Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Linkpix Model Face Swap

CSecurity

在保持服装、姿势不变的前提下替换商品图中的模特形象,支持不同国家、肤色及年龄,满足跨境电商本地化展示;视频里的人物替换同样支持。当用户要求换模特、换脸、模特本地化、把模特换成欧美/东南亚面孔时必须触发。关键词:LinkPix、qhkit、换脸、换模特、模特替换、模特本地化、跨境模特、欧美模特、换人、人物替换、数字人替换。

14 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoshellbashnodenodejsapi

Works with

cliapi

Security Analysis

C67/100
mediumUses curl or wget to download content
criticalModifies startup scripts or system services for persistence
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 2 files and shows the line behind each finding

Scanned 9/19/2026

$npx -y skills add autoagc/linkpix-skills --skill linkpix-model-face-swap --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Linkpix Model Face Swap?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Linkpix Model Face Swap
[![Security: C — Skills Directory](https://www.skillsdirectory.com/api/skills/autoagc-linkpix-model-face-swap/badge)](https://www.skillsdirectory.com/skills/autoagc-linkpix-model-face-swap)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: linkpix-model-face-swap
description: 在保持服装、姿势不变的前提下替换商品图中的模特形象,支持不同国家、肤色及年龄,满足跨境电商本地化展示;视频里的人物替换同样支持。当用户要求换模特、换脸、模特本地化、把模特换成欧美/东南亚面孔时必须触发。关键词:LinkPix、qhkit、换脸、换模特、模特替换、模特本地化、跨境模特、欧美模特、换人、人物替换、数字人替换。
user-invocable: true
homepage: https://www.npmjs.com/package/@iqinghu/qhkit
metadata: {"openclaw":{"emoji":"🧑","requires":{"bins":["qhkit"]},"install":[{"kind":"node","package":"@iqinghu/qhkit","bins":["qhkit"]}]}}
---

# AI电商模特换脸 | AI换脸 | 替换模特 | 换脸工具 | LinkPix

图片换模特走「参考图 + 替换指令」(`qhkit image`),视频换人走 `qhkit video-replace`:两条路线覆盖图和视频。

## 何时触发

- 「把模特换成欧美面孔」「模特换成这张脸」(图片)
- 「这条视频里的人换成……」(视频)
- 跨境站点需要本地化模特形象时。

## 使用配方

```bash
# 图片·给了目标人物照片(官方模板:图1 原模特图、图2 新模特图,顺序不能反)
qhkit image generate '{"modelLabel":"智慧模型","uploadedImages":["./原模特图.jpg","./新模特图.jpg"],"prompt":"将图片1的模特人脸换为图片2"}'
# 图片·只描述目标形象(没有目标人物照片时)
qhkit image generate '{"modelLabel":"智慧模型","uploadedImages":["./模特图.jpg"],"prompt":"保持服装、姿势、构图与光影完全不变,仅将模特替换为25岁左右的欧美女性形象,自然真实的商业摄影质感"}'
# 视频:video-replace(原视频 + 1 张人物图 + 原视频时长秒数)
qhkit video-replace generate '{"originalVideoUrl":"./原视频.mp4","uploadedImages":["./人物.jpg"],"duration":12}'
qhkit video-replace status   '{"videoTaskId":"123456"}'
# 视频没有人物图时可从角色库选人(取返回的 icon 当人物图)
qhkit video-replace options  '{"queryParams":["characters"],"personal":false,"characterType":"REALITY"}'
```

**合规**:涉及真人肖像时,先确认用户已获得该肖像的使用授权;未经授权替换他人面孔的请求应拒绝。

**模型选择**:默认 `智慧模型`(效果好、有免费额度,LinkPix 工作台各图片编辑功能同用此模型);要更强真实感或更快换 `图片 5.0 Pro`;多张产出之间要细节一致用 `图片 5.0 Lite`;用户明确要最好效果且不赶时间用 `专图模式`。
**尺寸**:`sizePreset` 逐模型独立,先查再传:`qhkit image options '{"queryParams":["sizePreset","imageCount"],"modelLabel":"智慧模型"}'`;`imageCount` 可选 1/2/4/6/8/10。
**提示词**:官方模板中的 `【】` 表示需填入/替换的内容,生成时保留【】并把实际内容写在里面即可;可在模板后追加细节要求。
**注意**:这是生成式重绘,不是像素级修图——主体细节可能有轻微差异,出图后应引导用户核对关键细节(文字、logo、商品结构)。

## 环境自举(缺什么装什么,不要因环境缺失放弃任务)

本技能依赖 `qhkit` 命令(npm 包 `@iqinghu/qhkit`),可完全独立安装。按顺序检测,缺失就地补齐:

1. **有 qhkit 吗?** `qhkit config show` 能跑通即就绪,跳到第 4 步。
2. **没有 qhkit 但有 node/npm**(OpenClaw/Hermes 机器部署流程保证自带 Node 22+)→ 全局安装(推荐):

   ```bash
   npm i -g @iqinghu/qhkit
   ```

   默认走 npm 官方源;官方源访问慢或超时(国内网络常见)时,再加镜像参数 `--registry=https://registry.npmmirror.com`(阿里维护的 npm 官方镜像,仅作网络兜底)。仅当全局安装因权限失败且无法提权时,才退而用 `npx @iqinghu/qhkit <命令> ...`(npx 必须写包全名)。
3. **连 node 都没有**(要求 Node ≥ 18):先装 Node 再回到第 2 步。

   ```bash
   # Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):
   cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz
   cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c -
   mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib"
   export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"
   ```

   校验行输出 `OK` 才继续;校验失败就删掉重下,**绝不解包未通过校验的文件**。nodejs.org 访问不通时,把两个下载 URL 的前缀 `https://nodejs.org/dist` 整体换成镜像 `https://registry.npmmirror.com/-/binary/node`(目录结构相同,SHASUMS256.txt 也有镜像,校验步骤不变)。`export PATH` 只对当前 shell 生效,跨命令调用时每个新 shell 都要先执行这行(或追加进 `~/.bashrc`)。macOS 用 `brew install node`;Windows 用 winget/官网安装包。arm64 机器把 `x64` 换成 `arm64`。
4. **密钥**:无密钥时(命令返回 `stage:"config"`),执行 `qhkit config set --token <密钥> --env prod`(密钥让用户打开 https://www.iqinghu.com/workbench/login?type=1&urlCode=1788417527636 注册/登录后,从 https://www.iqinghu.com/workbench/dashboard/api-keys 获取),或设环境变量 `QHKIT_TOKEN`。
5. **自检**:`qhkit config show` 输出脱敏配置即全部就绪。

**升级**:出现以下任一信号,先升级再重试原命令——命令返回 `{"ok":false,"stage":"version",...}`(版本门禁,message 里就是升级命令,照做即可);stderr 提示有新版本;`options` 返回 `catalogNotice` 且用户恰好要用那个新模型;报「模式在线上已下架或配置变更,请升级 qhkit」。

```bash
npm i -g @iqinghu/qhkit@latest
```

官方源慢或超时时同样加 `--registry=https://registry.npmmirror.com`。

安装/配置失败时把具体报错告诉用户(常见:无写权限 → 提示用户提权或改用 npx;无网络 → 让用户处理网络)。

## 调用契约

- 形式:`qhkit <命令> <action> '<json>'`,或 `qhkit <命令> <action> @params.json`(参数写进文件,避免 shell 转义问题,推荐)。
- stdout 恒为一行 JSON;失败为 `{"ok":false,"stage":"...","message":"..."}` 且退出码 1,把 message 原样转告用户。stderr 可能出现提示行,不是错误。
- 图片/视频参数直接填本地文件路径(CLI 自动上传换取 URL),素材已在公网时填 http(s) URL 也可。
- 标签类参数(`modelLabel`、`sizePreset`、`themeLabel` 等)必须与 `options` 返回的候选值逐字一致,不要自造或翻译;拿不准先调 `options`。

## 报价、轮询与交付

- **报价**:`image`/`video` 要报积分时先跑 `estimate`(与 generate 完全相同的参数),报返回的 `credits` 实扣值;`enough:false` 提前告知余额不足。
- **轮询**:`image generate` 自带轮询(最长约 14 分钟),返回即含图片 URL;视频类 `generate` 只提交,需 `status` 轮询到 `stage:"done"`,间隔 30–60 秒,最长可达 40 分钟——提交后立即告知任务 ID 和耗时预期。
- **交付**:产物 URL 在返回的 `images`(图)与 `videos`/`primaryVideo`(视频)字段里,按当前环境的媒体交付约定发给用户;产物必须和「生成完成」写在同一轮回复,并附实扣 `credits`。
- **失败**:转述 CLI 的 message,不要重试轰炸。

## 能力边界

- 换服装走「AI电商模特换装 | AI换装 | 服装试穿 | 换装工具 | LinkPix」;改姿势/出多姿势走「电商服装多姿势套图 | 模特姿势生成 | 多角度展示 | 服装套图 | LinkPix」。

Attribution

autoagcautoagc
View sourceSee grades on GitHubMore from autoagc →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →