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 l0s3r-Q/wps-skills --skill document-intelligencegit clone --depth 1 https://github.com/l0s3r-Q/wps-skillsWrote 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/l0s3r-q/wps-skills/document-intelligence)<a href="https://agentmods.dev/skills/l0s3r-q/wps-skills/document-intelligence"><img src="https://agentmods.dev/badge/skills/l0s3r-q/wps-skills/document-intelligence/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/l0s3r-q/wps-skills/document-intelligence"><img src="https://agentmods.dev/badge/skills/l0s3r-q/wps-skills/document-intelligence.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 | $0.00270 | $0.08667 |
| Opus 5.5 | $0.00108 | $0.03467 |
| Sonnet 5.5 | $0.00054 | $0.01733 |
| Haiku 4.5 | $0.00027 | $0.00867 |
Grade A, and why
document-intelligence 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
document-intelligence —— 文档智能写作代理
能力概述
输入用户自然语言 → 判定文档类型 → 决策结构策略 → 制定写作计划 → 调用 document-toolkit MCP 解析/生成 → 输出成品 .docx / .xlsx / .pdf / .pptx。
四层工作流：
- 意图识别：从用户描述中提取文档类型、主题、要求
- 类型判定：映射到 10 类规范 + 3 类格式（official/thesis/contract/bidding/general/legal/government_report/techdoc/resume/notice + excel/pdf/ppt）
- 结构决策：根据"是否有输入文件"和"是否要求改结构"选择策略
- 计划与执行：章节规划 → 内容要点 → 排版参数 → 生成 → 回读校验
一、意图识别规则
| 关键词 | 文档类型 | doc_type |
|---|---|---|
| 请示、批复、决定、意见、红头、发文、机关通知、政府令 | 党政公文 | official |
| 论文、学位论文、毕业论文、开题报告、学术论文、毕业设计 | 学位论文 | thesis |
| 合同、协议、合约、条款、甲乙双方、违约责任 | 合同协议 | contract |
| 招标、投标、招标公告、招标文件、投标文件、评标、中标 | 招投标文书 | bidding |
| 报告、方案、说明、总结、计划、邮件、说明书、通用文档 | 通用文档 | general |
| 会议纪要、周会纪要、会议记录、纪要 | 会议纪要 | meeting_minutes |
| 演讲稿、演讲、致辞、发言稿、讲话稿、汇报发言 | 演讲稿 | speech |
| 方案建议书、项目建议书、立项方案、建议方案、实施方案 | 方案建议书 | proposal |
| 邀请函、邀请信、请柬、参会邀请 | 邀请函 | invitation |
| 新闻稿、宣传稿、通讯稿、媒体报道 | 新闻稿 | news_release |
| 工作总结、年度总结、季度总结、述职总结 | 工作总结 | work_summary |
| 产品说明书、产品手册、使用说明书 | 产品说明书 | product_manual |
| 验收报告、项目验收、竣工验收 | 验收报告 | acceptance_report |
| 起诉状、答辩状、律师函、上诉状、法律文书、诉讼、仲裁申请 | 法律文书 | legal |
| 政府工作报告、政府汇报、人大报告、政府述职 | 政府工作报告 | government_report |
| 需求说明书、设计文档、操作手册、技术方案、接口文档、白皮书 | 技术文档 | techdoc |
| 简历、个人简介、求职、应聘 | 简历 | resume |
| 通知公告、放假通知、会议通知、活动通知、停水停电通知、放假公告、公司公告、社区公告 | 通知公告 | notice |
| Excel、表格、报表、数据表、花名册、Excel清单、数据清单、xlsx、统计表 | Excel 表格 | excel |
| PDF、导出PDF、转成PDF、转PDF、生成PDF | PDF 转换 | |
| PPT、演示文稿、幻灯片、汇报演示、路演、pptx、做PPT | PPT 演示 | ppt |
判定规则（按优先级）：
- 明确改写指令优先："改成X/按X格式/按X规范" → 以目标类型为准（如"把方案改成招标公告"→ bidding）
- 最长关键词优先：命中多个类型时，取匹配关键词最长的类型（如"会议通知"（4 字）优于"通知"（2 字）→ notice）
- 等长冲突时按表序（official > thesis > contract > bidding > legal > government_report > techdoc > resume > notice > excel > pdf > general）
- "通知/公告"语境规则：出现"公司/社区/单位内部/放假/活动"等非党政语境 → notice；出现"红头/发文/机关" → official
- "报告"默认归 general（工作总结报告），除非明确"政府工作报告"（→ government_report）或公文体裁词；"会议纪要/周会纪要/会议记录"归 meeting_minutes
- Excel/PDF/PPT 指令独立判定："做/生成/导出 XX 表格/报表/花名册" → excel；"转 PDF/导出 PDF" → pdf；"做 PPT/做演示/生成幻灯片" → ppt（与文档类型并行，且当动词为 做/生成/导出/转、宾语为表格/报表/PDF/演示类时优先于 doc_type 判定）
- 无法判定时默认 general。
What ships with it
12 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.
- examples/prompt-examples.md 3.3 KB
- README.md 1.4 KB
- templates/bidding.md 1.2 KB
- templates/contract.md 1.3 KB
- templates/general.md 733 B
- templates/government_report.md 853 B
- templates/legal.md 1.0 KB
- templates/notice.md 1.0 KB
- templates/official.md 1.1 KB
- templates/resume.md 1008 B
- templates/techdoc.md 1.3 KB
- templates/thesis.md 1.3 KB
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 · 422 lines · 270 tokens per session scan A b3680de0c1be
document-intelligence is a skill published in the GitHub repository l0s3r-Q/wps-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 270 tokens to every session and 8,667 once invoked, about $0.0011 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
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
surfsense-documents
Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.