Agent skill

WeChat Article Title Strategist

by liucongg in liucongg/liucong-skills

Generates, rewrites, critiques and ranks titles for Chinese WeChat official account articles, grounded in the article's real content and any history data supplied.

Apache-2.0Auto-check passedWriting & Content

SKILL.md written in Chinese; this summary is our English description.

Install WeChat Article Title Strategist

skills CLI
$ npx skills add liucongg/liucong-skills --skill gzh-title-strategist -a claude-code

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

GitHub CLI
$ gh skill install liucongg/liucong-skills gzh-title-strategist --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/liucongg/liucong-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gzh-title-strategist .claude/skills/gzh-title-strategist && 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
gzh-title-strategist
GitHub stars
248
Token cost
~471 tokens
SKILL.md length
95 words
Files
6 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generates, rewrites, critiques and ranks titles for Chinese WeChat official account articles, grounded in the article's real content and any history data supplied.

  • Works in 8 steps: 阅读完整文章或用户提供的最完整稿件。处理 Word、PDF… → 诊断文章 → 根据内容类型读取… → …
  • Writing titles for a Chinese WeChat official account article
  • SKILL.md covers 工作流程, 标题决策顺序, 复盘已有标题 and 硬性规则, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The instructions are in Chinese. The agent reads the complete article, extracting text from Word or PDF files when needed, and diagnoses its type, target reader, one-line conclusion, strongest factual evidence, takeaway deliverables and the companies or products named in the body. It consults reference files on content types, title mechanics, heat research and empirical signals, and uses only historical article data or evidence you provide, so it must not invent current trending status or present past keyword correlations as recommendation rules.

Titles are generated in groups by click motive: steady and accurate, internet-style click-driven, professional and authoritative, data-keyword titles when data supports them, and long-lived ones. The top five are scored from 1 to 5 on click appeal, fact match, audience match, differentiation and long-term value with risks flagged, and one main title plus two alternatives are recommended. It can also review existing titles against same-account baselines, separating title factors from topic, timing and account factors, and it may not add claims, products or numbers the body does not support.

When your agent uses it

  • Writing titles for a Chinese WeChat official account article
  • Judging why an existing article title performed well or poorly
  • Deciding whether a trending keyword belongs in a title
  • Choosing between a statement and a question form for a title

Example prompts

  • “Write titles for this WeChat article about an open-source coding agent and rank the top five.”
  • “Review why last month's title got fewer reads than our usual posts.”
  • “Is it worth putting this trending keyword in the title, given what the article actually says?”

Workflow steps

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

  1. 阅读完整文章或用户提供的最完整稿件。处理 Word、PDF 时,调用对应文档能力提取正文。
  2. 诊断文章
  3. 根据内容类型读取 references/content-types.md,根据句式和标点需要读取 references/title-mechanics.md。
  4. 涉及热词、流量词或推荐池猜测时,读取 references/heat-research.md。只使用历史文章数据或用户提供的证据;不得虚构当前热度,不主动查询微信指数或跨平台热度。
  5. 排序关键词或使用数据规律时,读取 references/empirical-signals.md。历史相关性只能称为“流量锚点关联”,不能称为推荐池触发规则。
  6. 按不同点击动机生成标题,不做同一句话的表面替换
  7. 选出前 5 名,分别按 1~5 分评价:点击欲望、事实匹配、人群匹配、差异化、长期价值。标记标题党、术语堆砌、证据不足、标点过度和关键词过期风险。
  8. 推荐 1 个主标题和 2 个备选标题,说明各自对应的读者动机与适用场景。

What it can do on your machine

Read from SKILL.md and the folder at commit d08416a. 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.

    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

WeChat Article Title Strategist loads about 471 tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 95 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~471
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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

The full file from liucongg/liucong-skills at commit d08416a, republished under its Apache-2.0 licence (© liucongg). 95 words, ~471 tokens.

Download SKILL.mdSave it as .claude/skills/gzh-title-strategist/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
gzh-title-strategist
description
分析中文微信公众号文章,生成、改写、批评和排序标题。综合文章类型、目标读者、事实证据、网感表达、历史数据关键词和账号过往表现。适用于起公众号标题、分析标题好坏、生成爆款感/专业型/数据关键词型标题、选择肯定句或疑问句,以及判断热词是否值得进入标题。

