lingzao

lingzao is a skill for Claude Code, Codex from EthanYoQ/Skill-hub. It costs 141 tokens per session (8,659 once invoked), scanned A, original, MIT.

A toolkit for researching and producing public creator content for Xiaohongshu, Douyin, and WeChat official accounts. Xiaohongshu, also called XHS, is a Chinese social platform focused on lifestyle and creator posts.

In plain words
What is it for?
Use it to search posts and creators, inspect recent public content and metrics, research keywords, break down popular posts, and prepare titles, cover text, post copy, keywords, and related materials.
Why use it?
It reduces the manual work of finding public posts, studying competing accounts, researching search terms, and turning source material into a content plan. It also keeps research and content drafting in one workflow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to search posts and creators, inspect recent public content and metrics, research keywords, break down popular posts, and prepare titles, cover text, post copy, keywords, and related materials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ethanyoq/skill-hub/lingzao
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add EthanYoQ/Skill-hub --skill lingzao
Clone the repo
git clone --depth 1 https://github.com/EthanYoQ/Skill-hub

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lingzao

README.md
[![agentmods](https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lingzao/github.svg)](https://agentmods.dev/skills/ethanyoq/skill-hub/lingzao)
Your own site
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/lingzao"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lingzao/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lingzao

Your own site · 80×15
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/lingzao"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lingzao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.08659
Opus 5 $0.00071 $0.04330
Sonnet 5 $0.00028 $0.01732
Haiku 4.5 $0.00014 $0.00866

Measured today against content hash 5ed2e412c03c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

lingzao scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L "$subtitle_markdown_url" -o /tmp/lingzao-profile-subtitles.md
archives/user-installed-skills/lingzao/b256a2fa1d5c12dc/lingzao/SKILL.md · 616 lines

How it starts

The opening of the file, as written. The whole thing — 616 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lingzao

Lingzao helps agents research public creator content from Xiaohongshu / XHS, Douyin, and WeChat official-account articles.

Search phrases this Skill is designed to support: Lingzao Skill, lingzao xhs, Lingzao Xiaohongshu, XHS SEO, Xiaohongshu SEO, Xiaohongshu account analysis, XHS account diagnosis, Xiaohongshu keyword research, XHS title optimization, Xiaohongshu viral note breakdown, Xiaohongshu benchmark account finder, XHS content workflow, hand-drawn route map card, 手绘收藏地图, 美食地图, 旅游路线图, 生活清单地图, and 工作流说明书地图.

Use this skill when the user asks to:

  • Search Xiaohongshu notes by keyword.
  • Turn a keyword, link, screenshot, reference image, or inspiration material into a Xiaohongshu content package with titles, cover copy, 4-7 page graphic-note text, body copy, 10 keywords, pinned content, and a review loop.
  • Get Xiaohongshu search suggestions or popular recommendations.
  • Search public creators by keyword.
  • Look up a creator profile.
  • Read a creator's recent public posts.
  • Get recent post copy, subtitles, covers, metrics, and commercial signals from a creator profile.
  • Get details for a Xiaohongshu or Douyin post.
  • Get top-level public comments for one Xiaohongshu or Douyin post.
  • Get one WeChat official-account article's public detail and text.
  • Get public metrics for one WeChat official-account article.
  • Get related public WeChat official-account articles.
  • Extract spoken copy or transcript from a public short-video link.
  • Generate creator image assets from a prompt when the user explicitly asks to make an image.
  • Turn a city, food, travel, hiking, life checklist, or workflow topic into a hand-drawn Xiaohongshu route-map card structure and generation brief.

Use the lightweight sub-skills under skills/ when a user only needs a single task such as XHS title writing, Xiaohongshu account diagnosis, keyword design, note breakdown, cover lab, hand-drawn route-map card, pre-publish check, or post-publish review. Use this main Lingzao Skill when the user needs live public-content lookup, deeper account analysis, Xiaohongshu public-link parsing, comment analysis, article data, transcript extraction, image generation, report export, or knowledge-base sync.

Read the full file on GitHub · 616 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 616 lines · 141 tokens per session scan A 5ed2e412c03c

Subscribe to this mod's changes

lingzao is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 8,659 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.