Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yokingma/weclawsnpx agentmods add skills/yokingma/weclaws/lark-slidesWrote 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/yokingma/weclaws/lark-slides)<a href="https://agentmods.dev/skills/yokingma/weclaws/lark-slides"><img src="https://agentmods.dev/badge/skills/yokingma/weclaws/lark-slides.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 | $0.00074 | $0.09692 |
| Opus 5 | $0.00037 | $0.04846 |
| Sonnet 5 | $0.00015 | $0.01938 |
| Haiku 4.5 | $0.00007 | $0.00969 |
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 8d 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 `+create --slides` 的 `@./path` 占位符自动上传 → 拿 `file_token` 写进 This is a copy
98% identical to lark-slides — 1 line 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 — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slides (v1)
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md，其中包含认证、权限处理
CRITICAL — 生成任何 XML 之前，MUST 先用 Read 工具读取 xml-schema-quick-ref.md，禁止凭记忆猜测 XML 结构。
CRITICAL — 如果用户提到“模板”“套用模板”“参考某种主题/风格/版式”，或用户需求明显落在已有场景模板内（如工作汇报、产品介绍、商业计划书、培训、晋升汇报等），MUST 先用 scripts/template_tool.py 的 search 做模板检索；默认给出 2-3 个最匹配模板候选供用户选择。锁定模板后用 summarize 获取主题和布局摘要；只有需要布局骨架时才用 extract 裁切目标页型 XML。不要直接读取完整模板 XML。
[!NOTE]
scripts/template_tool.py需要 Python 3。references/template-index.json是脚本缓存/轻量路由索引，不是默认给 agent 阅读的文档；assets/templates/*.xml是机器资源，只应通过脚本摘要或裁切，不要全文读取。
CRITICAL — 使用模板生成或改写页面时，MUST 先 summarize 目标页型；只有需要具体布局骨架时才 extract。生成本地 XML 后，如可运行 Python，MUST 先用 scripts/layout_lint.py 检查 XML well-formed、重叠/越界/文本高度风险，再创建或追加页面。它不是完整 XSD schema 校验。
编辑已有幻灯片页面：优先用 +replace-slide（块级替换/插入，不动页序）；选择 action 和完整读-改-写流程见 lark-slides-edit-workflows.md。
身份选择
飞书幻灯片通常是用户自己的内容资源。默认应优先显式使用 --as user（用户身份）执行 slides 相关操作，始终显式指定身份。
--as user（推荐）：以当前登录用户身份创建、读取、管理演示文稿。执行前先完成用户授权：
lark-cli auth login --domain slides
--as bot：仅在用户明确要求以应用身份操作，或需要让 bot 持有/创建资源时使用。使用 bot 身份时，要额外确认 bot 是否真的有目标演示文稿的访问权限。
执行规则：
- 创建、读取、增删 slide、按用户给出的链接继续编辑已有 PPT，默认都先用
--as user。 - 如果出现权限不足，先检查当前是否误用了 bot 身份；不要默认回退到 bot。
- 只有在用户明确要求"用应用身份 / bot 身份操作"，或当前工作流就是 bot 创建资源后再做协作授权时，才切换到
--as bot。
快速开始
一条命令创建包含页面内容的 PPT（推荐）：
lark-cli slides +create --title "演示文稿标题" --slides '[
"<slide xmlns=\"http://www.larkoffice.com/sml/2.0\"><style><fill><fillColor color=\"rgb(245,245,245)\"/></fill></style><data><shape type=\"text\" topLeftX=\"80\" topLeftY=\"80\" width=\"800\" height=\"100\"><content textType=\"title\"><p>页面标题</p></content></shape><shape type=\"text\" topLeftX=\"80\" topLeftY=\"200\" width=\"800\" height=\"200\"><content textType=\"body\"><p>正文内容</p><ul><li><p>要点一</p></li><li><p>要点二</p></li></ul></content></shape></data></slide>"
]'
What ships with it
60 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.
- assets/templates/administration--all_hands_meeting.xml 104 KB
- assets/templates/administration--annual_gala.xml 62 KB
- assets/templates/administration--company_intro.xml 66 KB
- assets/templates/administration--corporate_culture.xml 84 KB
- assets/templates/hr--employee_training_workshop.xml 70 KB
- assets/templates/hr--employee_training.xml 52 KB
- assets/templates/hr--onboarding.xml 42 KB
- assets/templates/marketing--brand_communication.xml 68 KB
- assets/templates/marketing--brand_logo_design.xml 68 KB
- assets/templates/marketing--brand_operations_plan.xml 63 KB
- assets/templates/marketing--business_plan.xml 80 KB
- assets/templates/marketing--marketing_plan.xml 72 KB
- assets/templates/marketing--marketing_strategy.xml 72 KB
- assets/templates/marketing--product_whitepaper.xml 74 KB
- assets/templates/marketing--roadshow_business_plan.xml 75 KB
- assets/templates/misc--book_sharing.xml 70 KB
- assets/templates/misc--club_event_plan.xml 204 KB
- assets/templates/misc--student_career_plan.xml 83 KB
- assets/templates/office--dark_general.xml 198 KB
- assets/templates/office--dept_annual_report.xml 63 KB
- assets/templates/office--light_general.xml 183 KB
- assets/templates/office--project_kickoff.xml 148 KB
- assets/templates/office--quarterly_review.xml 58 KB
- assets/templates/office--work_report.xml 54 KB
- assets/templates/office--work_summary_report.xml 70 KB
- assets/templates/office--work_summary.xml 215 KB
- assets/templates/operations--brand_logo_design.xml 68 KB
- assets/templates/operations--brand_operations_plan.xml 63 KB
- assets/templates/operations--marketing_plan.xml 72 KB
- assets/templates/operations--product_promotion.xml 31 KB
- assets/templates/personal--experience_sharing.xml 110 KB
- assets/templates/personal--personal_resume.xml 97 KB
- assets/templates/personal--promotion_defense.xml 53 KB
- assets/templates/personal--promotion_report.xml 52 KB
- assets/templates/personal--self_intro.xml 32 KB
- assets/templates/personal--teaching_sharing.xml 152 KB
- assets/templates/product--business_case_analysis.xml 66 KB
- assets/templates/product--market_analysis.xml 42 KB
- assets/templates/product--product_analysis.xml 75 KB
- assets/templates/product--product_intro.xml 146 KB
- assets/templates/product--product_promotion_2.xml 31 KB
- assets/templates/product--product_promotion.xml 31 KB
- references/examples.md 8.5 KB
- references/lark-slides-create.md 7.0 KB
- references/lark-slides-edit-workflows.md 7.1 KB
- references/lark-slides-media-upload.md 5.5 KB
- references/lark-slides-replace-slide.md 11 KB
- references/lark-slides-xml-presentation-slide-create.md 8.6 KB
- references/lark-slides-xml-presentation-slide-delete.md 3.8 KB
- references/lark-slides-xml-presentation-slide-get.md 3.3 KB
- references/lark-slides-xml-presentation-slide-replace.md 6.9 KB
- references/lark-slides-xml-presentations-get.md 2.8 KB
- references/slide-templates.md 9.1 KB
- references/slides_demo.xml 12 KB
- references/slides_xml_schema_definition.xml 166 KB
- references/template-catalog.md 27 KB
- references/template-index.json 51 KB
- references/xml-format-guide.md 8.9 KB
- references/xml-schema-quick-ref.md 5.9 KB
- scripts/layout_lint_test.py 6.8 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.
- 8d ago First seen · 526 lines · 74 tokens per session scan A bb3eb7d1e022
lark-slides is a skill published in the GitHub repository yokingma/weclaws (38 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 9,692 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 98% identical to lark-slides, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
csv-analyzer
Analyze CSV files to generate summary statistics, detect data quality issues, and produce formatted reports.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
wxjava-api-contributor
A contributor guide for adding or maintaining official WeChat API support in WxJava, a Java software development kit. It covers services, request and response data objects, data conversion, HTTP handling, starter configuration, and regression tests.
wxjava-troubleshooter
A troubleshooting guide for WxJava, a Java library used to connect applications to WeChat services. It organizes problems involving setup, access tokens, signatures, payment certificates, callbacks, data conversion, network requests, and multiple accounts.
wxjava-upgrade-guide
A migration guide for upgrading WxJava, a Java software development kit for WeChat services, from one version or dependency setup to another. It checks dependencies, Java versions, configuration, HTTP clients, and public programming interfaces.