Token导航 LogoToken导航

Agent Skill · 研究检索

aavegotchi-svg-custom(aavegotchi svg 自定义)

aavegotchi-svg-custom 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

aavegotchi-svg-custom 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 24,630。

总安装 3,966周安装 162GitHub Stars 公开资料未说明下载 1,283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
1.1.3

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:aavegotchi-svg-custom(aavegotchi svg 自定义)
来源仓库:https://github.com/aaigotchi/aavegotchi-svg-custom
安装命令:
openclaw skills install aavegotchi-svg-custom
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 aavegotchi-svg-custom

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

从Base链数据生成经典SVG/PNG格式的Aavegotchi图像服务。适用于个人资料展示、社区头像与数字收藏品展示场景。支持自定义负载注入与现有TokenID批量渲染处理。SVG矢量图适合缩放不失真,PNG适合静态背景使用。链上数据可能存在延迟,建议添加缓存刷新机制提升体验。

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 aavegotchi-svg-custom;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

    它需要接触敏感数据,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

aavegotchi-svg-custom 怎么安装?

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

aavegotchi-svg-custom 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。

aavegotchi-svg-custom 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

aavegotchi-svg-custom 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。

aavegotchi-svg-custom 用的人多吗?

公开数据是累计安装 3,966 次,近一周安装 162 次,下载 1,283 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。

aavegotchi-svg-custom 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
aavegotchi-svg-custom

aavegotchi svg 自定义 · 本页

3,966—接触敏感数据MIT-0有提醒

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
aavegotchi-svg-custom
description
Render OG Aavegotchi SVG and PNG images from Base for custom hypothetical loadouts or existing token IDs. Use when the user wants classic onchain SVG-style gotchis rather than 3D renders.
metadata

aavegotchi-svg-custom

Use this skill when the user wants a custom OG Aavegotchi render in the classic SVG style from selected traits, wearable names, wearable IDs, or a token ID on Base.

Plain-language requests should also route here, for example:

  • "render an OG SVG ETH gotchi with common eyes, aagent hat, shades, shirt, headset, and pistol"
  • "show me a classic gotchi SVG with xibot mohawk, cyborg eye, and an energy gun"
  • "render token 3863 in the OG SVG style"
  • "make a Base gotchi SVG with mythical eyes and wizard gear"

Do not wait for the user to explicitly say aavegotchi-svg-custom.

What this skill does

  • renders official-style OG Aavegotchi SVGs from the Base Aavegotchi diamond
  • supports custom hypothetical loadouts and token-id renders
  • writes PNGs by default alongside the SVGs for Telegram/chat delivery
  • applies the centralized side-view exception table for wearable layering
  • keeps the background logic simple and deterministic: common by default, transparent on request, or any fixed rarity-tier color when explicitly requested
  • returns front, left, right, and back outputs plus a manifest JSON
  • supports friendlier presets, collateral aliases, and wearable-name lookup

Constraints

  • this skill is for OG SVG/classic gotchis on Base, not 3D renders
  • requires node and npm install in the skill root so the bundled @resvg/resvg-js rasterizer is available; qlmanage, rsvg-convert, magick, convert, or inkscape are only optional fallbacks
  • token renders depend on Base RPC availability
  • custom render requests must be executed through the shell wrapper, not described hypothetically
  • no environment variables are required for normal operation; AAVEGOTCHI_RPC_URL is optional if you want to override the default Base RPC

Routing Notes

  • Prefer this skill when the user asks for OG, SVG, classic, pixel, onchain, or Base gotchi renders.
  • Prefer this skill when the user wants a custom gotchi outfit in the classic Aavegotchi look.
  • Prefer gotchi-3d-custom-render instead when the user explicitly wants a 3D, portrait, headshot, hosted renderer, or Unity render.
  • Prefer this skill instead of generic image generation for gotchi outfit prompts. Do not use image_generate or any non-Aavegotchi art generator for OG gotchi requests.
  • If the user gives a token ID, use --token-id rather than reconstructing the outfit manually.

Entry points

  • main wrapper: scripts/render-custom-gotchi-svg.sh
  • delivery helper: scripts/show-svg-custom.sh
  • direct renderer: scripts/render-svg-custom.mjs

Execution Rules

For local/manual render requests outside chat, run the wrapper directly:

bash scripts/render-custom-gotchi-svg.sh ...

Do not just describe what the render would look like. Do not switch to generic image generation. Do not answer with hosted 3D renderer language.

For OpenClaw chat and Telegram replies, do not use the raw wrapper directly. Always use:

bash scripts/show-svg-custom.sh ...

That helper is the only allowed delivery path in chat because it guarantees:

  • a fresh tg-* slug
  • fresh output files
  • exact FRONT_MEDIA / LEFT_MEDIA / RIGHT_MEDIA / BACK_MEDIA
  • a matching SUMMARY

After running the wrapper:

  1. read the generated manifest JSON
  2. prefer the PNG outputs for chat and Telegram delivery
  3. only send raw SVG files if the user explicitly asks for SVG
  4. if only one angle is needed, send the most relevant PNG from the manifest
  5. if multiple angles are helpful, send front_png, left_png, right_png, and back_png

Quick usage

From the skill root:

bash scripts/render-custom-gotchi-svg.sh --preset blank-eth --slug blank-eth

Default mode produces both SVG and PNG outputs. Use --no-png only when SVG-only output is explicitly wanted.

