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 5.5 | $0.00020 | $0.01356 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 5mo ago), licensed MIT. It adds 51 tokens to every session and 3,390 once invoked, about $0.0002 per session on Opus 5.5. 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
resume-ssot
A career archive and job-application toolkit for maintaining a source-of-truth record and producing tailored resumes.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
grilling
A guided questioning process for testing a plan, decision, or idea. It maps dependent choices into a tree and asks only the questions that can be answered at each stage.
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.