Ppt Master
Generate presentation slides with AI-backed images by configuring provider-specific image backends and env fallbacks for ppt-master workflows.
Overview
ppt-master is an agent skill most often used in Build (also Validate, Launch) that configures multi-provider AI image generation for presentation workflows via image_gen.py and .env fallbacks.
Install
npx skills add https://github.com/hugohe3/ppt-master --skill ppt-masterWhat is this skill?
- Optional .env fallback chain for image_gen.py with four resolution paths (cwd, skill dir, repo root, ~/.ppt-master/.env)
- Five recommended image backends: openai, gemini, qwen, zhipu, volcengine
- Process environment variables override file-based config; no merge across multiple .env files
- Deprecated unified IMAGE_API_KEY / IMAGE_MODEL / IMAGE_BASE_URL in favor of provider-specific keys
- Supports solo builders shipping pitch decks and internal slides without a separate design toolchain
- 4-tier .env resolution order documented
- 5 recommended core image backends
Adoption & trust: 4k installs on skills.sh; 25.2k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need slide visuals from AI APIs but your agent keeps failing on wrong keys, deprecated env vars, or .env files in the wrong directory.
Who is it for?
Indie builders cloning or installing ppt-master who already know which image provider they will bill and want explicit backend env setup before generating deck assets.
Skip if: Teams that only need static Markdown docs with zero generated images, or builders who refuse to manage provider API keys in env or .env.
When should I use this skill?
You are running ppt-master image generation and need a resolved IMAGE_BACKEND with provider-specific credentials.
What do I get? / Deliverables
After configuration, image_gen.py resolves one clear backend and credential set so your agent can generate slide imagery on a repeatable path.
- Configured image backend for deck generation runs
- Resolved single .env or env-var credential set
- Generated slide imagery assets (via your deck pipeline)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is build/docs because the skill packages slide and image-generation workflow artifacts builders produce while shaping decks and product narratives. docs subphase fits deck creation, exportable narratives, and documentation-style deliverables rather than runtime app code.
Where it fits
Wire Gemini image backend before generating mock UI slides for a landing-page storyboard.
Set openai backend from skill-dir .env while the agent drafts a technical architecture deck.
Refresh pitch slide heroes with volcengine after copy is final but visuals are stale.
How it compares
Use as a skill-packaged image backend wiring layer, not as a hosted Canva-style MCP design server.
Common Questions / FAQ
Who is ppt-master for?
ppt-master is for solo and indie builders using Claude Code, Cursor, or similar agents who produce presentations or pitch materials and rely on OpenAI, Gemini, Qwen, Zhipu, or Volcengine for slide imagery.
When should I use ppt-master?
Use it in Validate when prototyping a narrative deck, in Build while drafting product or docs slides, and in Launch when refreshing pitch or distribution visuals—always after you choose a backend and set provider-specific env vars.
Is ppt-master safe to install?
The skill expects API keys and optional .env files on your machine; review the Security Audits panel on this Prism page and treat provider credentials as secrets you rotate and scope minimally.
SKILL.md
READMESKILL.md - Ppt Master
# ───────────────────────────────────────────────────────────── # Image Generation Configuration / 图片生成配置 # ───────────────────────────────────────────────────────────── # This file is an optional fallback config source for image_gen.py. # Current process environment variables take precedence over this file. # 当前文件是 image_gen.py 的可选 fallback 配置来源。 # 当前进程环境变量优先于这个文件。 # # Resolution order (only the FIRST existing file is read; keys are NOT merged across files): # 1. ./.env in your current working directory # 2. <skill-dir>/.env (skill install, e.g. ~/.agents/skills/ppt-master/.env) # 3. <repo-root>/.env (when running from a clone) # 4. ~/.ppt-master/.env (user-level config) # 查找顺序（只读第一个存在的文件，多个 .env 之间不合并）： # 1. 当前工作目录下的 ./.env # 2. skill 安装目录下的 .env（如 ~/.agents/skills/ppt-master/.env） # 3. 仓库根目录下的 .env（仅在 clone 模式下） # 4. ~/.ppt-master/.env（用户级配置） # Active backend (required) / 当前启用后端（必需） # Recommended core backends: openai / gemini / qwen / zhipu / volcengine # 推荐核心后端：openai / gemini / qwen / zhipu / volcengine # IMAGE_BACKEND=openai # You may also provide the same variables directly via the current process environment. # 也可以不写 .env，而是直接通过当前运行进程的环境变量提供同样的配置。 # IMPORTANT: # - IMAGE_API_KEY / IMAGE_MODEL / IMAGE_BASE_URL are no longer supported. # - Use provider-specific keys only. # 重要： # - 不再支持 IMAGE_API_KEY / IMAGE_MODEL / IMAGE_BASE_URL。 # - 请只使用各提供商自己的变量。 # ───────────────────────────────────────────────────────────── # Example: OpenAI / OpenAI 示例 (recommended / 推荐) # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=openai # OPENAI_API_KEY=sk-xxx # OPENAI_MODEL=gpt-image-2 # OPENAI_BASE_URL=http://127.0.0.1:3000/v1 # Allowed values: png / jpeg / webp # OPENAI_OUTPUT_FORMAT=png # jpeg/webp only, 0-100 # OPENAI_OUTPUT_COMPRESSION=80 # gpt-image-2: auto / opaque # OPENAI_BACKGROUND=auto # auto / low # OPENAI_MODERATION=auto # ───────────────────────────────────────────────────────────── # Example: Gemini / Gemini 示例 # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=gemini # GEMINI_API_KEY=your-gemini-api-key # GEMINI_MODEL=gemini-3.1-flash-image-preview # GEMINI_BASE_URL=https://your-proxy-url.com # ───────────────────────────────────────────────────────────── # Example: MiniMax / MiniMax 示例 # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=minimax # MINIMAX_API_KEY=your-minimax-key # MINIMAX_MODEL=image-01 # Default China endpoint / 默认国内地址 # MINIMAX_BASE_URL=https://api.minimaxi.com/v1/image_generation # Optional overseas endpoint / 可选海外地址 # MINIMAX_BASE_URL=https://api.minimax.io/v1/image_generation # ───────────────────────────────────────────────────────────── # Example: Qwen / 通义生图示例 # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=qwen # QWEN_API_KEY=your-dashscope-key # QWEN_MODEL=qwen-image-2.0-pro # QWEN_BASE_URL=https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis # ───────────────────────────────────────────────────────────── # Example: Zhipu / 智谱生图示例 # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=zhipu # ZHIPU_API_KEY=your-zhipu-key # ZHIPU_MODEL=glm-image # ZHIPU_BASE_URL=https://open.bigmodel.cn/api/paas/v4/images/generations # ───────────────────────────────────────────────────────────── # Example: Volcengine / 火山引擎示例 # ───────────────────────────────────────────────────────────── # IMAGE_BACKEND=volcengine # VOLCENGINE_API_KEY=your-volcengine-key # VOLCENGINE_MODEL=doubao-seedream-4-5-251128 # VOLCENGINE_BASE_URL=https://operator.las.cn-beijing.volces.com/api/v1/images/generations # ───────────────────────────────────────────────────────────── # Extended / Experimental backends # 扩展 / 实验后端 # ───────────────────────────────────────────────────────────── # STABILITY_API_KEY=your-stability-key # STABILITY_MODEL=stable-image-core # STABILITY_BASE_URL=https://api.stability.ai # # BFL_API_KEY=your-bfl-key # BFL_MODE