公众号标题策略师

先从文章真实价值中提炼标题,再决定是否加入网感表达或历史高表现关键词。不得用热词替代内容价值。

工作流程

  1. 阅读完整文章或用户提供的最完整稿件。处理 Word、PDF 时,调用对应文档能力提取正文。
  2. 诊断文章:
    • 主要内容类型;
    • 目标读者及其当下问题;
    • 一句话结论、变化或结果;
    • 最强事实证据:数字、实测、作品、对比、来源、经历;
    • 可带走的交付物:教程、代码、提示词、清单、模型、方法;
    • 正文真实出现的公司、产品、模型和技术名词;
    • 文章对事件时效和数据关键词的依赖程度。
  3. 根据内容类型读取 references/content-types.md,根据句式和标点需要读取 references/title-mechanics.md。
  4. 涉及热词、流量词或推荐池猜测时,读取 references/heat-research.md。只使用历史文章数据或用户提供的证据;不得虚构当前热度,不主动查询微信指数或跨平台热度。
  5. 排序关键词或使用数据规律时,读取 references/empirical-signals.md。历史相关性只能称为“流量锚点关联”,不能称为推荐池触发规则。
  6. 按不同点击动机生成标题,不做同一句话的表面替换:
    • 4 个稳健准确型;
    • 4 个网感点击型;
    • 3 个专业权威型;
    • 有数据依据时生成 3 个数据关键词型;
    • 2 个不过度依赖时效的长期型。
  7. 选出前 5 名,分别按 1~5 分评价:点击欲望、事实匹配、人群匹配、差异化、长期价值。标记标题党、术语堆砌、证据不足、标点过度和关键词过期风险。
  8. 推荐 1 个主标题和 2 个备选标题,说明各自对应的读者动机与适用场景。

标题决策顺序

按以下顺序取舍,后面的因素不得破坏前面的因素:

  1. 文章真实结论或成果;
  2. 读者能获得的具体结果;
  3. 支撑结果的事实证据;
  4. 与正文强相关的数据关键词;
  5. 网感措辞、节奏和标点。

复盘已有标题

当用户要求分析标题好坏或结合阅读数据复盘时:

  1. 先与同账号、相近月份和相似内容类型比较,避免直接跨账号比阅读量。
  2. 同时检查选题热度、账号基线、发布时间、事实证据、关键词、句式、网感和交付物。
  3. 将原因分为“标题因素”“选题/时机因素”“账号/分发因素”“暂时无法判断”,不要把爆款全部归因于标题。
  4. 同时选取高表现和低表现样本,说明哪些写法有效、哪些无效以及可能的混杂因素。

硬性规则

  • 正文没有依据时,不得添加公司、产品、评测、数字、结果、“官方”“首个”“最强”或“开源”。
  • 不得把历史相关关键词说成微信推荐算法或推荐池触发词。
  • 一个标题优先保留一个主承诺;第二分句只能补充证据、结果或交付物。
  • 把辨识度最高的实体和核心变化放在前部,避免被折叠后失去信息。
  • 网感必须具体,优先使用“冲突或变化+人的行动+具体结果”,避免空洞夸张。
  • 保留作者原有语气。技术型、反思型、机构型和个人型文章使用不同口语浓度。
  • 只有缺失信息会实质改变标题时才追问;否则基于明确假设直接生成。

默认输出

  1. 文章诊断:类型、读者、结论、证据、交付物、数据关键词依赖。
  2. 标题策略:推荐句式、实体和关键词选择、语气。
  3. 候选标题:按不同风格分组。
  4. 前5名评分:使用紧凑表格。
  5. 最终推荐:主标题、两个备选标题及理由。
  6. 风险提示:无依据表述、关键词堆砌、标点、时效风险。

用户只要求标题时,把文章诊断压缩到三行以内,但仍应提供实质不同的选项。

© liucongg, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/gzh-title-strategist of liucongg/liucong-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/content-types.md
  • references/empirical-signals.md
  • references/heat-research.md
  • references/title-mechanics.md

Open the folder on GitHubat commit d08416a

Compare with similar skills

WeChat Article Title Strategist 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.

WeChat Article Title Strategist compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
WeChat Article Title Strategist this skillliucongg/liucong-skills248—~471Automated safety check: PassApache-2.0
WeChat Account Topic and Title WriterBigPengSays/bigpeng-hot-gzh266—~501Automated safety check: PassMIT
WeChat Article Topics and Titlesaiworkskills/wechat-article-skills672—~1.3kAutomated safety check: PassApache-2.0
Money Contentiamzifei/show-me-the-money1k—~9.6kAutomated safety check: PassCustom licence
37 Social Caption Globalminhnv0807/ai-business-skills609—~2.2kAutomated safety check: PassMIT
Social Media Pro Maxcriptogus/agent-evolve-network288—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • WeChat Account Topic and Title Writer

    BigPengSays/bigpeng-hot-gzh

    Produces topic directions and candidate headlines for WeChat official account articles using seven title formulas, without writing the article itself.

    266 GitHub stars~501 tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • WeChat Article Topics and Titles

    aiworkskills/wechat-article-skills

    Researches topics, titles, digests and series plans for WeChat Official Account articles; used on its own only to revise titles or digests that already exist.

    672 GitHub stars~1.3k tokensUpdated 18 days ago
    Writing & ContentAuto-check passed
  • Money Content

    iamzifei/show-me-the-money

    Automated content creation pipeline for business growth. An agent skill from iamzifei/show-me-the-money.

    1k GitHub stars~9.6k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • 37 Social Caption Global

    minhnv0807/ai-business-skills

    A skill your agent uses when the user needs ORGANIC social captions for Instagram, LinkedIn, TikTok, Facebook, or X — hook, mobile-readable body, two A/B variants, platform-correct hashtags, written…

    609 GitHub stars~2.2k tokensUpdated 29 days ago
    Writing & ContentAuto-check passed
  • Social Media Pro Max

    criptogus/agent-evolve-network

    State-of-the-art viral content + social design intelligence.

    288 GitHub stars~1.6k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • X Algorithm Post Writing

    carson2222/skills

    Writes and reviews X posts, threads and replies using what the open-sourced For You ranking system rewards, and explains why a post may have underperformed.

    113 GitHub stars~3.8k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed

More from liucongg/liucong-skills

  • Design-Led Website Builder

    liucongg/liucong-skills

    Turns a short brief into a researched, distinctive website: lock the intent with at most one question, research live reference sites, source materials, then build and verify.

    248 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Traceable Model Evaluation

    liucongg/liucong-skills

    Sets up and runs side-by-side model evaluations with frozen questions, isolated tools and traceable results, using your own question bank or benchmark subsets.

    248 GitHub stars~752 tokensUpdated 1 mo ago
    Auto-check passed
  • Painterly 3D2 Cinema Prompts

    liucongg/liucong-skills

    Expands one sentence into a prompt package for painterly 3D-to-2D short films: story, 15-second segments, characters, scenes, Midjourney storyboards and Seedance video prompts.

    248 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • LLM Wiki Operations

    liucongg/liucong-skills

    Maintains an LLM Wiki in a Feishu knowledge base: initial setup, ingesting sources and articles, answering queries, health checks and entry upkeep.

    248 GitHub stars~898 tokensUpdated 1 mo ago
    Auto-check passed

Questions about WeChat Article Title Strategist

What does WeChat Article Title Strategist do?

Generates, rewrites, critiques and ranks titles for Chinese WeChat official account articles, grounded in the article's real content and any history data supplied. The instructions are in Chinese. The agent reads the complete article, extracting text from Word or PDF files when needed, and diagnoses its type, target reader, one-line conclusion, strongest factual evidence, takeaway deliverables and the companies or products named in the body.

When should I use WeChat Article Title Strategist?

WeChat Article Title Strategist fits situations like: writing titles for a Chinese WeChat official account article; judging why an existing article title performed well or poorly; deciding whether a trending keyword belongs in a title; choosing between a statement and a question form for a title.

How do I install WeChat Article Title Strategist in Claude Code?

Run `npx skills add liucongg/liucong-skills --skill gzh-title-strategist -a claude-code`. Or copy the skill folder (skills/gzh-title-strategist in liucongg/liucong-skills) into .claude/skills/gzh-title-strategist in your project. Claude Code loads it when a task matches its description.

How do I install WeChat Article Title Strategist in Codex?

Run `npx skills add liucongg/liucong-skills --skill gzh-title-strategist -a codex`. Or copy the skill folder (skills/gzh-title-strategist in liucongg/liucong-skills) into .agents/skills/gzh-title-strategist in your project. Codex loads it when a task matches its description.

Can I use WeChat Article Title Strategist 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 liucongg/liucong-skills --skill gzh-title-strategist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gzh-title-strategist, .gemini/skills/gzh-title-strategist, .github/skills/gzh-title-strategist and .opencode/skills/gzh-title-strategist in your project.

What does WeChat Article Title Strategist need to run?

SKILL.md names no scripts, command-line tools or credentials: WeChat Article Title Strategist is instructions for the agent only.

Does WeChat Article Title Strategist 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 WeChat Article Title Strategist 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 WeChat Article Title Strategist use?

WeChat Article Title Strategist is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does WeChat Article Title Strategist use?

About 471 tokens (SKILL.md is roughly 1.9k 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 3k tokens, read only when the agent opens those files.

What are the alternatives to WeChat Article Title Strategist?

Skills that share tags, products or a category with WeChat Article Title Strategist: WeChat Account Topic and Title Writer (BigPengSays/bigpeng-hot-gzh, 266 stars), WeChat Article Topics and Titles (aiworkskills/wechat-article-skills, 672 stars), Money Content (iamzifei/show-me-the-money, 1k stars) and 37 Social Caption Global (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains WeChat Article Title Strategist?

liucongg (a GitHub user) maintains it in liucongg/liucong-skills, which has 248 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 8, 2026.

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