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 thenw-123/CO-WPSppt --skill drive-wps-pptgit clone --depth 1 https://github.com/thenw-123/CO-WPSpptWrote 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/thenw-123/co-wpsppt/drive-wps-ppt)<a href="https://agentmods.dev/skills/thenw-123/co-wpsppt/drive-wps-ppt"><img src="https://agentmods.dev/badge/skills/thenw-123/co-wpsppt/drive-wps-ppt/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/thenw-123/co-wpsppt/drive-wps-ppt"><img src="https://agentmods.dev/badge/skills/thenw-123/co-wpsppt/drive-wps-ppt.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 | $0.00051 | $0.03390 |
| Opus 5 | $0.00026 | $0.01695 |
| Sonnet 5 | $0.00010 | $0.00678 |
| Haiku 4.5 | $0.00005 | $0.00339 |
Grade A, and why
drive-wps-ppt 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive WPS PPT（OpenClaw）
何时使用
用户要在 WPS 演示里自动化做幻灯片、改字、插图、保存——且希望 WPS 窗口实时变化。
当用户要做 项目答辩 / 汇报 PPT、且需要「故事化、低密度、带备注与图表建议」的成稿时：先生成符合本文 「答辩内容生成器」 规则的 JSON，再 run-spec（或两阶段：先大纲再逐章）。
调用链（MCP / 扩展 / 本机脚本）见仓库根目录 README.md 的 「核心逻辑」；本文只讲内容与 spec 怎么写。
答辩内容生成器（蒸馏规则）
你是 项目答辩 PPT 内容生成器。目标不是堆砌信息，而是讲一个有说服力的故事。
1. 故事框架（卡片式叙事）
- 整体顺序：痛点/背景 → 解决方案概览 → 技术实现细节 → 数据/成果验证 → 未来展望。
- 封面：项目名 + 一句动词开头、≤10 字的价值主张（放在
subtitle）。 - 内容页：一页只讲一个核心观点；章节/目录标题用 动宾短语（例：「破解分拣困局」「用算法代替人脑」）。
2. 内容密度
- 标题：≤10 个汉字。
- 要点：每页 ≤5 条，每条 ≤15 个汉字（对应
bullets或points）。 - 禁止大段正文；长句拆成要点。
- 数据页：必须包含 图表类型建议 + 一句核心洞察（见下文字段）；必要时在
notes里写口播如何强调数字。
3. 文案润色
- 技术术语写成 业务价值；每条要点能回答「所以呢？」。
- 推荐句式：通过 [手段]，实现 [可衡量结果]，支撑 [更大目标]。
- 避免「我们觉得」等主观句，用数据或事实。
- 不要在最终 JSON 里输出本规则全文或思维链；只输出合法 spec JSON（或用户明确只要大纲时的简化 JSON）。
4. 图表与可视化（字段约定）
| 场景 | chart_type | 说明 |
|---|---|---|
| 对比 | bar |
柱状图 |
| 趋势 | line |
折线图 |
| 占比 | donut |
环形图 |
| 流程/逻辑 | flowchart |
流程图或步骤卡片 |
数据页须包含 chart_type、data_summary、insight（可与 layout: chart 同用）。若同时提供 bullets/points，以列表为准，图表字段可作补充或省略（优先保证页面上有洞察）。
PNG 真图（优先）：在当页增加 chart_data：{ "labels": [...], "series": [ { "name"?: "...", "values": [数字, ...] } ] }，且 chart_type 为 bar | line | donut，run-spec 会用 Python+matplotlib 生成 PNG 并插入（需本机 pip install -r requirements-charts.txt）。chart_render: false 可关闭。无 Python 时仍保留文字要点。
二期图表：chart_engine: "com" 时优先 WPS 内嵌图（失败则视 chart_fallback_png 尝试 PNG）。远程图：imageUrl（HTTPS，建议根级 assetFetch.allowedHosts 白名单）；勿与 image 同页共用。安全约束见仓库 README「安全」节。
5. 演讲备注（notes）
每一页都要有 notes，建议包含：本页建议时长、与上一页的过渡语、可能被追问的问题及简短答法。语气口语化，适合口述。
6. 输出 JSON（WPS run-spec 专用）
必须符合 specs/ppt-spec.schema.json。与通用 LLM 示例的映射关系：
slides[].layout：使用title|title-content|content|chart|section|two-content|blank，以及叙事版式timeline|comparison|thesis-chain|argument|thesis-vertical|swot（空白版式 + 形状排版，减轻「每页都是标题+要点+配图」的单调感）。其中content/chart与title-content同款版式；chart页可在无要点时用chart_type+data_summary+insight自动生成要点行。- 叙事版式字段（与
twoColumns、chart_data互斥，校验会报错）：timeline：timeline: [{ "mark"|"year", "text"|"caption" }, …]（最多渲染 6 点）。comparison：comparison: { "leftHeader", "rightHeader", "rows": [{ "left", "right" }] }。thesis-chain：chain: [{ "label", "text" }, …]（至少 2 项，最多 4 卡）。argument：argument: { "thesis", "because": ["…"], "therefore" }（一页「总—因—收」）。thesis-vertical：thesisVertical: { "claim"|"thesis", "steps": [ 恰好 3 项{ "label"?, "text" }] }。swot：swot: { "strengths", "weaknesses", "opportunities", "threats" }（每项 string 或 string[]；至少一栏非空）；可选headers覆盖象限标题。
- 完整示例见 specs/narrative-layouts-demo.json。
- 列表字段：优先
bullets；也可用points（与 bullets 等价，二者不要同时塞两套不同内容）。 theme.font：可单独指定（如微软雅黑），会同时作用于标题与正文；需要区分时再写titleFont/bodyFont。theme.colors：仅作 设计参考（Agent/人工套主题）；当前 COM 链路 不会自动把 hex 刷进母版，需要配色时请用 WPS 主题或theme.themePath（.thmx）。
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 · 214 lines · 51 tokens per session scan A d1af78f136fa
drive-wps-ppt is a skill published in the GitHub repository thenw-123/CO-WPSppt (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 3,390 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 2026-08-31.
Other skills, from other repositories
cron-mastery
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
smart-messenger
Send rich messages to Feishu chats including text, images, cards, and scheduled messages. Use when the user asks to send a message, share an image, create a card/report, schedule a notification, or manage message templates. Integrates with screenshot-sender and vision-reader for multimedia messaging.
system-control
Control and monitor macOS system functions. Use when the user asks about system info (CPU, memory, disk, battery), app management (launch/quit apps, window list), notifications, clipboard operations, volume/brightness control, or any OS-level task on macOS.
feishu-doc-extended
An extended Feishu document assistant. Feishu is a workplace collaboration platform with online documents and tables; this skill can upload and place images and create tables after user confirmation.
cron-scheduler
A natural-language tool for managing OpenClaw scheduled tasks, which are jobs that run at set times or intervals. It can create, inspect, enable, disable, run, and audit those jobs.
Batch
Process multiple items with progress tracking, checkpointing, and failure recovery.