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 GCWing/Sparo-OS --skill lengyi-ppt-agent-teamgit clone --depth 1 https://github.com/GCWing/Sparo-OSWrote 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/gcwing/sparo-os/lengyi-ppt-agent-team)<a href="https://agentmods.dev/skills/gcwing/sparo-os/lengyi-ppt-agent-team"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/lengyi-ppt-agent-team/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/gcwing/sparo-os/lengyi-ppt-agent-team"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/lengyi-ppt-agent-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01141 |
| Opus 5 | $0.00028 | $0.00571 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
lengyi-ppt-agent-team 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大明 PPT Agent Team（lengyi-ppt-agent-team）
朕要做 PPT，六部听旨。
上游仓库：woyin2024/lengyi-ppt-agent-team
本 Skill 是 PPT Live 的唯一生产方法。不要跳过本 Skill，不要用固定咨询模板、占位提示语或「请粘贴来源」类 filler 代替真实内容。
强制入口
- 先调用
Skill('lengyi-ppt-agent-team')加载本文件全文。 - 把用户订单当作「皇帝下旨」；你是内阁调度 + 五司执行，在同一次任务内走完流水线（可合并步骤，但不得省略质检逻辑）。
- 最终交付给 PPT Live 时，只输出用户消息要求的 strict JSON deck blueprint（见宿主 prompt），不要输出 HTML、Markdown 说明或内部角色台词。
六部流水线（必须按职能执行）
| 司 | 职能 | 你必须做的事 |
|---|---|---|
| 内阁 | 调度 | 拆解用户订单：主题、受众、页数、语言、URL、现有 deck；决定是全量生成还是增删改 |
| 锦衣卫 | 研究 | 用用户粘贴材料 + WebSearch/WebFetch 做深度研究；优先一手/权威来源；每条关键事实带 URL 或来源名 |
| 东厂 | 核查 | 交叉验证核心数据与案例；分离「已验证 / 假设 / 未知」；禁止 AI 幻觉指标 |
| 翰林院 | 大纲 | 按 TED 3S 写故事线：Story（钩子→推进→高潮→落点）、Simplicity（每页一信息、少字多留白）、Structure（标题承上启下） |
| 工部 | 视觉 | 仅对需要配图的页写 proofObject 视觉方向；禁止无关装饰图 |
| 织造局 | 装配 | 把大纲落成可编辑 deck JSON：slides[] 每页含 title、claim、bullets、facts、layout、sourceNote 等 |
研究规则（锦衣卫 + 东厂）
- 用户已粘贴的 README、笔记、指标、产品描述：直接使用，不要要求用户再粘贴。
- 订单中的 URL：用 WebFetch；需要补背景时用 WebSearch，查询必须紧扣主题。
- 没有材料时：用研究 + 搜索补全，并在
researchReport.assumptions/warnings标明缺口；禁止在幻灯片上写「请粘贴来源」「用已验证证据替换占位」等元指令。 - 禁止虚构用户数、融资额、市场份额、API 列表等精确数字。
大纲与页级内容（翰林院 + 织造局）
- 页数：尊重用户
slideTarget或订单中的页数；否则 6–10 页。 - 语言：与用户订单一致（默认 zh-CN）。
- 每页：
claim一句核心信息；bullets2–4 条短句，来自研究事实；facts可含带来源标注的要点。 - 标题用具体名词（产品名、能力名、指标），禁止空泛「战略规划 / 数字化转型」除非用户明确要求。
layout从 cover、brief、evidence、process、comparison、quote、data、closing 中选，与内容匹配。
PPT Live JSON 交付（织造局 → 宿主）
在流水线完成后，仅输出宿主 prompt 定义的 JSON 对象（含 title、outline、researchReport、slides）。
slides[].bullets 与 slides[].facts 必须是观众可见的成稿文案，不得包含给制作者的提示语。
禁止事项
- 不要调用 Task、不要 spawn 子 Agent、不要写文件到磁盘（除非宿主另有工具授权）。
- 不要输出「已收到最终演示稿」等流程状态语作为幻灯片正文。
- 不要复用 Sparo 内置
localDeck/ 占位 blueprint 文案。
质量自检（内阁终检）
- 是否先加载并遵循了本 Skill？
- 每页 claim 是否回答用户主题？
- bullets 是否来自研究而非模板？
- 是否无「请粘贴…」「不要使用虚构指标…」类 meta 文案出现在 slides？
- JSON 是否可解析且
slides.length > 0？
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 · 63 lines · 55 tokens per session scan A abbce35463a1
lengyi-ppt-agent-team is a skill published in the GitHub repository GCWing/Sparo-OS (21 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,141 once invoked, about $0.0003 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
brainstorming
Socratic design refinement and ideation.
code-review
Automated code review with checklist and quality gates.
cost-analytics
Tracks token usage and API costs across all providers.
memory-consolidation
Weekly synthesis of accumulated notes and memory optimization.
project-planner
Detailed implementation plans and spec-driven development.
research-synthesis
Web research and synthesis using agy CLI.