跳到正文
cccskills
免费在 GitHub 公开

doc

Create, inspect, and edit Word documents (`.docx`) with local code-execution tools. Use for document drafting, structured edits, tables, comments, and layout-sensitive Word deliverables.

中文简介正在准备中。当前显示原文说明。

集成工具Word
查看安装方法

包含的文件(6)

  • SKILL.md2.2 KB
  • agents/openai.yaml295 B
  • assets/doc-small.svg1.6 KB
  • assets/doc.png1.2 KB
  • LICENSE.txt10.5 KB
  • scripts/render_docx.py8.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Word documents

This is workflow guidance, not a callable tool. Use the shell or code-execution tool exposed by the active OIX harness. Do not look for a tool named doc.

Workflow

  1. Inspect the source before editing. Preserve its structure, styles, identifiers, and branding unless the user asks for a redesign.
  2. Use python-docx for creation and structured edits. For unsupported features such as tracked changes or complex comments, edit OOXML deliberately and keep the change narrowly scoped.
  3. Write one cohesive script for a substantial change instead of a chain of fragile one-line mutations.
  4. Save to a new file while iterating unless the user explicitly asked to replace the original.
  5. Verify content by reopening the saved document with python-docx and checking the requested text, tables, and section structure.
  6. When layout matters, render every page with scripts/render_docx.py or an available permissive office renderer, inspect the images, fix defects, and render again.
  7. If the file is open in Interpreter, call interpreter-app tools builtin-interpreter interpreter_refresh_file --json '{"path":"/absolute/path.docx"}' once after the final write.

Dependencies

Prefer uv and install only what the task needs:

uv pip install python-docx

Use an existing Python installation when available. If installation is blocked, ask for approval for the exact dependency command.

Quality bar

  • Use named styles and a consistent type, spacing, margin, and heading system.
  • Keep tables within page bounds; avoid clipped text, broken pagination, and accidental blank pages.
  • Preserve source identity and exact requested facts.
  • Keep scratch files outside the final deliverable folder.
  • Reopen the final .docx and inspect all rendered pages before delivery when rendering is available.

This skill is derived from an Apache-2.0 OpenAI document workflow and has been modified for OIX code execution and Workstation refresh behavior.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Build a period-end accrual schedule by computing each accrual, citing support, and drafting journal entries for controller approval. Use during month-end close; this drafts entries only and must not post them.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

audit-xls

免费

Audit a spreadsheet for formula accuracy, errors, and common financial-model mistakes. Use for selected ranges, single sheets, or whole-workbook model checks including balance-sheet balance, cash tie-out, roll-forwards, and logic sanity.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

Use this skill when the user needs advanced Playwright control of an already running browser session through Interpreter's app-managed browser bridge and the `builtin-js-repl` `js_repl` tool, after simple browser page work cannot be handled by the unified `builtin-interpreter` browser page tools.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

Drive a native desktop app through Interpreter's builtin-cua-driver. Use get_app_state, click/type/scroll/drag, and verify by calling get_app_state again when the user asks to operate a real desktop app, browser chrome, native dialog, menu, secure prompt, file chooser, or hidden/background window.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

Design or revise Interpreter UI for non-developers with an ultra-minimal, utilitarian style inspired by the OpenAI website and ChatGPT, not the developer platform. Use when simplifying settings, onboarding, chat, forms, empty states, or helper copy; when removing extra containers, labels, or visual noise; when replacing technical wording with plain language; when clarifying hierarchy and making the main user action obvious; when making every visible label and status understandable to an average HR admin or other non-technical user; when hiding implementation details such as logs, IDs, endpoints, paths, or protocol names; or when a screen must respect the app's existing CSS variables and light/dark theme behavior.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

Use for AI image, video, audio, or 3D generation/editing. Prefer configured media tools when present, estimate cost before running a paid model, and keep provider credentials in the user's environment or provider configuration.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-workstation282026年10月19日 更新

查看 openinterpreter 的全部技能

报告此技能的问题