tencent-docs

tencent-docs is a skill for Claude Code, Codex from chuancyzhang/deepseek-cowork. It costs 210 tokens per session (3,964 once invoked), scanned A, a copy of tencent-docs, Apache-2.0.

A skill for working with Tencent Docs, an online cloud document service at docs.qq.com. It covers documents, spreadsheets, presentations, mind maps, flowcharts and related files.

In plain words
What is it for?
Use it to create, read, search, edit, rename, move, copy, delete, import or export Tencent Docs files. It also manages knowledge-base spaces and folders, and can upload web pages or local files.
Why use it?
It removes the need to handle cloud documents manually when creating, finding, editing, organising or transferring content.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to create, read, search, edit, rename, move, copy, delete, import or export Tencent Docs files. It also manages knowledge-base spaces and folders, and can upload web pages or local files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chuancyzhang/deepseek-cowork/tencent-docs
Install

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.

Any agent
npx skills add chuancyzhang/deepseek-cowork --skill tencent-docs
Clone the repo
git clone --depth 1 https://github.com/chuancyzhang/deepseek-cowork

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tencent-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/tencent-docs/github.svg)](https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/tencent-docs)
Your own site
<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/tencent-docs"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/tencent-docs/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.

agentmods 80×15 button for tencent-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/tencent-docs"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/tencent-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00210 $0.03964
Opus 5.5 $0.00084 $0.01586
Sonnet 5.5 $0.00042 $0.00793
Haiku 4.5 $0.00021 $0.00396

Measured 1mo ago against content hash 260f05f71aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tencent-docs 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.

The scan reads SKILL.md. This mod also ships 5 executable files (aipage_pack.js, generate_slide.js, import_file.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

86% identical to tencent-docs — 54 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.

ai_skills/tencent-docs/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

腾讯文档 MCP 使用指南

腾讯文档 MCP 提供了一套完整的在线文档操作工具,支持创建、查询、编辑多种类型的在线文档。

支持的文档类型

类型 doc_type 推荐度 说明
文档 smartcanvas ⭐⭐⭐ 首选 排版美观,支持丰富组件;MDX 格式兼容全部 Markdown 语法
Excel sheet / tencentsheet ⭐⭐⭐ 数据表格专用
PPT slide / tencentslide ⭐⭐⭐ 幻灯片,演示文稿专用
思维导图 mind ⭐⭐⭐ 知识图谱专用
流程图 flowchart ⭐⭐⭐ 流程展示专用
Word doc / tencentdoc ⭐⭐ 传统格式,排版一般
收集表 form / tencentform ⭐⭐ 表单收集
智能表格 smartsheet ⭐⭐⭐ 高级结构化表格,支持多视图、字段管理
Html smartpage ⭐⭐⭐ html演示文稿专用

⚙️ 快速配置

首次安装使用时,需要先完成本地安装和注册,详见 references/auth.md。

🎯 场景路由表

根据任务场景,选择对应的参考文档:

场景 文档类型 参考文档
报告、笔记、文章、总结等 smartcanvas smartcanvas/entry.md(MDX 格式,兼容全部 Markdown 语法)
结构化数据管理 smartsheet references/smartsheet_references.md
计算、筛选、统计、Excel 操作 sheet sheet/entry.md(sheet.* 系列工具,已集成到 tencent-docs 中)
Word 文档编辑 word references/docengine_references.md(doc.* 系列工具,已集成到 tencent-docs 中))
论文、公文、合同等专业文档(作为docengine替补) word (doc) doc/entry.md
PPT / 演示文稿(AI 生成整份 PPT) slide references/slide_references.md
PPT / 幻灯片精细编辑(增删页 / 形状 / 文本 / 表格 / 图表 / 批注 / 动画 / 主题 / 备注等任何对已有 PPT 的修改) slide references/slideengine_references.md(slide_ 系列工具,必须通过独立的 slide-mcp 服务调用;禁止用 doc_ 或 tencent-docs 通用工具改 PPT)**
层次化知识整理 mind references/diagram_references.md
流程/架构展示 flowchart references/diagram_references.md
收集表 form references/manage_references.md(使用 manage.create_file,file_type=form;传入 space_id 可在空间内创建)
知识库空间管理(空间/节点/文件夹) — references/space_references.md
图片识别 / 图片转 Word / 图片转 Excel ocr.* references/ocr_references.md
获取文档内容、上传图片、网页剪藏等公共接口 — references/workflows.md (get_content/upload_image)
不支持能力上报(report_unsupported_feature) — references/unsupported_feature_reporting.md
文件管理(重命名/移动/删除/复制/导入导出/权限等) — references/manage_references.md
本地 HTML 一键上云(.aipage 打包+导入) aipage references/aipage_references.md
其他通用场景 smartcanvas smartcanvas/entry.md

Read the full file on GitHub · 184 lines

Files

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.

Changes

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.

  1. 1mo ago First seen · 184 lines · 210 tokens per session scan A 260f05f71aa3

Subscribe to this mod's changes

tencent-docs is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 210 tokens to every session and 3,964 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to tencent-docs, differing in 54 lines, and is treated as a copy.