Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

digital-product-builder数字产品构建者

Agent Skill

digital-product-builder 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。

总安装

3,634

周安装

147

GitHub Stars

公开资料未说明

下载量

1,141
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:digital-product-builder(数字产品构建者)
来源仓库:https://github.com/sabroo3-commits/digital-product-builder
安装命令:
openclaw skills install digital-product-builder
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 digital-product-builder

简介

助力在 Gumroad、itch.io 等平台零成本发布数字产品。

  • 自动生成封面图、资产列表与商品描述文案。digital-product-builder 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 降低创作者进入门槛,聚焦内容而非运营技巧。
  • 支持电子书、游戏模组、设计模板等多种产品类型。
  • 建议先小规模试卖再根据反馈迭代优化产品形态。

SKILL.md

name
digital-product-builder
description
Build and launch zero-cost digital products on Gumroad, itch.io, and DriveThruRPG. Use when: creating cover images or product art without external AI image services, generating product listing copy cheaply, building downloadable asset packs (TTRPG tokens, design kits, templates), or setting up a new digital storefront. Uses Python Pillow for images ($0, no login, no browser needed) and Groq for copy (~$0.01/product). Works on Linux, macOS, and Windows-WSL. Includes platform size presets, font discovery, and a catalog of common blockers with proven fixes.

Digital Product Builder

Build and ship digital products for Gumroad, itch.io, and DriveThruRPG without spending money on image generators or expensive AI models.

Stack: Python Pillow for images ($0) + Groq for copy (~$0.01/product) + Claude main session for orchestration only.


Quick Start

# Check Pillow
python3 -c "from PIL import Image, ImageDraw, ImageFont; print('Pillow ready')" 2>/dev/null || echo "Not installed"

# Install if missing (try each until one works)
pip3 install Pillow
# or: pip install Pillow
# or: python3 -m pip install Pillow

Image Generation — Pillow

Never use the browser tool for image generation. Pillow is faster, crash-free, and requires no login or external service.

Find available fonts (run this first)

import os
font_dirs = [
    '/usr/share/fonts',                          # Linux
    '/System/Library/Fonts',                     # macOS
    'C:/Windows/Fonts',                          # Windows
    os.path.expanduser('~/.fonts'),
]
fonts = []
for d in font_dirs:
    if os.path.exists(d):
        for root, _, files in os.walk(d):
            for f in files:
                if f.endswith(('.ttf', '.otf')):
                    fonts.append(os.path.join(root, f))
print('\
'.join(fonts[:20]))

Common font paths (Ubuntu/Debian)

/usr/share/fonts/truetype/liberation/LiberationSerif-Bold.ttf
/usr/share/fonts/truetype/liberation/LiberationSans-Bold.ttf
/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf

Common font paths (macOS)

/System/Library/Fonts/Helvetica.ttc
/System/Library/Fonts/Georgia.ttf
/Library/Fonts/Arial.ttf

Safe fallback (always works, no font file needed)

font = ImageFont.load_default()  # basic but guaranteed

Platform cover sizes

PlatformSizeNotes
itch.io630×500pxRequired for browse visibility
Gumroad1280×720px16:9
DriveThruRPG900×700pxLandscape or portrait
Social preview (OG/Twitter)1200×630pxStandard

Cover image boilerplate

from PIL import Image, ImageDraw, ImageFont
import os

W, H = 630, 500
SERIF_BOLD = "/usr/share/fonts/truetype/liberation/LiberationSerif-Bold.ttf"

img  = Image.new("RGB", (W, H), (20, 20, 40))
draw = ImageDraw.Draw(img)
font = ImageFont.truetype(SERIF_BOLD, 36)
gold = (201, 168, 76)

# Border
draw.rectangle([10,10,W-10,H-10], outline=gold, width=4)

# Centered title
b = draw.textbbox((0,0), "Your Title", font=font)
draw.text(((W-(b[2]-b[0]))//2, (H-(b[3]-b[1]))//2), "Your Title",
          fill=gold, font=font)

img.save("/path/to/output.png", "PNG", optimize=True)
print(f"Saved ({os.path.getsize('/path/to/output.png')//1024}KB)")

Radial gradient (dark-to-light effect)

def lerp(a, b, t):
    return tuple(int(a[i] + (b[i]-a[i])*t) for i in range(3))

center = (230, 180, 80)   # bright centre
edge   = (60,  30,  10)   # dark edge
for step in range(30, 0, -1):
    t  = step / 30
    c  = lerp(center, edge, t)
    r  = int(radius * step / 30)
    draw.ellipse([cx-r, cy-r, cx+r, cy+r], fill=c)

