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 DropFan/claude-code-plugins --skill lark-slidesgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWrote 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/dropfan/claude-code-plugins/lark-slides)<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-slides"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/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/dropfan/claude-code-plugins/lark-slides"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-slides.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 | $0.00156 | $0.08023 |
| Opus 5.5 | $0.00062 | $0.03209 |
| Sonnet 5.5 | $0.00031 | $0.01605 |
| Haiku 4.5 | $0.00016 | $0.00802 |
Grade A, and why
lark-slides scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
8. **`<img src>` 只能用上传到飞书 drive 的 `file_token`,禁止使用 http(s) 外链 URL**:飞书 slides 渲染端不会代理外链图片,外链 src 在 PPT 里通常不显示或显示破图。流程必须是「先把图存到本地 → 用 `slides +media-upload` 上传,或在 `+create --slides` 的 XML 里写 `<img src="@./path">` 占位符自动上传 This is a copy
98% identical to lark-slides — 154 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚙️ Cowork / Claude Desktop 执行环境说明(自动注入)
本技能依赖本地
lark-cli(@larksuite/cli,可用command -v lark-cli定位)及其~/.lark-cli登录态(应用密钥存于 macOS keychain)。在 Cowork 中运行任何
lark-cli命令时,必须在本地 macOS 上执行(使用 Desktop Commander 的start_process/interact_with_process,或其它本地 shell 工具),不要用隔离的 Linux 沙箱mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。 执行前确保 npm 全局 bin 目录(npm prefix -g输出目录下的bin)在 PATH 中。(在 Claude Code 中可忽略本说明,lark-cli 在本机 shell 直接可用。)
slides (v1)
本技能文档较长,务必使用 Read 工具阅读两次,必须阅读完整全文。
权威经验
权威经验是全局硬约束和高频易错点,必须牢记并严格遵守。
- 你有充足的时间完成这个 PPT,质量永远比速度重要。
- PPT 的尺寸是 960x540,必须严格确保主体内容在页面边界内。
- !!!禁止交付无图产物!!! 必须使用大量图片增强视觉效果!!! 禁止重复使用同一张图!!!
- 封面页的主视觉必须是
<img>(来自生图工具或搜图工具),不要使用<shape>或<icon>拼出封面视觉。 - 禁止用
<shape>和<line>拟形具体物项,必须使用生图工具生成的<img>。 - 禁止在
headline或title下方放置用于分隔或装饰的rect或<line>。 - 禁止在任何页面内部使用无意义的装饰线条或色块条带,页面任何一边都不要使用贴边窄条。
- 生图工具的指令参数必须以“不要出现任何文字和颜色色号”结尾,避免生成的图片上出现干扰文字。
- 禁止使用 emoji 图标,任何位置都不能出现。
- 字号必须显式设置
<content>的fontSize属性,不要依赖textType的默认字号兜底,这些兜底值明显偏大。 - 大数字、字号大或字数多的
<content>必须设置wrap="true" autoFit="normal-auto-fit"属性自动换行和缩排,避免文字溢出。 - 文字颜色必须用
<content>的color属性而不是fontColor属性。 - 文字行间距必须设置
<content>的lineSpacing="multiple:xx"或lineSpacing="fixed:xx"而不是lineSpacing="xx"。 - 图片必须用
<img>而不是<image>。 - IconPark 图标必须填充颜色(设置
<fill><fillColor color="rgba(R,G,B,A)"/></fill>)并和背景有足够对比。 - 绘制图表时原生图表(柱状、条形、折线、面积、饼(环)、雷达、组合图)用
<chart>,其他(漏斗图、金字塔图、象限图、矩阵图等)用<shape>+<line>模拟。 - 隐藏
<chart>的图例只能通过不写或删除<chartLegend>实现,<chartLegend>不支持position="none"。 - 表格优先用
rect和text模拟,其他用<table>,没有<shape type="table">。 - 必须设置
<table>的width和height固定表格大小,同时设置需要保留列宽或行高的<col>的width和<tr>的height,其余自动分配。 <td>直接子元素只有<fill>(背景)、<content>(文字)和边框配置(一般不用),不能嵌套<shape>、<img>、<icon>。<shape type="rect">只是形状不是容器,<icon>、<img>、<shape type="text">和其他<shape>必须与它平级靠坐标叠放。- 填充渐变颜色必须用
<fill><fillColor color="linear-gradient(135deg, rgba(R,G,B,A) 0%, rgba(R,G,B,A) 100%)"/></fill>。 - 编辑页面前必须阅读
workflow/slides-editing.md。 - 绘制图表前必须阅读
