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 huaweicloud/huaweicloud-skills --skill huawei-cloud-clouddocs-aipagegit clone --depth 1 https://github.com/huaweicloud/huaweicloud-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/huaweicloud/huaweicloud-skills/huawei-cloud-clouddocs-aipage)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-clouddocs-aipage"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-clouddocs-aipage/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/huaweicloud/huaweicloud-skills/huawei-cloud-clouddocs-aipage"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-clouddocs-aipage.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 | $0.00174 | $0.03549 |
| Opus 5.5 | $0.00070 | $0.01420 |
| Sonnet 5.5 | $0.00035 | $0.00710 |
| Haiku 4.5 | $0.00017 | $0.00355 |
Grade A, and why
huawei-cloud-clouddocs-aipage 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 yesterday.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
huawei-cloud-clouddocs-aipage — 基于内容创建在线 page 文档（最基础版）
从 slide 技能裁剪出的最小 page 技能：用户给内容 → 模型生成 markdown → page +create 一次创建 → 交付链接 → file +export 导出本地 docx。只保留全新创建链路、导出收尾与幂等断点，不包含单块编辑、模板、批量等能力。
核心设计：生成 markdown → 一次创建 → 导出 docx ★
全程一条主链路，无分阶段渲染：
- 生成：模型根据用户原始需求构造 markdown，写入
<项目工作目录>/drafts/page.md（内容规范见references/page-content.md）。 - 创建：
create_page.py读 markdown，经clouddocs-cli page +create --title <t> --content <c> [--format 1]一次创建在线 page 文档，落created_doc.json锚点，回吐doc_id+doc_url。 - 交付：把
doc_url（{base}/wapp/doc/<docId>）交给用户。 - 导出：
clouddocs-cli file +export --document_id <doc_id> --export_type word把在线文档导出为 docx 存到本地交付目录（创建后先等 10 秒，失败隔 10 秒重试一次，仍失败则放弃导出只交付链接）。
organization_id / wiki_id 由 CLI 自动解析（个人空间 + 默认文档库），脚本无需前置 space +fetch / docbase +fetch；可选 --parent-document-id 建到指定父文档（如 AI 创作文档）。幂等是关键护栏：created_doc.json 已在则重跑只回吐、绝不重复建文档。
草稿目录约定（drafts 一律建在项目工作目录）★
- drafts 目录（
page.md/created_doc.json/page.kpge等中间产物）一律建在当前用户项目工作目录（会话 cwd / 调用方工作目录）下：<项目工作目录>/drafts/。 - 禁止写入技能安装目录（
~/.cac/skills/<技能名>/）或技能源码目录（<skills 源码仓库>/.../skills/<技能名>/）——技能目录是只读的规范与脚本，不属于任何一次具体运行。 - 步骤 1 由模型用 Write 建
<项目工作目录>/drafts/page.md（Write 自动创建目录）；脚本默认--drafts-dir drafts，在项目工作目录运行即解析到<项目工作目录>/drafts/。 created_doc.json（幂等锚点）与page.kpge随 drafts 一起落在项目工作目录，随会话交付物留存，可跨会话断点恢复。
用户交互铁律
向用户只输出："正在生成文档内容..."（可选）/ "文档已创建：<链接>" / "本地Word：<本地路径>"（收尾）/ 简洁错误说明（导出失败时：「文档已创建：<链接>，本地 Word 导出失败」）。其余一律静默——技能名 / 脚本名 / 文件路径 / doc_id / 接口返回原文等内部状态全部不许出现。收尾只报本地文件路径，不附加文章内容概述/章节总结。
前置检查
- CLI 已安装：
command -v clouddocs-cli（Windows cmd/PowerShell 用where clouddocs-cli/Get-Command clouddocs-cli）能定位到可执行文件；找不到则先按<技能基目录>/bin/cli-installation-guide.md安装子技能完成安装（仅支持 Windows，执行bin/windows/install-windows.ps1，详见该子技能），装完再继续。 - 认证：
clouddocs-cli auth status显示ready；否则用「两步走」设备授权（禁止直接运行阻塞式clouddocs-cli auth login——它打印 URL 后挂起轮询等待授权，命令不退出，被管道捕获时 URL 也不输出，会卡死）：clouddocs-cli auth login --no-wait --json→ 立即返回 JSON，取verification_url和device_code；- 自动打开授权页（Windows）：
powershell.exe -NoProfile -Command "Start-Process '<verification_url>'"（实测可靠弹出浏览器；若环境仍无法打开，把 URL 念给用户手动打开）； - 后台续接自动感知授权：发起授权后立即在后台运行
clouddocs-cli auth login --device-code <device_code>（该命令自带轮询，默认最多 240s）——用户授权成功那一刻后台任务自动完成登录并保存凭证，无需等用户通知；后台任务未结束期间把 URL 交给用户点授权。
- 服务地址：
clouddocs-cli config init --host <url>，或~/.clouddocs/config.json已配置base_url。 - 排查用：在项目工作目录运行
python3 <技能基目录>/scripts/create_page.py --probe-auth（只看 base/鉴权，不发网络）。
What ships with it
9 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.
- bin/cli-installation-guide.md 5.5 KB
- bin/windows/clouddocs-cli-0.5.7-m3prod-windows-amd64.zip 3167 KB
- bin/windows/install-windows.ps1 8.9 KB runs code
- bin/windows/SHA256SUMS 111 B
- references/iam-policies.md 2.6 KB
- references/page-content.md 3.5 KB
- references/verification.md 2.3 KB
- scripts/_hws_cli.py 8.7 KB runs code
- scripts/create_page.py 9.5 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.
- yesterday First seen · 147 lines · 174 tokens per session scan A 7e749b5e93cc
huawei-cloud-clouddocs-aipage is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 174 tokens to every session and 3,549 once invoked, about $0.0007 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 2026-10-27.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
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.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.