document-writer
Document generation skill for creating DOCX, PDF, PPTX, and other formatted documents. Guides structured content creation with proper formatting, headings, tables, and professional presentation.
Best use case
document-writer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Document generation skill for creating DOCX, PDF, PPTX, and other formatted documents. Guides structured content creation with proper formatting, headings, tables, and professional presentation.
Teams using document-writer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/document-writer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How document-writer Compares
| Feature / Agent | document-writer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Document generation skill for creating DOCX, PDF, PPTX, and other formatted documents. Guides structured content creation with proper formatting, headings, tables, and professional presentation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Document Writer Skill ## When to use this Skill Use this Skill when you are: - Creating a formatted document (DOCX, PDF, PPTX, XLSX) - Generating a report, proposal, or specification document - Converting markdown or structured data into a professional document format - Creating presentation slides from content ## Document Creation Process ### 1. Understand the Purpose - Identify the document type (report, proposal, specification, presentation) - Determine the target audience (technical, business, executive) - Note any formatting requirements or templates to follow ### 2. Structure the Content - Create a clear outline with logical section hierarchy - Use headings consistently (H1 for title, H2 for sections, H3 for subsections) - Organize information in order of importance or logical flow - Include a summary or executive overview for longer documents ### 3. Write the Content - Use clear, concise language appropriate for the audience - Support claims with data, examples, or references - Use bullet points and numbered lists for scannable content - Include tables for structured data comparisons - Add diagrams or charts where visual representation aids understanding ### 4. Format and Polish - Apply consistent styling throughout the document - Ensure headings, fonts, and spacing follow the template or convention - Add headers, footers, page numbers as needed - Include table of contents for documents longer than 5 pages - Review for grammar, spelling, and consistency ## Document Types ### Reports - Executive summary at the top - Findings organized by theme or chronology - Recommendations clearly separated from findings - Appendix for supporting data ### Presentations - One key message per slide - Minimal text — use visuals and bullet points - Speaker notes for detailed talking points - Consistent slide layout and branding ### Specifications - Clear scope statement - Detailed requirements with acceptance criteria - Diagrams for architecture or workflows - Glossary for domain-specific terms ## Things to Avoid - Walls of text without structure or headings - Inconsistent formatting within the same document - Mixing technical depth levels without clear audience targeting - Creating documents without understanding who will read them
Related Skills
qa-run
Run QA test suites against the local dev stack using Chrome DevTools and Playwright MCPs. Verifies environment, executes test flows, monitors for network errors, writes results, and creates Linear tickets for failures.
deploy-watch
Monitor GitHub Actions deploy workflows after merging a PR to staging. Polls until all deploys complete, diagnoses failures, and reports results.
tdd
Red-Green-Refactor test-driven development workflow. Guides the agent through writing failing tests first, then implementing code to pass them, then refactoring while keeping tests green.
linear-audit
Route audit findings to Linear as issues. Reads the most recent audit report from docs/audits/, parses findings at warning severity or above, and creates Linear issues in the project's configured team. Requires Linear MCP server to be available.
debugging
Structured debugging workflow: reproduce, isolate, trace, fix, verify. Use when investigating bugs, unexpected behavior, or test failures. Guides systematic root-cause analysis instead of trial-and-error.
code-reviewer
PR review, quality audit, and security checks. Invoke when reviewing code changes before merging or pushing. Performs structured review covering correctness, security, performance, and maintainability.
catholic
Apply reverent, faith-inspired Christian verbiage to non-code artifacts. Invoke when generating specs, plans, task lists, READMEs, or other documentation to infuse them with blessings, gratitude, and references to divine guidance. Never applies to source code or config files.
script_writer
专为“AI芝士派”定制的口播脚本创作助手。基于资深科技评论员视角，生成专业、犀利且接地气的科技/AI类短视频逐字稿。
documentation-research
Enforces documentation research before implementation. Auto-loads when implementing features to ensure current best practices are followed. Researches official docs first.
writer
Write content in Eric's voice — articles, blog posts, tweets, social media posts, marketing copy, newsletter drafts. Loads WRITING-STYLE.md and enforces kill phrases.
review-writer
将论文笔记和对比矩阵综合为结构化学术文献综述，含 BibTeX 引用
document-ocr
Convert scanned PDFs and document images into clean Markdown using docling for layout (figures, tables, reading order) plus a vision-language OCR model. Use when a user needs high-quality OCR of scanned documents, historical literature, or photographed pages — preserving multi-column reading order, diacritics, special characters, and figures. Supports local vLLM/Ollama servers and cloud vision APIs (OpenAI, Anthropic). Assumes an OCR backend already exists.