Token导航 LogoToken导航

Agent Skill · 效率

sticker-cog(贴纸齿轮)

sticker-cog 用于辅助前端页面、组件、样式和交互逻辑开发,适合在 OpenClaw 中需要维护前端项目、生成组件或检查界面实现时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

sticker-cog 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在效率类的 21,003 个 Skill 里排第 9,172。

总安装 6,291周安装 257GitHub Stars 公开资料未说明下载 2,035核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.5

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sticker-cog(贴纸齿轮)
来源仓库:https://github.com/nitishgargiitd/sticker-cog
安装命令:
openclaw skills install sticker-cog
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install sticker-cog

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

由 CellCog 驱动的 AI 贴纸包生成工具,支持多平台格式。可定制 WhatsApp、Telegram、Discord 等平台专用贴纸集。输入文字描述即可批量生成卡通风格表情图像。sticker-cog 属于效率类 Skill,可作为该场景下的辅助能力补充。需联网调用图像生成服务,注意版权与商用授权问题。

建议预览输出效果后再进行打包分发,避免低质素材。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install sticker-cog;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

sticker-cog 怎么安装?

在终端执行 openclaw skills install sticker-cog。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sticker-cog 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

sticker-cog 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

sticker-cog 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

sticker-cog 用的人多吗?

公开数据是累计安装 6,291 次,近一周安装 257 次,下载 2,035 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

sticker-cog 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
sticker-cog

贴纸齿轮 · 本页

6,291—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
sticker-cog
description
AI sticker pack generation powered by CellCog. Custom stickers, emoji sets, WhatsApp stickers, Telegram stickers, Discord emoji, Slack reactions. Character-consistent expressions, transparent backgrounds, batch generation, platform-ready packaging.
metadata
openclaw
emoji
✨
os
[darwin, linux, windows]
requires
bins
[python3]
env
[CELLCOG_API_KEY]
author
CellCog
homepage
https://cellcog.ai
dependencies
[cellcog]

Sticker Cog - One Character, Twenty Expressions, Perfect Consistency

One character. Twenty expressions. Every sticker looks like the same person. That's the hard part — and that's what CellCog does better than anyone.

Generating one cute sticker is easy. Every AI tool can do that. But generating a complete pack of 20 stickers where the character has the same face, same style, same proportions — just different expressions and poses? That's consistency at scale, and it's where most AI tools completely fall apart. By sticker #10, your character looks like a different person.

CellCog maintains character identity across every single generation, delivers with transparent backgrounds, and packages everything for your target platform — WhatsApp, Telegram, Discord, Slack, or iMessage.

How to Use

For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.

OpenClaw (fire-and-forget):

result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",
    task_label="my-task",
    chat_mode="agent",
)

All agents except OpenClaw (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent",
)
print(result["message"])

Why Sticker Packs Are Hard

The challenge isn't making one sticker. It's making twenty that look like they belong together.

The ProblemWhy It's HardHow CellCog Solves It
Character driftEach AI generation drifts slightly — different face shape, different proportionsCellCog's reference image threading maintains identity across all generations
Style consistencyLine weight, color palette, and art style shift between generationsThe agent establishes a visual style guide before generating and enforces it throughout
Expression rangeGetting 20 genuinely different expressions without changing the characterCellCog plans the full expression set upfront, then generates each with the character locked
Transparent backgroundsMany AI models struggle with clean transparencyDedicated transparent background model produces clean cutouts
Platform formattingEach messaging platform has different size, format, and packaging requirementsAutomatic conversion and optimization for WhatsApp, Telegram, Discord, Slack, iMessage

What Sticker Packs You Can Create

Character Sticker Packs

Design a character and get a complete expression set:

  • Original Characters: "Create a sticker pack with a friendly fox character — 20 expressions for everyday messaging"
  • Chibi/Anime Style: "Design a chibi version of a warrior princess with 15 battle and everyday expressions"
  • Mascot Packs: "Create a sticker pack for our startup mascot — a robot named Bolt"
  • Couple/Duo Packs: "Design two best friend characters and create stickers of them together"

Example prompt:

