Pinvou/pinvou-agent is an open-source desktop workspace where an AI agent helps with work, visual design, and software development. People use it to work with files and knowledge, create editable visual artifacts, connect coding agents to projects, and extend the workspace with tools, MCP servers, skills, and workflows; the catalogue skills add capabilities to that environment.
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 Pinvou/pinvou-agent --skill dwsgit clone --depth 1 https://github.com/Pinvou/pinvou-agentWrote 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/pinvou/pinvou-agent/dws)<a href="https://agentmods.dev/skills/pinvou/pinvou-agent/dws"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/dws.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00187 | $0.08865 |
| Opus 5 | $0.00093 | $0.04432 |
| Sonnet 5 | $0.00037 | $0.01773 |
| Haiku 4.5 | $0.00019 | $0.00886 |
Grade A, and why
dws scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 不要使用 dws 命令以外的方式操作(禁止 curl、HTTP API、浏览器)。**唯一例外**:aitable 导入/导出链路返回的预签名 `uploadUrl`/`downloadUrl`(`import upload` 申请的上传凭证、`export data` 返回的下载地址)允许用 curl 直传/直下(见 [aitable-export-import.md](./references/products/aitable/ How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
钉钉全产品 Skill
通过 dws 命令管理钉钉产品能力。
⚠️ 命令与 flag 以当前 dws 二进制为准:
dws <cmd> --help是 Cobra flags 事实源,Agent 选命令/参数约束/安全确认以 leaf Schema(--compact)为准,与本文档冲突时以二者为准。
严格禁止 (NEVER DO)
- 不要使用 dws 命令以外的方式操作(禁止 curl、HTTP API、浏览器)。唯一例外:aitable 导入/导出链路返回的预签名
uploadUrl/downloadUrl(import upload申请的上传凭证、export data返回的下载地址)允许用 curl 直传/直下(见 aitable-export-import.md);除此之外禁止 - 不要编造 UUID、ID 等标识符,必须从命令返回中提取
- 不要猜测字段名/参数值,操作前必须先查询确认
严格要求 (MUST DO)
- 所有命令必须加
--format json以获取可解析输出 - 危险操作必须先向用户确认,用户同意后才加
--yes执行 - 直接调用 dws 批量接口(如
record update)时单次批量不超过 30 条记录;使用 scripts/import_records.py 批量导入时按脚本默认 50 条/批(其DEFAULT_BATCH_SIZE=50,上限 100) - 所有命令必须严格遵循对应产品参考文档里面规定的参数格式(参数与参数值之间用空格隔开)
- 脚本只用于明确覆盖的复合任务:scripts/ 下的脚本可封装 AI 表格批量导入导出、钉盘目录树等流程;当公开
+Shortcut 已提供目标唯一解析、分页/部分失败 ledger 和确认语义时,优先 Shortcut。Chat 历史导出与机器人广播已完全下沉 Runtime,不再发布兼容脚本 - 脚本调用约定:统一用
python3调用(多数 macOS/Linux 环境没有裸python命令);文档中的scripts/...是相对本 Skill 根目录(SKILL.md所在目录)的路径,实际执行时应拼成完整路径(如python3 <Skill根目录>/scripts/attendance_report_monthly.py ...),不要假设当前工作目录(CWD)已在 Skill 根目录 - 实时个人事件例外:普通 IM 消息、reaction、已读和撤回默认走
dws event +listen-im ...;OA 审批、群生命周期、明确的原始 EventKey、Filter DSL、subscribe_id 或原始 envelope 使用dws event consume ... --flatten。不要写脚本轮询消息历史或审批列表
Shortcut 与原子命令的使用原则
shortcut 是对常用操作的高层封装,适合优先承担用户意图;产品参考文档和本 skill 负责判断意图、风险、跨产品流程和复杂参数,CLI 帮助负责声明当前版本真正可调用的命令。
- 先按产品参考、意图表和 recipe 路由。用户意图可由可见 Shortcut 满足时,优先使用
dws <service> +<verb> ... --format json,不要手写等价的多步原子命令。只有脚本明确补足 Shortcut 未覆盖的复合交付物且其安全/完整性契约仍适用时才选择脚本。 - 公开内建 shortcut 同时进入 Runtime Schema。用
dws schema --cli-path "<service> +<verb>" --compact --format json读取 Agent 选择、参数、跨参数约束和 risk/confirmation;只有参数映射、接口绑定或 provenance 审计才通过--jq精确读取 full leaf;dws shortcut list --service <service> --format json只作为轻量批量发现入口。 - 真正组装参数前用叶子帮助
dws <service> +<verb> --help核对当前 Cobra 接受的 flags。父级dws <service> --help只能发现子命令,不能替代叶子参数帮助。 - shortcut catalog 中
confirmation=user_required时,必须先获得用户确认,确认后才加--yes;not_required不额外确认。 - 如果 shortcut 不在 help / list 中,改用产品参考里的原子命令、脚本或标准流程;不要猜测未展示的
+命令。 - shortcut 失败时按“错误处理”流程先加
--verbose复查;若仍失败,应记录具体输入、输出、trace / endpoint / tool 信息。
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.
