agentmods.dev

laohan-fengmianzhuzige

laohan-fengmianzhuzige is a skill for Claude Code, Codex from hanzhcn/laohan-skills. It costs 140 tokens per session (2,844 once invoked), scanned A, original, MIT.

A cover-design workflow for creating vertical short-video covers from an AI or object background, a real person photo, and designed text layers. It defines a specific visual production process and checks the final image for layout and legibility issues.

In plain words
What is it for?
Use it to make 3:4 covers for spoken-video episodes from a script, background material, and a supplied portrait or posed photo.
Why use it?
It keeps the person, background, and typography under separate control instead of relying on one generated image to get every detail right. It also catches problems such as poor cropping, blocked faces, and unreadable text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 13repo +1 yesterday A scan 140 tokens original MIT

Good fit Use it to make 3:4 covers for spoken-video episodes from a script, background material, and a supplied portrait or posed photo.

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

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 laohan-fengmianzhuzige

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-fengmianzhuzige"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-fengmianzhuzige.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,844 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 $0.00140 $0.02844
Opus 5.5 $0.00056 $0.01138
Sonnet 5.5 $0.00028 $0.00569
Haiku 4.5 $0.00014 $0.00284

Measured 26d ago against content hash 63b1a71c7363, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

laohan-fengmianzhuzige 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 1 executable file (scripts/build_cover.py), 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-fengmianzhuzige/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

柱子哥式封面：三层合成 v6.1（定版）

v6.1定版（Jeffrey验收2026-09-20）：samples/shoucuogongju-v62-final.jpg（SHA-256前缀aeb933ed）为风格基线样张——OPPO形象照（藏青衬衫+眼镜+胡茬）+全栈v6.2（3:4材质字+左中证据卡EvidenceCard+右上MiniStamp小章+人物提亮档）。定版参数基线=samples/brief-example.json：人物提亮档（env_brightness 0.66/saturation 0.78/tint 0.26/face_boost 1.7/弱scrim 160）+text_top 748+kicker 236+证据卡三行（内容取自当期口播稿深水区清单）。同日实测教训：暗场单侧光素材（微信头像照）若脸的一半在暗部+裁切不当会"脸看不全"——素材验收第一优先级=脸完整明亮可见，其次才是光比融入；定版因此回到亮场形象照+提亮档路线。出厂检查纪律：三段放大逐字转录+关键边界像素级检测（章×脸间隙、脸区零遮挡、无全黑行），不得只靠整体打分。

路线定义（81张真实封面逐张检视实证 + 2026-09-20复刻实测）：柱子哥封面不是整幅AI生成，是三层合成——①AI生成/UI截图的无字背景物件板；②他本人真实照片（每期服装姿势不同，脸100%一致靠真人）；③设计工具排版的五层文字系统；合成后整图统一调色（冷调暗调ONE GRADE——先合成后调色，人物与环境才是一张照片）。2026-01他本人试过"AI生成整幅含人物"（#03/#04）后放弃，2026-03起全部转为三层合成。本skill用同一结构复刻。

历史教训链：v2.0误判"纯抽帧"（抓错图层）→ v3.0误改"AI单pass生成整幅海报"（身份不像/英文错字ERLY/版式失控三硬伤实测）→ v4.0三层合成确立 → v4.x小窗/抠像"贴纸感"翻车 → v5.1定案env_photo唯一正解 → v6.0实测钉死三个非参数级瓶颈并逐项修掉：(a)画幅错位——参考系81张全部3:4(covers_real 323x430)而产物曾是9:16，画幅改为1080x1440原生；(b)文字材质——PIL平面填充=PPT感，改为Remotion静帧渲染材质字（与正片HUD同源组件，templates-v2已验收）；(c)素材光线——亮场平光照片压暗后=灰暗监控感（v6加入机器可判的亮场预检），暗场摆拍是env_photo路线的硬前提。

输入与前置

  1. 当前 01-口播稿.md：取hook句+主记忆点→转标题组；
  2. 真人帧：封面专门摆拍优先（暗场+单侧实用灯+讲解手势，见下方"素材光线准入"）；无摆拍时用 07-剪辑/raw.mp4 hook时段抽帧（无烧录字幕，用raw-transcript.json定位时刻）；备选本期reference身份照；
  3. episode-config.schema_version 为4，绑定不满足时停止。

素材光线准入（v6硬门槛，机器可判）

env_photo源裁区在build时自动测光：mean>115 且 p95-p5<110 = 亮场平光→打WARN提示预期灰暗监控感；brief.strict_light=true时直接拒绝。这不是调参能救的：柱子哥照片的前提是暗场+实用灯（融入六法实证"他的房间是暗场"），亮房间压暗只是变灰不是变暗场。正确解法=按"补拍清单"（references/）重拍，不是继续调brightness。

标题组（五层文字系统，逐条落字后再动工）

  1. 英文眉题：顶部小字大写宽字距，概括主题（如 "EARLY WIN IS BAIT"），可配中文副题一行（Eyebrow组件双语）；
  2. 白色引导行：语境句6-10字（如"AI手搓的早期成功"）；
  3. 特大强调kicker：一个词3-6字超大粗黑（如"是个诱饵"），字符高≈画布高16-18%——语义色四选一：金#F5C518默认/金钱结论，红#E04545负面质疑否定，蓝#3B82F6科技品牌，绿#22C55E开源赚钱正面（紫在81张实证中几乎不用）；
  4. 高亮条/贴纸：黄底黑字条或红/绿tag一句副信息（如"该撞的墙我都撞了"）；右上角可加贴纸章（StampRed，密度填充四角）；
  5. 底部英文脚注：品牌行 "LAOHAN AI · CASE FILES NO.XX" 式小字宽字距。
  6. 品牌chip卡（左上，眉题下方）：圆角描边小卡"老韩AI | LAOHAN.AI · CASE 01"。
  7. 标题栈左对齐（align=left，left_x≈64）：对齐原版下部大字块的左对齐排法，行距收紧。

Read the full file on GitHub · 63 lines

Files

What ships with it

8 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 · 63 lines · 140 tokens per session scan A 63b1a71c7363

Subscribe to this mod's changes

laohan-fengmianzhuzige is a skill published in the GitHub repository hanzhcn/laohan-skills (13 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 2,844 once invoked, about $0.0006 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.

Claude CodeCreative and mediaDesign and UXai-contentbilibilidouyinopenclawskills
Related

Other skills, from other repositories

core-components

Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.

agent-skills-hub/agent-skills-hub · 27 tokens

build-webgl-liquid-glass

Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.

agent-skills-hub/agent-skills-hub · 44 tokens

build-sdf-liquid-glass

Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.

agent-skills-hub/agent-skills-hub · 42 tokens

lark-slides

A tool for creating and editing Feishu slide presentations, including their pages and content. Feishu is a workplace collaboration platform.

davidtoby/agent-skills · 156 tokens

baoyu-infographic

A generator for infographics that combines one of 21 information layouts with one of 21 visual styles.

davidtoby/agent-skills · 23 tokens

beautiful-feishu-card

Generate modern, elegant, and highly readable Feishu Interactive Cards (Schema 2.0 JSON) wrapped for CardKit (.card). Uses strict design system rules: 12 header color themes, color palette harmony (≤3 main colors), structured layouts (columnset, dividers, callout markdown), interactive preview messaging via lark-cli…

davidtoby/agent-skills · 81 tokens