document-skills
Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the most specific document skill to reduce noise and improve routing precision.
pinned to #34429a8updated 2 weeks ago
Ask your AI client: “install skills/document-skills”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/document-skillsmetahub onboarded this repo on the author's behalf.
If you own github.com/foryourhealth111-pixel/Vibe-Skills on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
2,381
Last commit
2 weeks ago
Latest release
published
- #agent-framework
- #agent-skills
- #agentic-coding
- #ai-agents
- #ai-scientist
- #ai-skills
- #ai-workflow
- #automation
- #claude-code
- #codex
- #context-engineering
- #developer-tools
- #llm
- #multi-agent
- #prompt-engineering
- #skills
- #vibe-coding
- #vibecoding
- #workflow-automation
About this skill
Pulled from SKILL.md at publish time.
Use this skill when the task is clearly “document work” but the exact format is not yet fixed, or when the user mixes multiple formats (e.g., “把论文里的表格做成 Excel,再导出 PDF 报告”).
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.34429a8· 2 weeks ago
Kind-specific
31Skill: SKILL.md present
found at bundled/skills/document-skills/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
304 words · 1,853 chars · 3 sections
Skill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrent34429a8warn2 weeks ago
Contents
Use this skill when the task is clearly “document work” but the exact format is not yet fixed, or when the user mixes multiple formats (e.g., “把论文里的表格做成 Excel,再导出 PDF 报告”).
Goal: fast dispatch to the most specific skill so we keep high hit-rate / low noise.
Quick dispatch rules
- PDF (
.pdf, “PDF”, “pypdf”, “pdfplumber”, “render pages”)
- Prefer the pdf skill.
- Typical tasks: extract text/tables, render pages, review layout, generate PDF reports.
- Word / DOCX (
.docx, “Word”, “tracked changes”, “python-docx”)
- Prefer the docx skill (or doc when the task is explicitly
.docxformatting/layout heavy and the doc skill is requested/required by your environment).
- Excel / Spreadsheets (
.xlsx,.csv,.tsv, “Excel”, “openpyxl”, “pivot table”)
- Prefer the xlsx skill.
- If the task is more “tabular ETL + analysis” than “Excel formatting”, you can use spreadsheet instead (but keep output fidelity requirements in mind).
- Slides / Posters / PPTX (
.pptx, “slides”, “poster”, “deck”, “PowerPoint”)
- Prefer scientific-slides for scientific slide decks.
- Prefer pptx-posters for posters.
- Use infographics / markdown-mermaid-writing when the user wants diagrams rather than editable slides.
Safety / noise controls
- Do not guess formats. If the user didn’t specify a target file type, ask: “你最终需要交付的是 PDF / DOCX / XLSX / PPTX 哪一种?”
- If multiple outputs are requested, sequence them: source-of-truth document → derived exports (e.g., XLSX → charts → PPTX → PDF).
Output expectations
- Always preserve formatting when the user provides a template.
- For any generated file, clearly state: output path(s) and how to verify (open in Office/Preview, check page breaks, confirm no Excel formula errors, etc.).
Reviews
No reviews yet. Be the first.
Related
orchestration-patterns
>
migration-patterns
>
deployment-sop
>
mh install skills/document-skills