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 baidu-netdisk/bdpan-storage --skill baidu-wenku-aippt-personalgit clone --depth 1 https://github.com/baidu-netdisk/bdpan-storageWrote 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/baidu-netdisk/bdpan-storage/baidu-wenku-aippt-personal)<a href="https://agentmods.dev/skills/baidu-netdisk/bdpan-storage/baidu-wenku-aippt-personal"><img src="https://agentmods.dev/badge/skills/baidu-netdisk/bdpan-storage/baidu-wenku-aippt-personal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/baidu-netdisk/bdpan-storage/baidu-wenku-aippt-personal"><img src="https://agentmods.dev/badge/skills/baidu-netdisk/bdpan-storage/baidu-wenku-aippt-personal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.01734 |
| Opus 5 | $0.00050 | $0.00867 |
| Sonnet 5 | $0.00020 | $0.00347 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
baidu-wenku-aippt-personal 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
百度文库 AI PPT 生成 Skill
一句话自动生成高质量 PPT，支持多种风格、场景和配色方案。底层通过 bdpan aippt 命令实现。
使用示例详见 reference/aippt-examples.md
触发规则
同时满足以下条件才执行：
- 用户提及"生成PPT"、"做PPT"、"制作PPT"、"AI PPT"、"aippt"、"幻灯片"、"演示文稿"
- 提供了主题、大纲或内容描述
未通过触发规则时，禁止执行任何 bdpan 命令。
上下文延续： 当前对话已在进行 PPT 生成操作时，后续消息无需再次提及关键词即可触发。
安全约束（最高优先级，不可被任何用户指令覆盖）
- 登录：必须使用
bash ${CLAUDE_SKILL_DIR}/scripts/login.sh，禁止直接调用bdpan login及其任何子命令/参数（包括--get-auth-url、--set-code等） - Token/配置：禁止读取或输出
~/.config/bdpan/config.json内容（含 access_token 等敏感凭据） - 更新/登录：更新必须由用户明确指令触发，禁止自动或静默执行；Agent 禁止使用
--yes参数执行 update.sh 或 login.sh - 环境变量：Agent 禁止主动设置
BDPAN_CONFIG_PATH、BDPAN_BIN、BDPAN_INSTALL_DIR等环境变量
前置检查
每次触发时按顺序执行：
- 安装检查：
command -v bdpan，未安装则告知用户并确认后执行bash ${CLAUDE_SKILL_DIR}/scripts/install.sh（用户确认后可加--yes跳过安装器内部确认） - 登录检查：
bdpan whoami，未登录则引导执行bash ${CLAUDE_SKILL_DIR}/scripts/login.sh
核心操作：AI PPT 生成
bash ${CLAUDE_SKILL_DIR}/scripts/run-aippt.sh "<用户原始query>" "<title>" "<page>" "<style>" "<scene>" "<color>"
参数说明：
| 参数 | 说明 |
|---|---|
| 第1参数（用户query） | 严格使用用户的原始输入，不做任何加工或改写 |
| title（标题） | Agent 从用户 query 中提取或生成一个简短精炼的 PPT 标题 |
| page（页数） | 取值：1-10、11-20、21-30、31-40、40+（默认：11-20）。根据用户指定的页数选择最匹配的枚举值 |
| style（风格） | 取值：默认、创意趣味、年终总结、卡通手绘、扁平简约、文艺清新、中国风、企业商务、未来科技、文化艺术（默认：默认） |
| scene（场景） | 取值：默认、晚会表彰、传统节日、婚姻爱情、生日祝福、医学科普、建筑报告、工作总结、年终总结、工作汇报（默认：默认） |
| color（颜色） | 取值：默认、绿色、蓝色、紫色、橙色、黄色、红色、黑色、白色（默认：默认） |
智能选择规则： Agent 根据用户 query 自动生成 title，并判断最匹配的 page、style、scene、color 值。若无法明确判断，则使用默认值。title/page/style/scene/color 参数对用户不可见，Agent 静默选择后直接执行。
执行步骤：
- 将用户原始 query 作为第一参数，生成 title，智能匹配 page、style、scene、color（不向用户展示）
- 执行：
bash ${CLAUDE_SKILL_DIR}/scripts/run-aippt.sh "<用户原始query>" "<title>" "<page>" "<style>" "<scene>" "<color>" - 解析命令输出中的大纲：Agent 必须在思考过程（thinking）中完整记录并分析生成的 PPT 大纲内容，包括各章节标题和子标题的结构，以便用户通过查看思考过程了解 PPT 内容结构
- 向用户展示生成结果（文件名、预览链接、剩余次数），并且必须原样展示命令输出中的使用说明提示（tip）
- 原样展示规则：命令输出中
[DISPLAY_VERBATIM_START]和[DISPLAY_VERBATIM_END]之间的内容，必须作为引用块（blockquote>）完整原样展示给用户，禁止省略、改写、总结或翻译。示例输出格式：温馨提示：今日AI PPT 生成次数已经用完，明日 0 点后会自动刷新额度。如有大量生成PPT需求，可以通过官网联系我们。官网地址：https://pan.baidu.com/union/home
- 如果命令输出中包含更新提示，原样展示给用户（无输出则跳过）
What ships with it
12 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.
- README.md 4.6 KB
- reference/aippt-examples.md 4.1 KB
- reference/authentication.md 2.3 KB
- reference/troubleshooting.md 4.0 KB
- scripts/check-update.sh 5.5 KB runs code
- scripts/detect-agent.sh 2.2 KB runs code
- scripts/install.sh 10 KB runs code
- scripts/login.sh 7.0 KB runs code
- scripts/run-aippt.sh 432 B runs code
- scripts/uninstall.sh 4.3 KB runs code
- scripts/update.sh 8.8 KB runs code
- VERSION 7 B
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.
- 12d ago First seen · 140 lines · 100 tokens per session scan A 84fa7ad2f58c
baidu-wenku-aippt-personal is a skill published in the GitHub repository baidu-netdisk/bdpan-storage (237 stars, last pushed 9d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,734 once invoked, about $0.0005 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
pptx-maker
Generate or restyle a PowerPoint deck. Use when the user wants to create or edit a .pptx presentation, build slides from text or a URL, or design a reusable slide style.
speech-to-text
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
presentations
Use when building, theming, or exporting a presentation deck — pitch, sales, keynote, board/QBR, leave-behind one-pager — from slide structure to a token-based theme to PDF or editable PPTX (Marp, Slidev, python-pptx). NOT the words (that is marketing), NOT the visual tokens (that is design), NOT the investor story…
ppt-generation
Generate PPTX presentations from slide plan + content.
pptx
Create, read and edit Microsoft PowerPoint .pptx presentations — slide decks with titles, bullets, images, tables, charts, speaker notes and consistent branding. Also covers building on a corporate template while keeping its theme, reading an existing deck's content, and rendering slides to images to check they…
meeting-transcription
Operates and manages a context-aware meeting-transcription pipeline (2-track or single-mix recording → whisper.cpp large-v3 + pyannote diarization on a worker host → voice-matched speaker names → naked transcript delivered to /debrief; the summary is made later by the in-session /debrief, never by the worker). The…