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.
npx skills add liucongg/liucong-skills --skill gzh-title-strategistgit clone --depth 1 https://github.com/liucongg/liucong-skillsWrote 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.
[](https://agentmods.dev/skills/liucongg/liucong-skills/gzh-title-strategist)<a href="https://agentmods.dev/skills/liucongg/liucong-skills/gzh-title-strategist"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/gzh-title-strategist/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.
<a href="https://agentmods.dev/skills/liucongg/liucong-skills/gzh-title-strategist"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/gzh-title-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.01184 |
| Opus 5 | $0.00044 | $0.00592 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
gzh-title-strategist 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 12d ago.
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.
What it actually says
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
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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：
- 文章真实结论或成果；
- 读者能获得的具体结果；
- 支撑结果的事实证据；
- 与正文强相关的数据关键词；
- 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：
- 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。
- 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。
- 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。
- 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
文章诊断：类型、读者、结论、证据、交付物、数据关键词依赖。标题策略：推荐句式、实体和关键词选择、语气。候选标题：按不同风格分组。前5名评分：使用紧凑表格。最终推荐：主标题、两个备选标题及理由。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。
What ships with it
5 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.
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.
- 12d ago First seen · 72 lines · 89 tokens per session scan A d31f9194d9fc
gzh-title-strategist is a skill published in the GitHub repository liucongg/liucong-skills (246 stars, last pushed 4d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,184 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…