- LICENSE 9.9 KB
- NOTICE 666 B
- references/best_practices/_common/conventions.md 3.2 KB
- references/best_practices/_common/recipe-conventions.md 1.8 KB
- references/best_practices/01-messaging.md 3.2 KB
- references/best_practices/02-task.md 2.6 KB
- references/best_practices/03-meeting.md 12 KB
- references/best_practices/04-document.md 11 KB
- references/best_practices/05-reporting.md 6.0 KB
- references/best_practices/06-data-analytics.md 4.3 KB
- references/best_practices/07-minutes.md 6.9 KB
- references/best_practices/08-directory.md 7.8 KB
- references/best_practices/09-mail.md 5.2 KB
- references/best_practices/10-minutes-speaker-match.md 8.5 KB
- references/best_practices/11-minutes-speaker-correct.md 4.3 KB
- references/best_practices/lite-recipes.md 16 KB
- references/capability-limits.md 2.8 KB
- references/error-codes.md 4.0 KB
- references/field-rules.md 5.4 KB
- references/global-reference.md 4.0 KB
- references/intent-guide.md 45 KB
- references/products/agoal.md 8.1 KB
- references/products/aisearch.md 15 KB
- references/products/aitable-record-ops.md 4.3 KB
- references/products/aitable.md 23 KB
- references/products/aitable/aitable-advperm.md 10 KB
- references/products/aitable/aitable-attachment.md 2.0 KB
- references/products/aitable/aitable-best-practices.md 2.2 KB
- references/products/aitable/aitable-cell-value.md 7.9 KB
- references/products/aitable/aitable-dashboard-chart.md 4.0 KB
- references/products/aitable/aitable-data-analysis-sop.md 4.8 KB
- references/products/aitable/aitable-error-recovery.md 5.3 KB
- references/products/aitable/aitable-export-import.md 8.6 KB
- references/products/aitable/aitable-field-properties.md 7.6 KB
- references/products/aitable/aitable-field.md 6.6 KB
- references/products/aitable/aitable-filter-sort.md 3.7 KB
- references/products/aitable/aitable-form.md 7.2 KB
- references/products/aitable/aitable-formula-guide.md 7.0 KB
- references/products/aitable/aitable-primary-doc.md 2.3 KB
- references/products/aitable/aitable-record-create.md 1.6 KB
- references/products/aitable/aitable-record-delete.md 582 B
- references/products/aitable/aitable-record-history.md 4.0 KB
- references/products/aitable/aitable-record-name-key.md 2.4 KB
- references/products/aitable/aitable-record-query.md 3.2 KB
- references/products/aitable/aitable-record-share.md 1.6 KB
- references/products/aitable/aitable-record-update.md 1.7 KB
- references/products/aitable/aitable-record-upsert.md 3.3 KB
- references/products/aitable/aitable-view-config.md 10 KB
- references/products/aitable/aitable-view-extras.md 8.0 KB
- references/products/aitable/aitable-workflow.md 13 KB
- references/products/attendance-report.md 30 KB
- references/products/attendance-schedule.md 27 KB
- references/products/attendance-vacation.md 9.4 KB
- references/products/attendance.md 92 KB
- references/products/calendar.md 47 KB
- references/products/chat-emoji-list.md 8.4 KB
- references/products/chat.md 148 KB
- references/products/contact.md 29 KB
- references/products/dev.md 11 KB
- references/products/devdoc.md 1.8 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.
- 5d ago Changed · +1 lines cd0371dd04f7
- 8d ago First seen · 314 lines · 187 tokens per session scan A 3102390ff32f
dws is a skill published in the GitHub repository Pinvou/pinvou-agent (1,667 stars, last pushed today), licensed MIT. It adds 187 tokens to every session and 8,865 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
schedule
A skill for creating and managing scheduled tasks, including tasks that run automatically at regular times.
skill-creator
A skill for creating, editing, improving, and testing skills for coding agents.
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…