multiple Lingzao research
  341. commands for one user request, summarize the total once. Do not show time-saved
  342. language for `doctor`, `check-version`, failed commands, or JSON-only internal
  343. processing.
  344. ## Commands
  345. ### Search Notes
  346. ```bash
  347. ~/.lingzao/bin/lingzao search-notes --platform xhs --keyword "AI写作"
  348. ~/.lingzao/bin/lingzao search-notes --platform xhs --keyword "AI写作" --sort most_liked
  349. ~/.lingzao/bin/lingzao search-notes --platform xhs --keyword "AI生图" --sort collect_descending --note-type "视频笔记" --time-filter "一周内"
  350. ~/.lingzao/bin/lingzao search-notes --platform douyin --keyword "AI生图" --sort most_liked --note-type "视频笔记"
  351. ```
  352. Use this when the user wants public notes around a topic.
  353. Before calling, ask the user for `--sort`, `--note-type`, and `--time-filter`
  354. when they have not specified those preferences.
  355. ### Search Suggestions
  356. ```bash
  357. ~/.lingzao/bin/lingzao search-suggestions --platform xhs --keyword "AI生图"
  358. ~/.lingzao/bin/lingzao search-suggestions --platform xhs
  359. ```
  360. Use this when the user wants Xiaohongshu keyword expansions, autocomplete
  361. phrases, or popular search recommendations. If `--keyword` is omitted, Lingzao
  362. returns popular recommendations.
  363. ### Search Creators
  364. ```bash
  365. ~/.lingzao/bin/lingzao search-users --platform xhs --keyword "母婴博主"
  366. ~/.lingzao/bin/lingzao search-users --platform douyin --keyword "AI生图"
  367. ```
  368. Use this when the user wants creators in a topic or niche.
  369. ### Get Creator Profile
  370. ```bash
  371. ~/.lingzao/bin/lingzao get-user-info --url "https://www.xiaohongshu.com/user/profile/..."
  372. ~/.lingzao/bin/lingzao get-user-info --platform xhs --user-id "63c21e0f000000002801a1bb"
  373. ~/.lingzao/bin/lingzao get-user-info --platform douyin --user-id "MS4wLjABAAAA..."
  374. ```
  375. Use this when the user provides a creator profile URL or platform user ID and needs full profile-level stats. For Douyin bare user IDs, use the profile `sec_user_id`. For basic homepage analysis, prefer `get-user-posted-notes` and avoid calling both commands by default.
  376. ### Get Creator Recent Posts
  377. ```bash
  378. ~/.lingzao/bin/lingzao get-user-posted-notes --url "https://www.xiaohongshu.com/user/profile/..."
  379. ~/.lingzao/bin/lingzao get-user-posted-notes --platform xhs --user-id "63c21e0f000000002801a1bb"
  380. ~/.lingzao/bin/lingzao get-user-posted-notes --platform douyin --user-id "MS4wLjABAAAA..." --limit 20
  381. ```
  382. Use this when the user wants to understand what a creator has posted recently. Use this by default for basic creator homepage analysis. Douyin recent posts are a single-page call and currently support `--limit 20` at most. If the user asks for full profile-level stats, add `get-user-info`; if the user asks for Xiaohongshu post copy, scripts, captions, or transcript text across recent posts, use `analyze-user-profile` instead. For Douyin transcript text, use `extract-video-copy` on selected video URLs.
  383. ### Analyze Creator Profile
  384. ```bash
  385. ~/.lingzao/bin/lingzao analyze-user-profile --url "https://www.xiaohongshu.com/user/profile/..." --limit 20
  386. ~/.lingzao/bin/lingzao analyze-user-profile --platform xhs --user-id "63c21e0f000000002801a1bb" --limit 40
  387. ~/.lingzao/bin/lingzao analyze-user-profile --platform douyin --user-id "MS4wLjABAAAA..." --limit 20
  388. ```
  389. Use this when the user wants deeper creator profile data, including post text, covers, commercial signals, and profile-level content signals. For Xiaohongshu, it also includes subtitle/script previews. For Douyin, it does not extract homepage subtitles or transcript text; use `extract-video-copy` on selected video URLs when the user needs spoken copy.
  390. Use `--limit 20` by default. The default Markdown output shows readable subtitle previews when the platform provides them.
