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 ddpie/lark-mcp-on-agentcore --skill lark-slidesgit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-slides)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-slides"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-slides/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/ddpie/lark-mcp-on-agentcore/lark-slides"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-slides.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 | $0.00174 | $0.03158 |
| Opus 5 | $0.00087 | $0.01579 |
| Sonnet 5 | $0.00035 | $0.00632 |
| Haiku 4.5 | $0.00017 | $0.00316 |
Grade A, and why
lark-slides 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slides (v1)
Quick Reference
| 用户需求 | 优先动作 | 关键文档 / 工具 |
|---|---|---|
| 新建 PPT | 先规划 slide_plan.json，再按复杂度选择一步或两步创建 |
planning-layer.md、visual-planning.md、asset-planning.md、lark_slides_create |
| 已有 PPT 大幅改写 | 多页整页重建用 lark_slides_replace_pages，单页局部编辑用 lark_slides_replace_slide |
lark_invoke(tool_name="lark_slides_xml_presentations_get")、lark-slides-replace-pages.md、lark-slides-edit-workflows.md |
| 编辑单个标题、文本块、图片或局部元素 | 优先块级替换/插入，不改页序 | lark_slides_replace_slide |
| 读取或分析已有 PPT | 解析 slides/wiki token，回读全文或单页 XML，保存 xml_presentation_id、slide_id、revision_id |
lark_invoke(tool_name="lark_slides_xml_presentations_get")、lark_invoke(tool_name="lark_slides_xml_presentation_slide_get") |
| 获取幻灯片页面截图 | 用 slide_id 或页号指定页面 |
lark_slides_screenshot、lark_get_skill(domain="slides", section="screenshot") |
| 上传或使用图片 | 先上传为 file_token，禁止直接写 http(s) 外链 |
lark_slides_media_upload，或 lark_slides_create 的 @./path 占位符 |
| 在 slide 中绘制柱/条/折线/面积/雷达/饼等有数据序列的图表 | 使用原生 <chart> 元素 |
xml-schema-quick-ref.md |
| 在 slide 中绘制流程图、时序图、架构图、散点图、漏斗图或装饰图案 | 必须先调用 lark_get_skill(domain="slides", section="whiteboard") 获取参考文档，再生成 <whiteboard> 元素 |
lark_get_skill(domain="slides", section="whiteboard") |
| 使用语义图标 | 先检索 IconPark，再写 <icon iconType="..."> |
lark_exec_script(script="lark-slides/scripts/iconpark_tool.py", args=["search", ...])、lark_get_skill(domain="slides", section="iconpark") |
| 创建失败、空白页、3350001、布局异常 | 先回读状态，再按排障清单修复，不假设原操作原子成功 | troubleshooting.md、validation-checklist.md |
CRITICAL — 生成任何 XML 之前，MUST 先调用 lark_get_skill(domain="slides", section="xml-schema-quick-ref") 获取 XML 协议规则，禁止凭记忆猜测 XML 结构。
CRITICAL — PPT 生成与模板编辑硬约束：PPT 的尺寸是 960x540，确保主体内容在页面边界内。多用生图，辅助搜图，必须要图文并茂。不要为了画出一个具象物体而堆叠 3 个以上仅用于拟形的 shape。生成背景图时必须在 prompt 中明确要求不要出现任何文字。用户指定 PPT 模板时，用 lark_drive_import(type="slides") 导入成 lark slides，回读理解每页版式后，直接在该 slides 上编辑，可以填改文字和图片、按需增删模板页，必须严格沿用原版式和字体，只改内容不做设计，完成后回读并微调，凝练文字或缩减字号消除文字溢出，调整 shape 顺序或位置避免文字遮挡。
What ships with it
28 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.
- references/asset-planning.md 7.5 KB
- references/examples.md 2.9 KB
- references/iconpark-index.json 816 KB
- references/iconpark.md 2.2 KB
- references/lark-slides-create.md 4.5 KB
- references/lark-slides-edit-workflows.md 4.5 KB
- references/lark-slides-media-upload.md 1.8 KB
- references/lark-slides-replace-pages.md 3.3 KB
- references/lark-slides-replace-slide.md 3.3 KB
- references/lark-slides-screenshot.md 3.3 KB
- references/lark-slides-whiteboard.md 14 KB
- references/lark-slides-xml-presentation-slide-create.md 2.3 KB
- references/lark-slides-xml-presentation-slide-delete.md 1.1 KB
- references/lark-slides-xml-presentation-slide-get.md 1.4 KB
- references/lark-slides-xml-presentation-slide-replace.md 1.7 KB
- references/lark-slides-xml-presentations-get.md 1.2 KB
- references/planning-layer.md 14 KB
- references/slide-templates.md 9.1 KB
- references/slides_chart_demo.xml 66 KB
- references/slides_demo.xml 12 KB
- references/slides_xml_schema_definition.xml 169 KB
- references/troubleshooting.md 5.5 KB
- references/validation-checklist.md 5.3 KB
- references/visual-planning.md 14 KB
- references/xml-format-guide.md 11 KB
- references/xml-schema-quick-ref.md 7.3 KB
- scripts/iconpark_tool.py 12 KB runs code
- scripts/xml_text_overlap_lint.py 13 KB runs code
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.
- 9d ago First seen · 122 lines · 174 tokens per session scan A f213ca145576
lark-slides is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 12d ago), licensed MIT. It adds 174 tokens to every session and 3,158 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
lark-cli
A command-line tool for working with Lark, also called Feishu, a workplace collaboration platform. It covers services such as calendars, meetings, documents, spreadsheets, messaging, tasks, approvals, and shared files.
cherry-studio-design-language
A design system and template library for creating Cherry Studio presentations and other visual materials. It defines reusable page layouts, spacing, typography, icons, and visual rules.
feishu-card-json-v2
Construct, refine, review, validate, and package polished Feishu/Lark Card JSON 2.0 payloads. Use when creating cards for Feishu custom-bot webhooks, application bots, notifications, alerts, reports, dashboards, approvals, forms, callbacks, updates, streaming AI output, Markdown-rich content, tables, charts, images…
lark-wiki-migration
A Feishu wiki migration tool copies all document pages from one Feishu knowledge base to another. Feishu is a workplace collaboration platform, and a wiki is an organized collection of linked documents.
004-Frank-AI项目PPT智能生成工具
A Chinese-language aid for turning an AI or digital-project proposal into a presentation outline with slide titles, key points, visual suggestions, and speaking notes.