RGBA transparency (for compositing)

img  = Image.new("RGBA", (W, H), (20, 20, 40, 255))
draw = ImageDraw.Draw(img, "RGBA")
# ... draw with alpha ...
# Flatten to RGB before saving PNG
bg = Image.new("RGB", (W, H), (20, 20, 40))
bg.paste(img, mask=img.split()[3])
bg.save(out_path, "PNG")

ZIP bundle

import zipfile
with zipfile.ZipFile("product.zip", "w", zipfile.ZIP_DEFLATED) as z:
    z.writestr("README.txt", readme_text)
    for fp in file_list:
        z.write(fp, f"subfolder/{os.path.basename(fp)}")

Copy Generation — Groq

API key location: Store your Groq API key in ~/.openclaw/workspace/dashboard/.env as GROQ_API_KEY=your_key_here

Node.js call pattern

const https = require('https');
const GROQ_KEY = process.env.GROQ_API_KEY;

const body = JSON.stringify({
  model: "llama-3.3-70b-versatile",
  messages: [{ role: "user", content: YOUR_PROMPT }],
  max_tokens: 600,
  temperature: 0.7
});

const req = https.request({
  hostname: 'api.groq.com',
  path: '/openai/v1/chat/completions',
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${GROQ_KEY}`,
    'Content-Type': 'application/json',
    'Content-Length': Buffer.byteLength(body)
  }
}, res => {
  let d = '';
  res.on('data', c => d += c);
  res.on('end', () => console.log(JSON.parse(d).choices[0].message.content));
});
req.write(body);
req.end();

Listing copy prompt template

Write a product listing for [PLATFORM]. Plain language. No em dashes.
No filler phrases ("elevate," "perfect for," "streamline your workflow").

Product: [NAME]
What it is: [DESCRIPTION]
Price: [PRICE]
Format: [FILE FORMAT]

Write: title (under 60 chars), tagline (1 sentence), description
(3 short paragraphs), what's included (5 items max), 5 search tags.

De-AI-ify checklist (always run before saving copy)

  • Remove em dashes — use periods or commas instead
  • Remove: "elevate," "enhance," "seamlessly," "perfect for," "streamline"
  • Break up long bullet lists into short paragraphs
  • If it sounds like a press release, rewrite it

Platform Playbooks

itch.io

  • New product: Dashboard → Create new project → Downloadable
  • Cover image: 630×500px required — no cover = invisible in browse
  • Pricing: fixed price or "pay what you want" with minimum
  • Upload: ZIP file for multi-file products
  • Tags: use specific terms (e.g. "ttrpg tokens" not just "game")

Gumroad

  • New product: Products → New Product → Digital
  • Cover: 1280×720 recommended
  • Description editor may require manual paste — automation sometimes blocked
  • Set Discover category in product settings for marketplace visibility
  • Configure payout threshold in account settings

DriveThruRPG

  • Free publisher account at drivethrurpg.com/publishers
  • Cover: 900×700px
  • Categories for tokens: Accessories > Tokens/Maps
  • Revenue: 70% creator / 30% DTRPG
  • Payout: PayPal, $10 minimum

Common Blockers & Fixes

BlockerFix
Bing Image Creator requires MS accountUse Pillow — no external services needed
ideogram.ai / external generators blocked by CloudflareUse Pillow
Browser crashes during canvas renderingDon't use browser for images. Pillow only.
Can't save canvas to file from browser JSPillow writes directly to disk
file:// URLs blocked in browser toolServe via python3 -m http.server PORT
Gumroad editor blocks automationPaste listing copy manually
require is not defined in browser evaluateUse exec + node script instead
itch.io "invalid token" on email verifySafe to ignore if account is already live

Cost Per Product

ItemToolCost
Cover imagePillow$0
Asset sheets / bundlesPillow$0
Product listing copyGroq llama-3.3-70b~$0.01
OrchestrationClaude main sessionminimal
Total per product< $0.05

No sub-agents needed. Do everything inline in the main session.


Example Products Built With This Skill

  • NPC Dialogue & Quest Text Packs — itch.io, $9
  • TTRPG Character Token Pack — DriveThruRPG, $7.99
  • Newsletter Creator Visual Kit — Gumroad, $12

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

92.34%
按下载量换算1,054

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills