一键导入
mofa-agent-memory-deck
Visualizes an agent's internal thought process, reasoning, and memory observations into a professional slide presentation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Visualizes an agent's internal thought process, reasoning, and memory observations into a professional slide presentation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Deploy static sites to GitHub Pages or Mac Mini hosting. Triggers: mofa publish, deploy site, publish website, 发布网站, 部署网页, github pages, deploy to mini, host website, 上线, push to pages, mofa deploy, 发布到GitHub.
Build or scaffold websites from content using Quarto, Astro, Next.js, or React/Vite. Triggers: mofa site, build website, make a website, 建网站, 做个网站, generate site, mofa web, create website, 生成网页, build lesson site, build docs site, 做个教程网站.
Shared CLI binary for all mofa skills (slides, cards, comic, infographic, video). Not a user-facing skill.
AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles.
AI-generated comic strips and illustrations. Triggers: comic, manga, xkcd, 漫画, comic strip, 四格漫画, panel comic, illustration strip, snoopy. Generates multi-panel comics via Gemini with optional Qwen-Edit refinement, stitched into a single image.
AI-generated infographics and visual posters. Triggers: infographic, poster, 信息图, 海报, data poster, visual summary, mofa infographic. Generates multi-section infographic via Gemini with optional Qwen-Edit refinement, stitched into a single tall image.
| name | mofa-agent-memory-deck |
| description | Visualizes an agent's internal thought process, reasoning, and memory observations into a professional slide presentation. |
This skill ingests an agent's memory logs—thoughts, decisions, and system observations—and synthesizes them into an engaging PowerPoint (.pptx) presentation. It bridges backend memory systems (like mofa-memory) with human-readable visual reporting, creating transparent, auditable slides of an agent's execution history.
Activate this skill when user says:
# Generate a comprehensive presentation deck from a pre-processed slides JSON
mofa slides \
--slide-dir ./mofa-slides \
--style memory-review \
--input agent_memory_slides.json \
--out memory_audit.pptx
The skill expects a raw JSON payload describing the agent's memory execution trace over a specific session. You can find a sample payload in examples/mock_agent_trace.json:
This skill conceptually starts from a raw JSON payload describing the agent's memory execution trace over a specific session. You can find a sample trace payload in examples/mock_agent_trace.json:
{
"agent_id": "Research-Agent-02",
"task": "Analyze distributed consensus algorithms for agents",
"traces": [
{ "timestamp": "2026-03-16T10:00:00Z", "type": "Observation", "content": "Found 12 research papers on Raft networks." },
{ "timestamp": "2026-03-16T10:05:00Z", "type": "Decision", "content": "Filtered out papers older than 2024 to ensure relevancy." }
]
}
In practice, this trace-shaped JSON is first transformed (by separate tooling or an upstream skill) into a slides input of the form:
[
{ "prompt": "Summarize the overall task and agent objective for the deck intro slide." },
{ "prompt": "Explain the key observations the agent made about Raft networks." }
]
This slides JSON (for example, agent_memory_slides.json) is what you pass to the mofa slides CLI via --input. The memory-review style must be available under the mofa-slides/styles/ directory (for example, mofa-slides/styles/memory-review.toml) so that --style memory-review can be resolved. The style template acts as a prefix instructing the model on how to organize the slides (e.g., Executive Summary, Key Decisions, Future Context) before passing the results to the standard mofa slides backend pptxgenjs/Rust generator.