Outputs land in:

  • Renders/<slug>-front.svg
  • Renders/<slug>-left.svg
  • Renders/<slug>-right.svg
  • Renders/<slug>-back.svg
  • Renders/<slug>-front.png
  • Renders/<slug>-left.png
  • Renders/<slug>-right.png
  • Renders/<slug>-back.png
  • Renders/<slug>-manifest.json

For OpenClaw Agents

Use scripts/show-svg-custom.sh when the goal is to send the render back into chat. It runs the renderer, auto-generates a fresh slug when one is not provided, and prints the exact media variables to use with the message tool.

cd ~/.openclaw/workspace/skills/aavegotchi-svg-custom
bash scripts/show-svg-custom.sh --collateral ETH --eye-shape common --eye-color common --head 'Aagent Fedora Hat' --eyes 'Aagent Shades' --face 'Aagent Headset' --body 'Aagent Shirt' --hand-right 'Aagent Pistol'

Example output:

FRONT_MEDIA=./skills/aavegotchi-svg-custom/Renders/tg-1775338000-12345-front.png
RIGHT_MEDIA=./skills/aavegotchi-svg-custom/Renders/tg-1775338000-12345-right.png
CAPTION_FRONT=OG SVG gotchi - front view
CAPTION_RIGHT=OG SVG gotchi - right view
SUMMARY=OG SVG gotchi rendered. Rarity: rare (Malibu). Outfit: Aagent Shirt, Aagent Headset, Aagent Shades, Aagent Fedora Hat, Aagent Pistol.

Then use the message tool like this:

message(action: "send", media: FRONT_MEDIA, caption: CAPTION_FRONT)
message(action: "send", media: RIGHT_MEDIA, caption: CAPTION_RIGHT)

Do not pass chatId in normal Telegram reply handling. Do not use filePath for images when media is enough. Prefer workspace-relative paths like ./skills/aavegotchi-svg-custom/Renders/... over absolute paths. Do not reuse the literal example slug from this document; let the helper generate a fresh slug unless the user explicitly asks for a specific one. Never send eth-preview-* or any other stale pre-existing render. Only send the exact FRONT_MEDIA, LEFT_MEDIA, RIGHT_MEDIA, and BACK_MEDIA emitted by the current helper run.

Input contract

Supported flags:

  • --token-id
  • --preset
  • --slug
  • --collateral
  • --eye-shape
  • --eye-color
  • --body
  • --face
  • --eyes
  • --head
  • --pet
  • --hand-left
  • --hand-right
  • --left-hand
  • --right-hand
  • --bg
  • --background-mode
  • --find-wearable
  • --list-collaterals
  • --list-presets
  • --no-png

Wearable flags can take either:

  • numeric IDs like --head 59
  • quoted names like --head 'Aagent Fedora Hat'

Friendly examples

bash scripts/render-custom-gotchi-svg.sh --find-wearable aagent
bash scripts/render-custom-gotchi-svg.sh --preset blank-eth --slug blank-eth
bash scripts/render-custom-gotchi-svg.sh --token-id 3863 --slug token-3863
bash scripts/render-custom-gotchi-svg.sh --collateral ETH --eye-shape common --eye-color common --head 'Aagent Fedora Hat' --eyes 'Aagent Shades' --face 'Aagent Headset' --body 'Aagent Shirt' --hand-right 'Aagent Pistol' --slug aagent-svg
bash scripts/render-custom-gotchi-svg.sh --collateral ETH --eye-shape common --eye-color common --head 'Xibot Mohawk' --eyes 'Cyborg Eye' --body 'Punk Shirt' --face 'Beard of Wisdom' --hand-right 'Energy Gun' --hand-left 'Portal Mage Black Axe' --slug xibot-svg

Natural-language request examples this skill should handle:

  • "render a custom ETH gotchi in the OG SVG style with Aagent gear"
  • "show me a Base gotchi SVG with xibot mohawk and cyborg eye"
  • "render this with the rarity color background"
  • "render this with a transparent background"
  • "render token 3863 as PNGs"
  • "make a classic pixel gotchi with mythical eyes and wizard wearables"

Background mode rules:

  • default to --background-mode common
  • if the user asks for transparent background, no background, or without the rarity square, use --background-mode transparent
  • if the user does not specify a background color, keep it common even if the gotchi's computed rarity is different
  • if the user asks for a specific rarity color, use that exact tier:

- --background-mode common - --background-mode uncommon - --background-mode rare - --background-mode legendary - --background-mode mythical - --background-mode godlike

  • also accept the explicit rarity aliases:

- --background rarity-common - --background rarity-uncommon - --background rarity-rare - --background rarity-legendary - --background rarity-mythical - --background rarity-godlike

  • for prompts like in a mythical color background, pass --background mythical explicitly
  • for prompts like with transparent background, pass --background transparent explicitly
  • if no background wording appears in the prompt, pass --background common explicitly in chat so the generated file and caption cannot drift

Examples:

  • "render this with a mythical rarity background"
  • "use the godlike bg color"
  • "same gotchi with the default common background"
  • "same gotchi but with a rare background square"

When to read extra files

  • read references/presets.json when you need preset names
  • read references/wearables.tsv when you need wearable name lookup
  • read references/side-view-exceptions.json when debugging wearable layering
  • read references/base-deployment.json when checking Base contract or collateral aliases

平台分布

OpenClaw

82.76%
按下载量换算1,062

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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