"Create a WhatsApp sticker pack — 20 stickers: Character: A chubby orange tabby cat named Mochi Style: Kawaii, round, simple clean lines, warm color palette Expressions: 1. Happy/smiling 2. Laughing (rolling on back) 3. Crying (dramatic anime tears) 4. Angry (puffed up) 5. Sleeping (curled up, zzz) 6. Eating (bowl of ramen) 7. Love (heart eyes) 8. Confused (head tilt, question mark) 9. Excited (jumping) 10. Thumbs up 11. Facepalm 12. Waving hello 13. Sad (rain cloud above) 14. Celebrating (party hat, confetti) 15. Thinking (chin on paw) 16. Shocked/surprised 17. Cool (sunglasses) 18. Sick (thermometer, blanket) 19. Working (tiny laptop) 20. Goodnight (moon, stars) Every sticker MUST look like the same cat. Format for WhatsApp: 512×512, WebP, transparent backgrounds, under 100KB each."

Brand & Team Emoji

Custom reactions for your workspace:

  • Company Mascot Emoji: "Turn our company mascot into a Slack emoji set with 15 work-related reactions"
  • Team Reactions: "Create a custom emoji set for our engineering Slack — ship it 🚢, LGTM, hotfix, etc."
  • Themed Packs: "Make a set of 10 food-themed reaction stickers for our restaurant's Discord"

Example prompt:

"Create a Slack emoji set for our engineering team: Style: Minimal, flat design, consistent with tech aesthetic Reactions needed: - 'Ship it' (rocket launching) - 'LGTM' (green checkmark with sparkles) - 'Hotfix' (fire + wrench) - 'In review' (magnifying glass) - 'Blocked' (stop sign) - 'Needs coffee' (coffee cup) - 'On call' (phone ringing) - 'Deployed' (party popper) - 'Rollback' (reverse arrow) - 'Weekend mode' (palm tree) All 128×128 PNG with transparent backgrounds. Keep them readable at small sizes."

From Reference Photos

Turn real photos into sticker packs:

  • Pet Stickers: "Turn this photo of my golden retriever into a 15-sticker cartoon pack"
  • Self-Portrait Stickers: "Create a cartoon sticker pack based on my photo — keep the likeness but make it cute"
  • Group Stickers: "Use this team photo to create cartoon versions of us for our company Slack"

Example prompt:

"Here's a photo of my cat Luna: [upload photo] Create a Telegram sticker pack (15 stickers) based on Luna's actual appearance: - Keep her black fur, green eyes, and white chest patch - Style: Cute cartoon, slightly exaggerated proportions (bigger head, bigger eyes) Expressions: happy, sleepy, hungry, judgmental, playful, zoomies, loaf position, stretching, knocking something off a table, hiding in a box, batting at a toy, yawning, grooming, startled, and one with a crown (queen energy) Every sticker must be recognizably Luna. 512×512 PNG, transparent backgrounds."

Professional Reaction Stickers

Workplace-appropriate reactions:

  • Project Status: "Create stickers for project management — Approved, In Progress, Needs Revision, Shipped, Blocked"
  • Meeting Reactions: "Make stickers for virtual meetings — Agree, Disagree, Question, Great Idea, Let's Table This"
  • Feedback Stickers: "Create a set of code review reaction stickers — LGTM, Nit, Bug, Refactor Needed, Nice Pattern"

Platform-Specific Packs

Optimized for where your audience lives:

  • WhatsApp Packs: "Create a complete WhatsApp sticker pack — 30 stickers, ready to import"
  • Telegram Sets: "Build a Telegram sticker set with 25 stickers"
  • Discord Emoji: "Create 20 custom Discord server emoji"
  • iMessage Stickers: "Design a sticker pack for iMessage with 15 expressions"

Sticker Styles

StyleCharacteristicsBest For
KawaiiRound, cute, simple, big eyesCasual messaging, cute characters
Flat DesignClean lines, solid colors, minimal shadingProfessional/brand emoji
CartoonExpressive, dynamic, detailedCharacter-driven packs
Pixel ArtRetro, nostalgic, grid-basedGaming communities, nostalgia
WatercolorSoft, artistic, painterlyArtistic/lifestyle brands
Line ArtBlack outlines, minimal colorElegant, universal
Chibi/AnimeExaggerated proportions, big headsAnime communities, expressive
3D RenderGlossy, dimensional, modernTech brands, premium feel

Platform Specifications

PlatformFormatSizePer Pack
WhatsAppWebP, transparent512×512, <100KB each3-30 stickers
TelegramPNG or WebP, transparent512×512Up to 120 stickers
DiscordPNG or GIF128×128 or 320×320Per slot
SlackPNG, GIF, or JPG128×128Per slot
iMessagePNG, transparent300×300 recommended10-40 stickers
General UsePNG, transparentAny sizeAny count

Tell CellCog which platform you're targeting and it handles the formatting automatically — dimensions, file format, file size optimization, and transparent background generation.


