laohan-xuanti

laohan-xuanti is a skill for Claude Code from hanzhcn/laohan-skills. It costs 172 tokens per session (5,012 once invoked), scanned A, original, MIT.

A content-planning workflow for choosing topics for short spoken videos, especially on Douyin, the Chinese short-video platform. It compares current signals, competing angles, audience needs, and original sources before selecting a topic.

In plain words
What is it for?
Use it to find timely AI or software topics, check whether similar videos already exist, choose an angle, and prepare evidence for production and later review.
Why use it?
It reduces the risk of choosing a topic only because it appears popular or has misleading engagement data. It records why a topic was selected, rejected, or split into a series.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to find timely AI or software topics, check whether similar videos already exist, choose an angle, and prepare evidence for production and later review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hanzhcn/laohan-skills/laohan-xuanti
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 hanzhcn/laohan-skills --skill laohan-xuanti
Clone the repo
git clone --depth 1 https://github.com/hanzhcn/laohan-skills

Made for: Claude Code.

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 laohan-xuanti

README.md
[![agentmods](https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-xuanti/github.svg)](https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-xuanti)
Your own site
<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-xuanti"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-xuanti/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 laohan-xuanti

Your own site · 80×15
<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-xuanti"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-xuanti.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00172 $0.05012
Opus 5.5 $0.00069 $0.02005
Sonnet 5.5 $0.00034 $0.01002
Haiku 4.5 $0.00017 $0.00501

Measured 26d ago against content hash 2a626ea99a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

laohan-xuanti scanned grade A with 0 findings 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 26d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check-topic-contract.mjs, scripts/collect-topic-signals.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

laohan-xuanti/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

①选题决策

热点只用于发现,最终结果是一个可审计的生产决策:为什么现在做、给谁看、论点凭什么成立、抖音上有哪些重复角度、为什么淘汰其他候选,以及发布后如何按固定窗口复盘。

边界

  • 本 skill 是①唯一主写者,写 signals、candidates、source-health 和 00-选题.*。
  • laohan-douyinsousuo 只写 00-抖音搜索证据.{json,md};同一 Agent 宿主按 bianpai 路由执行,不做 programmatic skill-to-skill 调用。
  • ②才写口播稿;①不生成正文、大纲段落或封面。
  • ⑤才做完整事实核验;①仍须给最终事实前提找到至少一条 PRIMARY 原始来源。
  • 不安装新浏览器、爬虫、Python runtime 或第三方 skill。抖音平台访问只用已安装 OpenCLI。
  • 同一事件可以形成观点候选和教程候选;受众任务、标题承诺和内容路径真正不同时可分别参加比较。②—④沿用选中 lane,不混写。

输入

Episode 模式必须读取:

  1. 本期 episode-config.json 与 00-编排/ 冻结产物。
  2. 本期已显式登记的反馈快照;没有就记录 NOT_AVAILABLE,不得扫描旧 episode 猜经验。
  3. 本轮真实 signals 与抖音搜索证据。

标准 Episode 为 AUTO_SELECT:AI按五步法完成发现、过滤与定题, Jeffrey 保留事后否决权(00-选题-Jeffrey否决.json,否决原因必填,否决后按原因重新扫描)。Jeffrey 明确给题时走 USER_SEED,仍须给出至少一个真实替代候选、抖音取证、PRIMARY 证据和测量合同。

Jeffrey给出的是软件、方法或系列方向时,先走USER_DIRECTION_RESEARCH:读取项目docs/系列选题研究与分期规格.md,完成四平台定向搜索、内容级拆解、需求判断、系列分期和单期资料包。它不运行与方向无关的9账号泛扫描来凑热度。只有DEMAND_VALIDATED可进入三期以上系列,EXPERIMENTAL_ONE_OFF只进入单期,DIRECTION_REJECTED停止。正式episode仍须提供替代候选。

工作流

1. 采集当前信号

先写00-选题-signals.json.discovery_mode:无方向为AUTONOMOUS_SCAN;Jeffrey已给方向为USER_DIRECTION_RESEARCH。后者把已通过node scripts/check-series-research.mjs的series_research_path与SHA写入direction_research,并把哔哩哔哩、小红书、抖音、知乎四路结果分别登记为signals来源。DEMAND_VALIDATED至少两个平台有真实需求信号;EXPERIMENTAL_ONE_OFF只按研究包内已验证的官方新事件、Jeffrey亲历或小众任务依据进入单期,不强制伪造两个平台热度。

Episode 模式执行唯一确定性入口:

node ~/Documents/laohan-skills/laohan-xuanti/scripts/collect-topic-signals.mjs \
  --episode episodes/<slug>

AUTONOMOUS_SCAN按五步法第1步扫爆款:数据层/tracked-creators.json全池逐账号扫描(ACTIVE必扫且失败阻断;PENDING一并扫描供交叉印证,失败如实记录不阻断)、数据层/self-channel.json自频道异常倍数(自己异常倍数高的方向优先深挖)、全面热点(辅助输入)与script-pool/Jeffrey个人表达池.md(素材来源)。扫描同时执行时间分层(近30天异常=当下需求优先做;3个月前异常=常青题,需再验证当下热度)与异常分级(3倍=值得注意,10倍以上=大机会优先深挖),并消费每条异常的top_comments高赞评论——高赞评论是观众没被满足的问题,直接作为候选线索。默认发现与展示优先级为BENCHMARK_CREATOR(1) > SELF_CHANNEL(2) > BROAD_HOTSPOT(3) > PERSONAL_EXPRESSION(4)。全面热点默认 route 为 AIHOT、Hacker News、知乎、微博、36kr、B站、抖音热榜、头条、贴吧和虎扑;某一路失败如实记录,其他热点路继续。需要缩小热点route时才传 --sources,不能借此跳过达人库和自频道。

Read the full file on GitHub · 179 lines

Files

What ships with it

3 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. 26d ago First seen · 179 lines · 172 tokens per session scan A 2a626ea99a1d

Subscribe to this mod's changes

laohan-xuanti is a skill published in the GitHub repository hanzhcn/laohan-skills (13 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 5,012 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.

Related

Other skills, from other repositories

douyin-upload

A workflow for using the sau command-line tool to log in to Douyin, the Chinese short-video platform, check account cookies, and publish videos or image-and-text posts.

dreammis/social-auto-upload · 93 tokens

kuaishou-upload

A workflow for using the sau command-line tool to log in to Kuaishou, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.

dreammis/social-auto-upload · 92 tokens

xiaohongshu-upload

A workflow for using the sau command-line tool to log in to Xiaohongshu, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.

dreammis/social-auto-upload · 95 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

officecli-data-dashboard

Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…

iOfficeAI/OfficeCLI · 159 tokens

invest

First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…

longsizhuo/openInvest · 261 tokens