  391. Important for Xiaohongshu: the complete profile subtitle/copy Markdown artifact is a top-level response field, not a per-note subtitle URL. Always check:
  392. `data.artifacts.subtitle_markdown.status`
  393. `data.artifacts.subtitle_markdown.url`
  394. Do not search only inside `items[]`. If `data.artifacts.subtitle_markdown.status == "ready"` and `url` exists, download it before deep script or subtitle analysis:
  395. ```bash
  396. curl -L "$subtitle_markdown_url" -o /tmp/lingzao-profile-subtitles.md
  397. ```
  398. Use the downloaded Markdown file for complete subtitle/copy analysis. Use `--format json` when the user needs the structured fields. JSON includes `data.artifacts.subtitle_markdown.url` for the complete Markdown file when available, and inline `items[].text.subtitle.content/plain_text` are preview-sized to keep the response readable. If the artifact is unavailable, use the inline subtitle fields. For Douyin, expect `data.artifacts.subtitle_markdown.status == "unsupported"` and use the returned profile insights plus selected-video extraction instead.
  399. ### Get Post Detail
  400. ```bash
  401. ~/.lingzao/bin/lingzao get-note-detail --url "https://www.xiaohongshu.com/explore/..." --xhs-note-type image
  402. ~/.lingzao/bin/lingzao get-note-detail --platform xhs --note-id "69690331000000001a02266a" --xhs-note-type video
  403. ~/.lingzao/bin/lingzao get-note-detail --platform douyin --note-id "7372484715782352169"
  404. ```
  405. Use this when the user asks to analyze one public post.
  406. For Xiaohongshu details, pass `--xhs-note-type image` for 图文 and
  407. `--xhs-note-type video` for 视频. If the note came from `search-notes`,
  408. `get-user-posted-notes`, or `analyze-user-profile`, reuse that item's
  409. `xhs_note_type` value.
  410. ### Get Post Comments
  411. ```bash
  412. ~/.lingzao/bin/lingzao get-note-comments --url "https://www.xiaohongshu.com/explore/..."
  413. ~/.lingzao/bin/lingzao get-note-comments --url "https://www.xiaohongshu.com/explore/..." --sort most_liked
  414. ~/.lingzao/bin/lingzao get-note-comments --platform xhs --note-id "69690331000000001a02266a"
  415. ~/.lingzao/bin/lingzao get-note-comments --platform douyin --note-id "7372484715782352169"
  416. ~/.lingzao/bin/lingzao get-note-comments --url "https://www.douyin.com/jingxuan?modal_id=..." --cursor "next_cursor_from_previous_response"
  417. ```
  418. Use this when the user asks for public comments on one post. The first version returns top-level comments only. Use `--sort most_liked` for Xiaohongshu liked-count sorting; Douyin currently supports the default `latest` sort only. If the response has `data.page.next_cursor`, pass that value with `--cursor` to fetch the next page.
  419. Before calling Xiaohongshu comments, ask whether the user wants latest comments
  420. or liked-count sorting. For Douyin comments, use only `--sort latest`; do not
  421. pass `--sort most_liked`.
  422. ### Get WeChat Official-Account Articles
  423. ```bash
  424. ~/.lingzao/bin/lingzao get-article-detail --url "https://mp.weixin.qq.com/s/..."
  425. ~/.lingzao/bin/lingzao get-article-stats --url "https://mp.weixin.qq.com/s/..."
  426. ~/.lingzao/bin/lingzao get-related-articles --url "https://mp.weixin.qq.com/s/..."
  427. ```
  428. Use these when the user provides a public WeChat official-account article URL
  429. and asks to analyze the article, inspect public engagement metrics, or expand
  430. from that article to related public articles. The first version is URL-only and
  431. costs 20 credits per call. An empty related-articles list is a valid response.
  432. Do not use these commands for account article history, account listing, or
  433. multi-page fanout unless Lingzao adds a separate capability.
  434. ### Extract Short-Video Copy
  435. ```bash
  436. ~/.lingzao/bin/lingzao extract-video-copy --url "https://www.xiaohongshu.com/explore/..."
  437. ~/.lingzao/bin/lingzao extract-video-copy --url "https://v.douyin.com/..."
