What it does
Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for OpenAI (per the README)
- Category 自动化与智能体
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/six-nut-pocketmen-with-you)相似的 Skill
同类工作,排序与 Skill 列表相同
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
Codex
依据开发者 README 和 repo 中的文件夹
安装
Is it safe?
- Who made it
GitHub account six-nut (person), 6 years old
- Use and upkeep
★ 294 stars, few users so far · code last changed 2026年10月13日
- Any scripts?
22 scripts that can run on a computer: runtime/pocketmen/__init__.py, runtime/pocketmen/atlas.py, runtime/pocketmen/backends/__init__.py, runtime/pocketmen/backends/base.py and 18 more
- Uses the internet?
Could not check every script (some are too large); read them first
- Changes machine-wide settings?
Scripts that touch settings folders (~/.claude or settings.json): runtime/pocketmen/install.py
Checked automatically from the repo files at commit b566598 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (363). Use "Let the AI install it" instead
Option 1让 Claude Code 帮你安装
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /pocketmen-with-you,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.claude/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
重新打开 Claude Code,输入 /pocketmen-with-you,或直接提出相关任务,Claude 会自动选用
ChatGPT 桌面应用
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
Option 1让 ChatGPT 帮你安装
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2自己放入文件夹
把 pocketmen-with-you 文件夹放到 ~/.agents/skills/pocketmen-with-you
~ 是你的主文件夹($HOME)
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
安装之后
- ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
- 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
- Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
网页版和手机版 ChatGPT
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Option 1让 Codex 帮你安装
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
重新打开 Codex 并提出相关任务,Codex 会列出这个 skill
Option 1让 Cursor 帮你安装
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 pocketmen-with-you
Checked against official docs 2026年11月12日 · Source: cursor.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.cursor/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
在 Cursor 的 Agent 聊天中输入 / 并选择 pocketmen-with-you
Option 1Let the AI install it
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
查看原始 SKILL.md
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: pocketmen-with-you
description: Turn 2+ user reference images into a high-fidelity animated Codex companion using PocketMen's own local stack. Prefer the open-weight Neural Local Studio (FLUX.2 klein 4B; optional Qwen-Image-Edit-2511 Identity-Max) on compatible hardware; otherwise fall back to the deterministic local renderer. Never require hatch-pet or OPENAI_API_KEY for the normal workflow.
---
# PocketMen with You — Neural Local Studio
Create a Codex companion from **at least two** user-provided reference images. The normal workflow is self-contained and **must not invoke `$hatch-pet` or request `OPENAI_API_KEY`**.
## Product goal
The user should be able to upload 2+ images and get a polished, identity-consistent Codex companion with minimal setup. PocketMen should aim for hosted-image-editor-like quality **within this narrow companion-creation task**, while being honest that local open-weight models are not guaranteed to equal a proprietary frontier model on every visual task.
## Engine order
Use this decision order:
1. inspect the references visually and build an Identity Lock;
2. run PocketMen hardware doctor;
3. if compatible neural runtime/hardware is available, use `neural-local`;
4. if the neural runtime is missing but an NVIDIA GPU with roughly 13 GB+ VRAM is present, bootstrap the skill-local neural profile once, then retry;
5. if neural inference is unavailable or fails, fall back to the deterministic local renderer;
6. never route failure into hatch-pet or OpenAI API-key setup.
### Default neural backend
`flux2-klein-4b`
- open-weight local generation/editing;
- multi-reference editing;
- commercial-friendly Apache-2.0 weights;
- intended for consumer NVIDIA GPUs;
- preferred for most users.
### Identity-Max backend
`qwen-image-edit-2511`
Use only when the user prioritizes identity consistency over setup size/latency or when FLUX state outputs visibly drift. This backend is heavier and should not be silently installed unless needed.
### Deterministic fallback
`local-deterministic-motion-puppet`
Guaranteed no-model path. It preserves supplied pixels and produces a valid Codex atlas, but cannot invent unseen anatomy/poses at neural quality.
## First step: visual Identity Lock
Before running any command, inspect all supplied references and summarize only stable visible details.
Record:
- `subject_type`: `person`, `animal`, `creature`, `mascot`, or `auto`;
- face/head shape;
- hair/fur/material and stable markings;
- eye color and eye shape;
- silhouette/body proportions;
- fixed accessories (collar, earrings, glasses, watch, ribbon, backpack, etc.);
- stable outfit details when the user wants them locked;
- personality cues relevant to motion;
- any traits that vary between images and must **not** be locked.
Turn these into one concise `--identity-notes` string. This is important: the local neural backend sees image references, but explicit stable identity notes substantially reduce drift across animation states.
Do not infer sensitive identity attributes. Describe only visible appearance needed for rendering.
## Style choice
Allowed styles:
- `soft-real` — photo-faithful humans/animals; preserve fur/hair/eyes/markings/accessories;
- `hero-chibi` — premium 3D toy-like chibi, handsome/cute balance, roughly 2.7–3 heads tall;
- `plush` — premium collectible plush interpretation;
- `capsule-creature` — original PocketMen pocket-creature styling using PocketMen's own red/yellow Companion Capsule;
- `auto` — conservative; use `soft-real` unless the user clearly requests stylization.
For a real deceased or memorial pet, prioritize identity fidelity over cuteness and do not imply the digital pet is literally the deceased animal.
## Quality choice
- `draft`: one neural canonical master + deterministic nine-state motion;
- `balanced`: canonical master + state-specific neural key poses; recommended default;
- `max`: independently generate every state key pose; best for publication-quality showcases and important personal companions.
Use `max` when the user explicitly asks for maximum quality, ImageGen-like results, or very high fidelity.
## Runtime discovery
Resolve the installed skill directory first.
Runtime Python:
Windows:
```text
<skill-dir>\.venv\Scripts\python.exe
```
macOS/Linux:
```text
<skill-dir>/.venv/bin/python
```
If the virtual environment does not exist, run:
```bash
python <skill-dir>/scripts/setup_runtime.py --skill-dir <skill-dir> --profile core
```
## Hardware doctor
Run:
```bash
<python> <skill-dir>/scripts/create_local_pet.py doctor
```
If `recommended_engine` is `neural-local` but the neural dependencies are missing, run once:
```bash
python <skill-dir>/scripts/setup_runtime.py --skill-dir <skill-dir> --profile neural
```
The first real neural creation may download `black-forest-labs/FLUX.2-klein-4B` into the normal Hugging Face cache. This is a local model download, **not an OpenAI API call**, and no OpenAI key is required.
If the user explicitly requests Identity-Max, use:
```bash
python <skill-dir>/scripts/setup_runtime.py --skill-dir <skill-dir> --profile identity-max
```
## Creation command — default high-quality path
```bash
<python> <skill-dir>/scripts/create_local_pet.py create \
--reference /absolute/path/ref1.jpg \
--reference /absolute/path/ref2.jpg \
--name "<display name>" \
--pet-id "<stable-id>" \
--subject-type <person|animal|creature|mascot|auto> \
--identity-notes "<stable visible identity details>" \
--style <soft-real|hero-chibi|plush|capsule-creature|auto> \
--engine auto \
--backend auto \
--quality balanced \
--output /absolute/path/to/output \
--install
```
For maximum local quality:
```text
--engine neural --backend flux2-klein-4b --quality max
```
For identity-sensitive heavy mode:
```text
--engine neural --backend qwen-image-edit-2511 --quality max
```
Do not ask for API credentials if these fail. If neural fallback is allowed, PocketMen will use the deterministic path and report the reason.
## Neural rendering design
PocketMen owns the full pipeline:
1. choose a chroma color maximally separated from the references;
2. use 2–3 references as identity anchors;
3. generate a canonical master in the requested style;
4. generate semantically correct state-specific key poses from canonical + raw references;
5. use a strict structured prompt: purpose → subject → identity lock → action → style → composition → background → constraints;
6. render on a perfectly flat opaque chroma background;
7. remove only chroma-like pixels connected to the frame border, protecting same-colored eyes/accessories inside the subject;
8. use deterministic micro-motion between key poses to reduce identity flicker;
9. build, validate, preview and package the 8×9 Codex atlas.
## Motion contract
Rows and frame counts:
1. `idle` — 6
2. `running-right` — 8
3. `running-left` — 8
4. `waving` — 4
5. `jumping` — 5
6. `failed` — 8
7. `waiting` — 6
8. `running` — 6, meaning Codex is actively working, not physical locomotion
9. `review` — 6
The neural engine generates a true semantic key pose for each state in balanced/max modes. Deterministic transforms are reserved for subtle breathing, bounce, lean and timing—not for pretending a static cutout is a completely new pose.
For animals, `waving` should use a raised front paw with natural anatomy. For people, use a real hand wave. `running` should depict focused work with a compact plain laptop. `review` should depict inspection of a plain paper/blueprint. No readable brand logos or UI text.
## QA gates
Expected output:
```text
<output>/
package/<pet-id>/
pet.json
spritesheet.webp
run/final/
spritesheet.webp
validation.json
run/qa/
identity-lock.json
neural-generation.json # neural runs only
neural-raw/*.png # local QA artifacts
neural-cutouts/*.png # local QA artifacts
contact-sheet.png
review.json
run-summary.json
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 294
- 开发者
- six-nut
- 许可证
- MIT
- 最近代码更新
- 2026年10月13日
- repo 中的 SKILL.md 文件(含译本和模板)
- 1
- 主题
- agent-skill, ai-pet, character-consistency, codex, codex-skill, computer-vision, desktop-pet, flux2, image-editing, image-generation, local-ai, multimodal