Chat Mode for Sticker Packs

ScenarioRecommended Mode
Single sticker pack (10-20 stickers), emoji sets"agent"
Multiple coordinated packs, brand sticker system, large sets (30+)"agent team"

Use "agent" for most sticker work. A single pack with 10-20 stickers executes well in agent mode.

Use "agent team" for brand-level sticker systems — when you need multiple packs that share a design language, or very large sets where consistency across 30+ stickers benefits from deeper creative planning.


Example Prompts

Quick emoji set:

"Create 10 food-themed reaction emoji for our team's Slack: Style: Cute, kawaii, each food item has a face Include: Pizza (excited), Sushi (cool), Taco (party), Coffee (sleepy), Burger (happy), Donut (love), Broccoli (disgusted), Ice cream (melting), Ramen (slurping), Cookie (waving) 128×128 PNG, transparent backgrounds."

Character pack from scratch:

"Design a character and create a full Telegram sticker set: Character: A tiny astronaut with an oversized helmet, floating in space Personality: Curious, clumsy, optimistic Style: Flat illustration, limited color palette (white suit, blue visor, orange accents) 20 stickers covering common messaging scenarios: Hi, Bye, Thanks, Sorry, LOL, Crying, Love, Angry, Thinking, Sleeping, Celebrating, Confused, Excited, Thumbs up, Facepalm, Mind blown, Running late, On my way, Good morning, Good night 512×512 PNG, transparent backgrounds. The astronaut must look identical in every sticker."

Brand mascot stickers:

"Our company mascot is a friendly blue owl named Hoot. Here's the reference image: [upload mascot image] Create a WhatsApp sticker pack (20 stickers) using Hoot: - Keep Hoot's exact design, colors, and proportions - Add work-related expressions: 'Great job!', 'Deadline approaching', 'Meeting time', 'Need coffee', 'On it!', 'Thinking...', 'Approved!', 'Let's discuss', etc. - Mix of work reactions and casual expressions Format: 512×512 WebP, transparent backgrounds, under 100KB each. Also create a set of 10 as 128×128 PNG for Slack emoji."

Pet sticker pack:

"Create a sticker pack from my dog's photo: [upload dog photo] My dog is a corgi named Biscuit. Turn Biscuit into a cartoon character (keep the corgi proportions, stumpy legs, big butt) and create 15 stickers: Happy wiggle, Zoomies, Sploot, Begging for treats, Judging you, Sleeping in funny position, Barking, Head tilt, Catching a ball, Rolling in grass, Wet dog, Wearing a tiny hat, Digging, Tail wagging, Puppy eyes For Telegram. 512×512, transparent."

Tips for Better Sticker Packs

  1. Describe the character in detail: "Orange cat" is vague. "Chubby orange tabby with green eyes, white chest patch, round face, always slightly smug expression" gives CellCog what it needs for consistency.
  1. Plan your expressions upfront: List all the expressions you want before generating. This helps CellCog plan the full set and avoid drift.
  1. Specify the style clearly: "Kawaii", "flat design", "chibi anime" — one clear style direction keeps the whole pack cohesive.
  1. Include reference images when possible: If you're making stickers from a pet photo, mascot design, or existing character, upload the reference. CellCog uses it to maintain likeness.
  1. Think about readability at small sizes: Stickers are viewed tiny. Bold outlines, simple shapes, and clear expressions read better than detailed illustrations.
  1. Platform first: Different platforms have wildly different requirements. "For WhatsApp" vs. "For Discord" changes dimensions, format, and file size targets. Always specify.

If CellCog is not installed

Run /cellcog-setup (or /cellcog:cellcog-setup depending on your tool) to install and authenticate. OpenClaw users: Run clawhub install cellcog instead. Manual setup: pip install -U cellcog and set CELLCOG_API_KEY. See the cellcog skill for SDK reference.

平台分布

OpenClaw

84.32%
按下载量换算1,716

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills