Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhixuli0406/DuDuClaw --skill pptxgit clone --depth 1 https://github.com/zhixuli0406/DuDuClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhixuli0406/duduclaw/pptx)<a href="https://agentmods.dev/skills/zhixuli0406/duduclaw/pptx"><img src="https://agentmods.dev/badge/skills/zhixuli0406/duduclaw/pptx.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01152 |
| Opus 5 | $0.00019 | $0.00576 |
| Sonnet 5 | $0.00008 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
pptx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
PowerPoint (.pptx) 簡報處理
處理簡報的三件事：讀取抽取、建立、轉換 PDF。腳本用 uv run 執行，依賴以
PEP 723 inline metadata 宣告（python-pptx）；uv 不存在時改用
pip install python-pptx 後 python3 執行。
何時使用
- 收到
.pptx附件，需要讀出各投影片文字來彙總或改寫。 - 要把大綱/重點產出成一份簡報回傳。
- 需要把簡報轉成 PDF 交付。
腳本
腳本位於本技能的 scripts/ 目錄。兩種執行路徑，依你有沒有 Bash 工具擇一：
-
有 Bash / shell 工具 → 直接跑
uv run scripts/<script>.py ...（見下方各節）。 -
沒有 Bash / shell 工具（API 模式後端，如 Grok / DeepSeek / MiniMax） → 不要只回文字大綱， 改用
office_scriptMCP 工具在伺服器端跑同一支腳本：skill：pptxscript：create/extract/to_pdf（不含路徑，.py可省略）args：字串陣列，等同uv run後面那串參數；任何路徑須落在你的 agent 目錄或其attachments/。
例（把大綱做成簡報）：
{"skill": "pptx", "script": "create", "args": ["outline.md", "--out", "/你的agent目錄/attachments/deck.pptx"]}工具以
uv run（uv 不存在時退回python3）在你的 agent 目錄內執行並回傳腳本 stdout； 產出檔案後務必依下方 📎DELIVER 協定交付。
1. 讀取抽取 — extract.py
uv run scripts/extract.py <input.pptx> --format json # 每張投影片 → 文字段落陣列
uv run scripts/extract.py <input.pptx> --format md # 每張投影片 → markdown 段落
JSON 輸出 {"slides": [{"index": 1, "texts": [...]}, ...]}。
2. 建立 — create.py
從 markdown 大綱或 JSON 建立 .pptx（每個 # 標題起一張新投影片，- 為條列）：
來源型別依副檔名判定（.json → JSON，其餘 → markdown）：
uv run scripts/create.py outline.md --out /abs/out.pptx
uv run scripts/create.py deck.json --out /abs/out.pptx
JSON schema：{"slides": [{"title": str, "bullets": [str, ...]}, ...]}。
3. 轉 PDF — to_pdf.py
uv run scripts/to_pdf.py <input.pptx> --outdir <dir>
未安裝 LibreOffice（soffice）時明確回報未安裝、僅轉換功能不可用（優雅降級）。
交付檔案給使用者（📎DELIVER 協定）
產出後在回覆最後另起一行：
📎DELIVER:/絕對路徑/deck.pptx
路徑須為絕對路徑且位於你的 agent 工作目錄（或其 attachments/）下；標記行不顯示給
使用者，請另用文字說明。
API 模式同樣適用：用 office_script 產出檔案後，一樣在回覆最後一行輸出
📎DELIVER:<絕對路徑>，gateway 才會把 .pptx 傳回使用者——只回文字大綱不算完成。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 91 lines · 39 tokens per session scan A ca8ae0529609
pptx is a skill published in the GitHub repository zhixuli0406/DuDuClaw (47 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,152 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
office-router
Route Office requests into the correct xlsx, docx, or pptx workflow, while preferring Slidev for new presentation drafts unless .pptx is explicitly required.
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
pptx-review
Review existing pptx decks with V1 slide extraction, and only use direct pptx generation paths when Slidev is not appropriate or .pptx is explicitly required.
pptx-creator
Create PowerPoint presentations from outlines, Markdown, or templates.
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…