  438. ```
  439. Use this when the user asks for short-video spoken copy, transcript, subtitles, or口播文案.
  440. ### Generate Image
  441. ```bash
  442. ~/.lingzao/bin/lingzao generate-image --prompt "一张小红书封面图,主题是 AI 生图新手避坑,干净明亮,中文大标题留白" --output /tmp/lingzao-image.png
  443. ~/.lingzao/bin/lingzao generate-image --prompt "极简产品海报,白底,柔和阴影" --size 1024x1536 --output /tmp/poster.png
  444. ~/.lingzao/bin/lingzao generate-image --prompt "参考两张图,保留人物风格,把产品界面换成灵造首页截图" --size 1536x2048 --image /tmp/style.png --image /tmp/product.png --output /tmp/poster.png
  445. ~/.lingzao/bin/lingzao generate-image --prompt "批量生成 3 张封面草稿" --count 3 --size 1024x1536 --output /tmp/poster.png
  446. ```
  447. Use this only when the user asks to generate a creator image asset. For normal
  448. research, do not call image generation automatically.
  449. Before calling `generate-image`, run the minimal intake gate. If the user only
  450. says something like "给我做一张某某海报图" or provides only a broad topic, do
  451. not spend credits immediately. Ask for the two visual anchors first:
  452. 1. 你有没有参考图?可以发 1-3 张你喜欢的封面/海报/图文截图。
  453. 2. 你有没有想要的配色?比如明亮白底、绿色清爽、黑金高级、蓝色科技感。
  454. If those are still unclear, ask at most one extra route-changing question, such
  455. as the publishing platform/size, exact on-image text, or whether the user wants
  456. people/no people. Only proceed directly without asking when the user already
  457. provided enough constraints: topic + platform/format + visual style/reference
  458. or color + on-image text/material.
  459. Use `--image` for local reference images; repeat it for multiple images. The
  460. Skill uploads those files directly to Lingzao for the current request, so the
  461. user does not need to upload them elsewhere first. Supported reference image
  462. formats are png, jpeg, and webp.
  463. #### Reference Image Handling
  464. For Codex, WorkBuddy, and other agent runtimes:
  465. - `--image` accepts local filesystem paths only. If the user provides a
  466. reference image through a chat attachment, pasted image, screenshot, or input
  467. box, first materialize that image as a local file before calling the CLI.
  468. Preserve the original supported image format when saving the file.
  469. - Use a per-run temporary directory for runtime-provided images, for example
  470. `/tmp/lingzao-image-inputs/<run-id>/ref-1.png` and
  471. `/tmp/lingzao-image-inputs/<run-id>/ref-2.png`. Use absolute paths in the CLI
  472. call.
  473. - If the user already provided a stable local path, such as a file under
  474. `/Users/...`, you may pass that path directly. If the runtime-provided image
  475. lives in a transient attachment/cache path, copy it into the per-run temp
  476. directory first.
  477. - Do not proactively convert image formats. If the input image is already png,
  478. jpeg, or webp and its file size is reasonable, pass it as-is. Do not convert
  479. png to webp or jpeg just because an example path uses a different extension.
  480. - Only when a reference image is larger than 2 MB, create a smaller copy in the
  481. temp directory and pass that copy with `--image`. Keep the file extension and
  482. actual image bytes consistent. If resizing or compression fails, use the
  483. original supported image file instead of trying another format.
  484. - Do not overwrite the user's original image file. Do not store reference
  485. images in the repo. If the runtime cannot save an uploaded or pasted image to
  486. a local path, ask the user to save the image locally and provide the path.
  487. - In the prompt, state what should be borrowed from the reference images, such
  488. as layout, color palette, product shape, character style, or composition. Do
  489. not say only "reference this image" when a more specific instruction is
  490. possible.
  491. Example with a runtime-provided reference image:
  492. ```bash
  493. mkdir -p /tmp/lingzao-image-inputs/run-001 /tmp/lingzao-image-outputs/run-001
  494. ~/.lingzao/bin/lingzao generate-image \
  495. --prompt "参考这张图的排版和明亮色彩,生成一张小红书封面图,主题是 AI 生图新手避坑,中文大标题留白" \
  496. --size 1024x1024 \
  497. --image /tmp/lingzao-image-inputs/run-001/ref-1.png \
  498. --output /tmp/lingzao-image-outputs/run-001/result.png
  499. ```
  500. The command creates a Lingzao async batch and automatically polls the returned
  501. status URL until the background job finishes or the command timeout is reached.
