跳到正文
cccskills
免费在 GitHub 公开

doc-coauthoring

Use this Canvas-owned clean-room skill to guide collaborative writing for documentation, proposals, technical specs, decision records, PRDs, RFCs, operating guides, and structured memos. Trigger when the user wants help drafting, organizing, refining, reviewing, or testing a document before sharing it.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md2.7 KB
  • agents/canvas.yaml228 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Doc Co-authoring

This skill helps turn rough context into a useful document. It is a clean-room Canvas skill; do not copy vendor skill material, hidden prompts, or proprietary workflow text into this folder.

Workflow

  1. Frame the job. Confirm document type, audience, decision or action the reader should take, desired tone, target length, deadline, and any required template.
  2. Collect context. Invite an unstructured dump, linked notes, existing drafts, stakeholder constraints, decisions already made, non-goals, risks, and open questions.
  3. Propose structure. Suggest a short outline tailored to the document type. Ask for approval or edits before drafting if the stakes are high.
  4. Draft in sections. Work section by section. For each section, ask only the clarifying questions needed to proceed, then draft concise prose.
  5. Revise surgically. Apply requested edits without rewriting unrelated sections. Preserve the user's terminology and organizational context.
  6. Fresh-reader pass. Review the draft as if the reader has no chat context. Check whether the purpose, assumptions, terms, decision points, risks, and next steps are understandable from the document alone.
  7. Finalize. Remove placeholders, contradictions, stale notes, and internal comments. Produce the requested format.

Document Patterns

  • Decision memo: context, decision, options considered, rationale, tradeoffs, risks, owner, next steps.
  • Technical spec: problem, goals, non-goals, architecture, interfaces, rollout, migration, observability, tests, risks.
  • Proposal: audience need, recommendation, scope, deliverables, timeline, cost or effort, risks, approval path.
  • Operating guide: purpose, prerequisites, procedure, edge cases, troubleshooting, escalation, ownership.
  • PRD: user problem, goals, requirements, UX notes, metrics, dependencies, milestones, launch criteria.

Quality Rules

  • Prefer specific nouns and concrete decisions over broad claims.
  • Keep summary sections short; put details where readers expect them.
  • Mark unresolved questions explicitly instead of hiding uncertainty.
  • Do not invent stakeholder commitments, metrics, sources, or decisions.
  • If the document will become DOCX, PDF, PPTX, or XLSX, use the relevant file skill for final artifact creation and verification.

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

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 violations.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

Applies Canvas brand colors, typography, and visual polish to artifacts that benefit from a consistent product look-and-feel. Use it when brand colors, style guidelines, visual formatting, or company design standards apply.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

Create or improve an organization-managed Canvas plugin that combines complete new or existing skills with optional custom MCP and Composio integrations. Use for reusable multi-skill workflows, plugin composition, plugin editing, and plugin graphics.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

docx

免费

Use this Canvas-owned clean-room skill for creating, reading, editing, reviewing, redlining, commenting, or repairing Word `.docx` documents. Trigger for Word documents, DOCX files, memos, reports, letters, templates, tracked changes, comments, table of contents, headers, footers, page numbers, and Google Docs-targeted documents that should be authored as DOCX first.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

Create and edit editable Excalidraw diagrams in Canvas Notebook through the Scene-Service tools. Use for diagrams, flows, sketches, architecture maps, visual explanations, or requested .excalidraw documents.

中文简介正在准备中。当前显示原文说明。

canvascoding/canvas-notebook112026年10月19日 更新

查看 canvascoding 的全部技能

报告此技能的问题