zouchenzhen/openclaw-gpt-image2-skill

Perfil de zouchenzhen

Última atividade de origem registrada: 30 de abril de 2026 às 17:28

Catálogo do SkillsMP atualizado: 26 de outubro de 2026 às 11:37

skills coletadas: 1

Estrelas no GitHub: 1
Forks no GitHub: 0

README do repositório

Arquivo de origem do README: README.md

Ler o README original

Expandir README completo

# OpenClaw GPT Image 2 Skill Generate images from OpenClaw conversations with `gpt-image-2`, save them locally, and send them through Telegram or QQBot. This is a small, auditable skill for users who already have an OpenAI-compatible Images API endpoint configured in `~/.openclaw/openclaw.json`, or who want to pass `-BaseUrl` and an API key environment variable directly. ## What it includes - `SKILL.md`: OpenClaw skill instructions and trigger description. - `scripts/generate_gpt_image2.ps1`: PowerShell script that calls `/v1/images/generations`. - `agents/openai.yaml`: optional UI metadata. No API keys, bot tokens, chat IDs, or provider secrets are included. ## Install Copy this folder into an OpenClaw skills directory: ```powershell Copy-Item -Recurse . "$env:USERPROFILE\.openclaw\skills\gpt-image2" openclaw skills info gpt-image2 ``` Or install it as a workspace skill: ```powershell Copy-Item -Recurse . "E:\Openclaw_Workspace\skills\gpt-image2" openclaw skills info gpt-image2 ``` Restart the OpenClaw gateway or start a new conversation so the agent sees the new skill. ## Configure The script can read a provider from `~/.openclaw/openclaw.json`: ```json { "models": { "providers": { "cpamc": { "baseUrl": "https://example.com/v1", "apiKey": "..." } } } } ``` Then run: ```powershell pwsh -NoProfile -File .\scripts\generate_gpt_image2.ps1 -Prompt "A clean travel poster for Zhengzhou, China" -ProviderId cpamc ``` You can also avoid storing the API key in OpenClaw config: ```powershell $env:OPENAI_API_KEY = "sk-..." pwsh -NoProfile -File .\scripts\generate_gpt_image2.ps1 ` -Prompt "A clean travel poster for Zhengzhou, China" ` -BaseUrl "https://api.openai.com/v1" ` -ApiKeyEnv "OPENAI_API_KEY" ` -ProviderId openai ``` ## Telegram Set a target chat ID once: ```powershell $env:OPENCLAW_TELEGRAM_TARGET = "123456789" ``` Generate and send: ```powershell pwsh -NoProfile -File .\scripts\generate_gpt_image2.ps1 ` -Prompt "A clean travel poster for Zhengzhou, China" ` -SendTelegram ` -Caption "郑州旅游海报" ``` ## QQBot Generate and emit a structured payload: ```powershell pwsh -NoProfile -File .\scripts\generate_gpt_image2.ps1 ` -Prompt "A clean travel poster for Zhengzhou, China" ` -EmitQQPayload ` -Caption "郑州旅游海报" ``` The agent should return the printed `QQBOT_PAYLOAD:` block exactly, with no extra text. ## Security - Do not commit `~/.openclaw/openclaw.json`, `.env`, generated images, chat IDs, or tokens. - Review any third-party image skill before installing it. Skills can run local commands and access files. - This script only sends the prompt to the configured image provider endpoint. ## License MIT

Carregando o README do repositório…

Skills neste repositório

Artistas de efeitos especiais e animadores Artistas plásticos, incluindo pintores, escultores e ilustradores

2 categorias ocupacionais · 100% classificado

skill

ocupação

descrição

atualizado

gpt-image2

Artistas de efeitos especiais e animadoresArtistas plásticos, incluindo pintores, escultores e ilustradores

Generate images with GPT Image 2 through a local OpenAI-compatible Images API script, then deliver them through OpenClaw chat channels such as Telegram or QQBot. Use when the user asks to generate, draw, create, or send an image, poster, photo, illustration,…

Idioma do texto original: inglês

2026-04-30

Mostrando 1 de 1 skills coletadas.

Instalar com um assistente de IA

Copie este prompt para o assistente de IA que você usa.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/zouchenzhen/openclaw-gpt-image2-skill.