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 hanzhcn/laohan-skills --skill laohan-fengmianqiuzhigit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-fengmianqiuzhi)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-fengmianqiuzhi"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-fengmianqiuzhi/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/hanzhcn/laohan-skills/laohan-fengmianqiuzhi"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-fengmianqiuzhi.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 | $0.00099 | $0.02159 |
| Opus 5 | $0.00049 | $0.01079 |
| Sonnet 5 | $0.00020 | $0.00432 |
| Haiku 4.5 | $0.00010 | $0.00216 |
Grade A, and why
laohan-fengmianqiuzhi 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
真人口播封面直接生成
目标:从口播稿提炼一个跨平台可成立的点击钩子,只使用秋芝方向,按推荐顺序直接生成3张“人物+场景+准确中文标题”的9:16视觉母版,再以默认01或 Jeffrey 明确改选的同一rank生成3张真实尺寸封面,共享到四平台7个逻辑入口。三个比例必须分别重新构图和生成,不把裁切或发布页临时取景当成适配。不要拆成无字底图、排字脚本、评分器或多阶段合成。
输入与边界
episode-config.schema_version为4;身份reference或稿件绑定不满足时停止,不自行改合同。- 读取当前
01-口播稿.md、12-发布/多平台发布内容.md和锁定的抖音发布信息。 - 人物参考固定为本期
05-封面/reference/jeffrey-reference.jpg,并作为 image reference 传给生图模型。 - ⑥先生成3张9:16完整候选,再为默认01生成3张共享真实尺寸封面;Jeffrey明确改选02或03时,⑫前必须为新rank重新生成这3张,旧rank成品不能混用。不允许简单裁掉人物、主物件或标题。
- 不在 prompt 中写“模仿某博主风格”。只使用
references/douyin-cover-study.md的秋芝观察和references/qiuzhi-template-library.md。 - 默认只生成3个秋芝方向候选;拉斐尔和柱子哥方向暂不进入默认输出。
- 三张按推荐程度从高到低排列为
01 → 02 → 03。没有Jeffrey明确改选时,后续发布自动化优先使用01作为发布封面的源候选。
执行
1. 提炼封面文字
从口播稿提炼:
主标题:4—10个汉字,最多两行;保留真正影响理解的产品名。辅助短句:0—8个汉字;主标题已经说清楚时不要添加。画面事件:Jeffrey正在做什么,他面对什么具体问题或结果。
禁止“AI神器”“效率翻倍”等可套用到任何选题的空话。封面文字不能超出口播稿事实。
2. 选择3个秋芝模板并排序
完整读取 references/douyin-cover-study.md 的秋芝部分和 references/qiuzhi-template-library.md,先按口播核心冲突筛选模板。
- 先在内部筛出语义最匹配的5—8个模板。
- 最终选择3个不同模板族;三张不能只是同一空间换衣服或换颜色。
- 每张独立遵守
1个基础模板 + 最多1个主物件机制。 - 按“口播钩子匹配度 → 手机缩略图辨识度 → 人物动作与主物件关系 → 与近期候选的差异”排序。
01必须是本期最推荐方案,不随机排序。 - 禁止凭“AI感”默认选择宇航员、驾驶舱、未来办公室或实验室;
CONDITIONAL_ONLY仍只在语义明确匹配时使用。
每条提示词都必须一次性描述:
- 9:16抖音完整封面;
- Jeffrey的身份、位置、表情、动作和服装;
- 与本期直接相关的一个主场景或主物件;
- 主标题和可选辅助短句的准确原文、断行、位置、颜色、粗黑描边;
- 该方向对应的版式规律;
- 禁止错字、多余文字、平台UI、水印、二维码、额外人物和无关装饰。
共用身份约束:
Use the supplied portrait as the non-replaceable identity reference for Jeffrey. Preserve his recognizable face shape, glasses, short hair, moustache and goatee, chin mole, skin tone and age impression. Exactly one Jeffrey.
共用文字约束:
Render only the following Chinese cover text, exactly as written, with no missing, substituted or extra characters: “[主标题]” and, only when provided, “[辅助短句]”. The Chinese text must be large, crisp, correctly spelled and readable at phone-thumbnail size. Do not render any other words, letters or numbers.
3. 直接生成3张
- 用3条提示词分别调用 image provider,并传入同一张 Jeffrey reference。
- 三张都生成9:16完整成图,按推荐顺序保存为
cover-01-qiuzhi-9x16.<ext>、cover-02-qiuzhi-9x16.<ext>、cover-03-qiuzhi-9x16.<ext>;ext只允许png、jpg、jpeg或webp。 - 完整成图直接保存到
05-封面/根目录;不创建backgrounds/,不运行后排字脚本。 - 如果中文错字、人物不像或主题画错,只修正原提示词并重生该张;不要增加新流程。
- 三张排序候选真实、可解码、9:16且命名符合顺序,并且默认01的3张共享尺寸成品全部真实可解码、尺寸正确后,才满足⑥机械门槛。人物身份、标题准确度、主题一致性、缩略图安全区必须在当前任务中逐张视觉复看后如实报告,但不新增review文件或生产阶段。
- Jeffrey可明确改选02或03;没有明确改选时,发布准备默认从01适配平台所需封面比例,不能静默改用02或03。
What ships with it
2 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 · 131 lines · 99 tokens per session scan A 95aae51cf281
laohan-fengmianqiuzhi is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 2,159 once invoked, about $0.0005 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
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'…
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…
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.
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.
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.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.