  502. Image generation can take several minutes; `--timeout` can extend waiting for
  503. large or slow batches, but does not shorten the built-in per-image polling
  504. window. For one image, `--output` writes the result to the exact path you
  505. provide. For `--count` greater than 1, `--output /tmp/poster.png` writes every
  506. successful image as numbered files such as `/tmp/poster-1.png`,
  507. `/tmp/poster-2.png`, and so on. Default Markdown output requires `--output` so
  508. paid generated images are saved locally. Use `--format json` only when you need
  509. structured item statuses or raw image payloads.
  510. ## Usage Notes
  511. - For profile and post URLs, pass the URL directly when possible.
  512. - For raw IDs, include `--platform`.
  513. - Omit `--limit` unless the user asks for a specific count.
  514. - Search notes default to comprehensive sorting, all note types, and all time; use `--sort`, `--note-type`, and `--time-filter` when the user asks for ranked or filtered note search.
  515. - Use `--format json` only when another tool needs structured output.
  516. - Default output is Markdown for agents to read and summarize.
  517. - If the API key or account needs attention, ask the user to open the Lingzao dashboard.
README.md · README · 186 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # 灵造 Skill
  2. 给 Claude Code、Codex、OpenClaw 等 Agent 使用的创作者公开内容研究 Skill。
  3. Lingzao / 灵造是一个面向 **XHS / Xiaohongshu / 小红书运营** 的 Agent
  4. Skill 包,覆盖 Xiaohongshu SEO、XHS keyword research、账号诊断、对标账号、
  5. 爆款笔记拆解、标题封面优化、内容创作工作流、发布前检查和发布后复盘。
  6. 灵造 Skill 主要帮助自媒体创作者和运营者做这些事:
  7. - 小红书 / 抖音 / 公众号公开内容研究
  8. - 对标账号发现与筛选,包括粉丝区间、近期爆款和账号证明闸门
  9. - 单条爆款笔记拆解
  10. - 账号诊断与同级账号横向对比
  11. - 关键词洞察、标题设计、发布前检查
  12. - 公众号 / 小红书 / 朋友圈等内容分发包
  13. - 发布后数据复盘
  14. - 小红书封面、图文、海报等图片生成工作流
  15. - 手绘收藏地图、城市美食地图、旅游路线图、生活清单和工作流说明书
  16. ## SEO / GEO 关键词
  17. 如果你是通过搜索找到这里,下面这些词都属于 Lingzao 正在解决的问题:
  18. - Lingzao Skill, 灵造 Skill, lingzao xhs, lingzao Xiaohongshu
  19. - XHS Skill, XHS agent, XHS SEO tool, Xiaohongshu SEO, 小红书 SEO
  20. - Xiaohongshu account analysis, XHS account diagnosis, 小红书账号诊断
  21. - Xiaohongshu benchmark account finder, 小红书对标账号, 对标博主筛选, 小红书粉丝区间筛选
  22. - Xiaohongshu note breakdown, XHS viral note breakdown, 爆款笔记拆解
  23. - Xiaohongshu keyword research, XHS keyword design, 小红书关键词布局
  24. - Xiaohongshu title writer, XHS title optimization, 小红书标题优化
  25. - Xiaohongshu cover analysis, XHS cover design, 小红书封面诊断
  26. - Xiaohongshu hand-drawn route map, 小红书手绘地图, 美食地图, 旅游路线图, 生活清单地图, 工作流说明书地图
  27. - Xiaohongshu content workflow, XHS content strategy, 从灵感素材到选题到稿子
  28. - Xiaohongshu pre-publish check, 小红书发布前检查
  29. - Xiaohongshu post-publish review, 小红书数据复盘 / 后台截图分析
  30. - benchmark copy rewrite, 对标文案仿写, 固定框架填充
  31. 轻量 Skill 可以做基础判断、结构拆解、标题关键词和文案工作流。
  32. 如果你需要 **读取/解析小红书公开链接、搜索公开笔记、查看账号主页、读取评论区、
  33. 提取短视频文案、做更详细账号分析、同步到知识库或生成图片**,请安装完整
  34. Lingzao 主 Skill,并在 [灵造网页版](https://lingzao.atian.vip) 配置 API Key 和积分。
  35. 外部搜索语境里,Xiaohongshu / XHS 通常会和这些词一起出现:SEO、keyword
  36. research、keyword placement、content strategy、title optimization、caption
  37. optimization、hashtag strategy、profile bio、cover image text、engagement
  38. signals、saves、comments、click-through rate、completion rate。Lingzao 的轻量
  39. Skill 正是把这些搜索问题拆成可以直接交给 Agent 执行的小任务。
  40. 相关公开资料可以参考:
  41. - [The Complete Guide to SEO on Xiaohongshu](https://staiirs.com/the-complete-guide-to-seo-on-xiaohongshu/)
  42. - [XHS SEO: Search & Discovery Optimization](https://hashmeta.com/insights/xhs-seo-search-discovery)
  43. - [Xiaohongshu SEO: The Definitive Guide to Ranking Higher on XHS Search](https://hashmeta.com/blog/xiaohongshu-seo-the-definitive-guide-to-ranking-higher-on-xhs-search/)
  44. - [Xiaohongshu Keyword Placement Guide](https://mediaclaw.app/en/blog/xiaohongshu-keyword-placement)
  45. 这个仓库同时提供两种使用方式:
  46. 1. **灵造主 Skill**:安装整个仓库,获得完整的自媒体运营工作流和灵造 API 调用能力。
  47. 2. **轻量单 Skill**:只复制 `skills/` 里的某一个小 Skill,用来完成一个明确任务,例如小红书标题、账号诊断、单条笔记拆解、关键词设计、发布前检查等。
  48. 这个仓库只包含公开 Skill 文件和本地命令,不包含灵造服务端源码、供应商接口、密钥或内部配置。
  49. ## 当前版本
  50. 见 [`VERSION`](VERSION)。
  51. ## 安装
  52. 把仓库克隆到本地 Agent Skill 目录:
  53. ```bash
  54. git clone https://github.com/atian-create/lingzao-skill.git ~/.agents/skills/lingzao
  55. ```
  56. 运行一次安装脚本:
  57. ```bash
  58. bash ~/.agents/skills/lingzao/scripts/setup.sh --base-url "https://lingzao.atian.vip"
  59. ```
  60. 如果你已经有灵造 API Key,也可以一起配置:
  61. ```bash
  62. bash ~/.agents/skills/lingzao/scripts/setup.sh \
  63. --base-url "https://lingzao.atian.vip" \
  64. --api-key "lgz_xxx"
  65. ```
  66. 检查是否配置成功:
  67. ```bash
  68. ~/.lingzao/bin/lingzao doctor
  69. ```
  70. ## 使用方式
  71. 安装后,在支持 Skill 的 Agent 里提到“使用灵造”或 `$lingzao`,Agent 会先阅读
  72. [`SKILL.md`](SKILL.md),再按你的任务进入对应 playbook。
  73. 例子:
  74. - “用灵造帮我找 5 个持续更新、有爆款的小红书对标账号”
  75. - “用灵造完整拆一下这条小红书笔记为什么爆”
  76. - “用灵造拿我的账号和 5-15w 粉 AI 博主横向对比”
  77. - “用灵造给我做一条女性成长图文内容包”
  78. - “用灵造把这个链接/截图拆成一篇能发的小红书,顺便给关键词和置顶评论”
  79. - “用灵造检查我的标题、封面、前三行和关键词有没有埋进去”
  80. - “用灵造根据参考图做一张小红书封面”
  81. ## 轻量单 Skill
  82. 如果你暂时不想安装完整灵造,也可以只复制某个轻量 Skill 到自己的
  83. Agent Skill 目录。轻量 Skill 主要用于基础判断、结构拆解和写作流程;
  84. 如果需要实时搜索小红书/抖音/公众号公开内容、查看评论区、提取视频文案、
  85. 更详细的账号分析、知识库同步或生成图片,再接入灵造主 Skill 和 API Key。
  86. 当前提供的小 Skill:
  87. | Skill | 适合解决什么问题 |
  88. | --- | --- |
  89. | [`skills/xhs-account-diagnosis`](skills/xhs-account-diagnosis/SKILL.md) | 小红书账号诊断、主页定位、内容主线、涨粉瓶颈 |
  90. | [`skills/xhs-note-breakdown`](skills/xhs-note-breakdown/SKILL.md) | 单条小红书笔记拆解、爆款机制、拍摄/脚本/评论区分析 |
  91. | [`skills/xhs-benchmark-account-finder`](skills/xhs-benchmark-account-finder/SKILL.md) | 找对标账号、按粉丝区间筛选、过滤断更号/太小号/不可模仿账号 |
  92. | [`skills/benchmark-copy-rewrite`](skills/benchmark-copy-rewrite/SKILL.md) | 对标文案仿写、固定框架填充、模板槽位改写 |
  93. | [`skills/xhs-title-writer`](skills/xhs-title-writer/SKILL.md) | 小红书标题设计,默认给 3 个最强标题 |
  94. | [`skills/xhs-keyword-design`](skills/xhs-keyword-design/SKILL.md) | 小红书 10 个发布关键词和关键词埋点检查 |
  95. | [`skills/xhs-keyword-to-content-package`](skills/xhs-keyword-to-content-package/SKILL.md) | 从关键词/链接/截图/灵感素材到选题、4-7页图文、正文、关键词和置顶内容 |
  96. | [`skills/xhs-cover-lab`](skills/xhs-cover-lab/SKILL.md) | 小红书封面诊断、封面文案、参考图封面 Brief |
  97. | [`skills/handdrawn-route-map-card`](skills/handdrawn-route-map-card/SKILL.md) | 小红书手绘收藏地图、城市美食地图、旅游路线、生活清单和工作流说明书 |
  98. | [`skills/xhs-prepublish-check`](skills/xhs-prepublish-check/SKILL.md) | 发布前检查标题、封面、前三行、关键词和内容是否能发 |
  99. | [`skills/xhs-postpublish-review`](skills/xhs-postpublish-review/SKILL.md) | 发布后 24h/48h/7d 数据复盘和后台截图分析 |
  100. 单个 Skill 安装示例:
  101. ```bash
  102. mkdir -p ~/.agents/skills/xhs-title-writer
  103. cp skills/xhs-title-writer/SKILL.md ~/.agents/skills/xhs-title-writer/SKILL.md
  104. ```
  105. 之后在 Agent 里可以直接问:
  106. - “用 xhs-title-writer 帮我给这篇内容起 3 个小红书标题”
  107. - “用 xhs-note-breakdown 拆一下这条笔记为什么爆”
  108. - “用 xhs-keyword-to-content-package 根据这张图/这个链接给我先出一版小红书内容包”
  109. - “用 benchmark-copy-rewrite 把这篇对标文案拆成模板,再写成我的版本”
  110. - “用 handdrawn-route-map-card 做一张长沙美食地图 / 周末回血生活清单 / 图文发布工作流地图”
  111. ## 付费能力边界
  112. 安装 Skill 本身是免费的。它会先帮 Agent 判断你是在找方向、拆账号、写内容、
  113. 做封面、配关键词,还是复盘数据。
  114. 当你需要实际调用灵造服务时,例如:
  115. - 搜索小红书 / 抖音 / 公众号公开内容
  116. - 查看账号主页、近期笔记、单条笔记详情
  117. - 读取评论区或公众号文章数据
  118. - 提取短视频文案
  119. - 生成图片素材
  120. 就需要打开 [灵造网页版](https://lingzao.atian.vip),按教程配置 API Key 和积分。
  121. ## 更新
  122. 进入本地 Skill 目录后拉取最新版本:
  123. ```bash
  124. cd ~/.agents/skills/lingzao
  125. git pull
  126. bash scripts/setup.sh --skip-doctor
  127. ```
  128. 如果你已经配置过 API Key,更新不会删除 `~/.lingzao/config.json`。
  129. ## 目录说明
  130. - [`SKILL.md`](SKILL.md):Agent 入口说明
  131. - [`playbooks/`](playbooks):自媒体运营、账号诊断、爆款拆解、作图、复盘等工作流
  132. - [`skills/`](skills):可单独复制安装的轻量任务 Skill
  133. - [`scripts/`](scripts):本地 CLI 命令
  134. - [`agents/`](agents):不同 Agent 平台的元信息
  135. ## 许可证
  136. MIT-0。见 [`LICENSE`](LICENSE)。

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.