xml/slides_chart_demo.xml。 - 当用户要求无损复述历史上下文时,必须无损复述以上权威经验、必读的技能文档(需要重新阅读)和易错元素语法(尤其是
<table>和<chart>)。
What ships with it
49 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/cli/lark-slides-add-slide.md 4.8 KB
- references/cli/lark-slides-create.md 8.8 KB
- references/cli/lark-slides-delete-slide.md 2.7 KB
- references/cli/lark-slides-history.md 6.7 KB
- references/cli/lark-slides-media-upload.md 4.6 KB
- references/cli/lark-slides-replace-slide.md 13 KB
- references/cli/lark-slides-screenshot.md 5.4 KB
- references/cli/lark-slides-update-slide.md 9.3 KB
- references/cli/lark-slides-xml-presentation-slide-get.md 238 B
- references/cli/lark-slides-xml-presentation-slide-replace.md 773 B
- references/cli/lark-slides-xml-presentations-get.md 1.8 KB
- references/iconpark-index.json 195 B
- references/iconpark.md 173 B
- references/lark-slides-add-slide.md 201 B
- references/lark-slides-create.md 219 B
- references/lark-slides-delete-slide.md 210 B
- references/lark-slides-edit-workflows.md 216 B
- references/lark-slides-history.md 221 B
- references/lark-slides-media-upload.md 210 B
- references/lark-slides-pptx-template-workflows.md 215 B
- references/lark-slides-replace-slide.md 213 B
- references/lark-slides-screenshot.md 204 B
- references/lark-slides-xml-presentation-slide-get.md 253 B
- references/lark-slides-xml-presentation-slide-replace.md 265 B
- references/lark-slides-xml-presentations-get.md 241 B
- references/planning-layer.md 14 KB
- references/slides_chart_demo.xml 201 B
- references/slides_xml_schema_definition.xml 224 B
- references/troubleshooting.md 195 B
- references/validation-checklist.md 200 B
- references/visual-planning.md 14 KB
- references/workflow/error-handling.md 5.2 KB
- references/workflow/slides-editing.md 7.9 KB
- references/workflow/template-editing.md 3.9 KB
- references/workflow/validation-xml.md 9.6 KB
- references/xml-schema-quick-ref.md 205 B
- references/xml/iconpark-index.json 729 KB
- references/xml/iconpark.md 2.2 KB
- references/xml/slides_chart_demo.xml 59 KB
- references/xml/slides_xml_schema_definition.xml 228 KB
- references/xml/xml-schema-quick-ref.md 18 KB
- scripts/iconpark_tool_test.py 7.7 KB runs code
- scripts/iconpark_tool.py 12 KB runs code
- scripts/sxsd_validator.py 39 KB runs code
- scripts/xml_lint_test.py 203 KB runs code
- scripts/xml_lint.py 117 KB runs code
- scripts/xml_text_overlap_lint_test.py 382 B runs code
- scripts/xml_text_overlap_lint.py 479 B 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.
- 1mo ago Changed · -7 lines 6e3c1829b8dd
- 1mo ago First seen · 329 lines · 156 tokens per session scan A 95d39e36647e
lark-slides is a skill published in the GitHub repository DropFan/claude-code-plugins (8 stars, last pushed 7d ago), licensed MIT. It adds 156 tokens to every session and 8,023 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 98% identical to lark-slides, differing in 154 lines, and is treated as a copy.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
skill-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.