suzheng/k2f

k2f-aesthetic-ms-word

Create polished, general-purpose Microsoft Word documents with clear structure, typed content blocks, and strong visual hierarchy for any brief.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/suzheng/k2f --skill k2f-aesthetic-ms-word

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

K2F Aesthetic MS Word — AI-Native Aesthetic Design

Create a polished Microsoft Word document for any brief: clear structure, distinct blocks of content, and a strong visual hierarchy. The page stays elegant when the document is long or mixed—reports, letters, and handoffs that still look designed once they are open in Word. Headings, tables, and body text keep distinct roles instead of one default style. K2F handles layout and typography.

  • A Word file people can keep editing: hierarchy and type roles, not a plain file with default styles
  • Complex briefs that stay designed: sections, tables, and emphasis without looking like a stock template

Purpose

Teach agents to create highly aesthetic, general-purpose Word documents—any topic, any audience—that open and stay editable in Microsoft Word. Work through explicit copy, section-level reading beats, typographic roles, and art direction in content_and_design.md, then build with k2f—not slide-deck bullets, manual bold-and-spacing hacks, tab-aligned pseudo tables, or “design as one screenshot.”

Built on K2F

This skill produces Word-ready packages as .K2F documents exportable to DOCX. Follow the k2f skill for authoring: unpack or init a workspace, edit the semantic tree, run pack/verify, then export. K2F keeps agents on meaning (sections, figures, hierarchy roles)—not frame coordinates—while the engine compiles layout and typography into an editable Word handoff.

Before you build, install the core skill: npx skills add suzheng/k2f --skill k2f.

When to Use

  • The user wants a beautiful, professional Word document and did not name a narrower K2F task skill—or the brief is general.
  • Primary deliverable is polished, editable DOCX for Microsoft Word or SharePoint, regardless of domain.
  • Restructuring messy drafts or Markdown into a scannable Word hierarchy, then exporting through k2f.
  • Optional: combine with another K2F task skill—that skill owns domain facts and compliance; this skill owns Word reading mode, block roles, and aesthetic design.

Workflow

Step 1. Generate the contentanddesign.md

One content_and_design.md merging reader path, section roles, typed content blocks, and design intent the engine can interpret. Use labeled sections; map pages later in k2f.

Sub-steps

  1. Document scenario — Audience, purpose (inform, decide, approve, archive), reading mode (skim vs study), approximate length, need for cover, TOC, signature block, and what must stay verbatim (policy, legal, pricing, quotes). Drop sections that do not serve the scenario.
  1. Document skeleton — Ordered parts: cover or title block, front matter (TOC, distribution, summary), body chapters or sections, appendix or references, closing (sign-off, contact). Tag sections as opening, narrative, reference, or closing so density is not uniform start to finish.
  1. Content inventory — Per section, list blocks with stable ids and roles: title, subtitle/deck, body (approximate word budget), pull quote (+ attribution), callout or sidebar, figure (+ caption + credit), table (title + column semantics), list (ordered vs unordered intent), CTA or signature block. Mark must-run user copy vs agent-drafted placeholders the user must replace.
  1. Information architecture — One dominant idea per major section; support with secondary blocks, not competing headlines. Linear flow: hook → context → detail → decision or action. Keep callouts beside the paragraph they annotate; park wide reference tables in appendix intent. Prefer real table blocks over tab-aligned columns.
  1. Design intent — Tone (executive crisp, academic sober, friendly internal), typographic hierarchy (title vs deck vs body vs caption—relative, not points), density (airy openers vs tight reference sections), list rhythm (short bullets vs numbered procedures), accent (neutrals + one color for rules, labels, CTAs), contrast target (readable on screen and when printed).

Rules & constraints

  • Role discipline: each block has one role; do not fake hierarchy with bold alone.
  • Word budgets: cap body per section; move overflow forward or to appendix—never shrink type in the authoring plan.
  • Verbatim gate: policy, legal, pricing, and certification language only from user sources.
  • Word handoff: prefer editable text and discrete figures over describing “designed as one image.”
  • No coordinates: state section boundaries and roles, not x/y or point sizes.
  • Not forms or print spreads: interactive fields → k2f-fillable-pdf; magazine spreads and IDML → k2f-idml.

Common failure modes

  • Slide-deck pacing (title + bullets every section) → assign narrative roles and varied section types.
  • Arial soup (random bold and font names) → map emphasis to roles in design intent.
  • Tab pseudo tables → table inventory with column semantics.
  • Captions separated from figures → lock figure+caption pairs in the inventory.
  • Buried executive summary → place skimmer entry in opening section roles.
  • Uniform wall of body → alternate narrative, callout, and reference sections.
  • Invented compliance or pricing → flag gaps; never fabricate.
  • Flattened page screenshots → discrete text and image blocks for Word editing.

Quality checklist

  • [ ] Skeleton lists every major part; each body section has a section role assigned.
  • [ ] Every figure/table has caption, credit when needed, and paired placement intent.
  • [ ] Headlines are unique and ranked (one primary per major section).
  • [ ] Word budgets fit the stated length without cramming.
  • [ ] Verbatim copy is quoted or flagged; no silent invention of legal or pricing.
  • [ ] Design intent covers tone, type roles, density, lists/tables, and accent without coordinates.
  • [ ] Closing section delivers the scenario CTA (sign-off, next step, contact).

Step 2. Use the contentanddesign.md and k2f skill to generate a K2F file and export to an appropriate file format.

Follow k2f skill to instantiate sections from content_and_design.md, bind content roles from the inventory, verify, and export the DOCX deliverable for Microsoft Word.

from this repository

More skills

All skills
suzheng
Community

k2f-event-poster

Turn event briefs into wall- or screen-ready posters with headline zone, hero visual intent, and scannable logistics—not programs, slide decks, or handout flyers. Use when the user asks for an event poster, concert poster, festival promo, exhibition poster, meetup banner, or large-format promo. Create event posters with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent

1h installs
19
GitHub stars
5
Updated
Nov 7
suzheng
Community

k2f-cv

Compile a complete academic or senior professional curriculum vitae from notes, publication lists, and appointment history—with correct section order, honest bibliographic detail, and readable long-list hierarchy (not a one-page job resume). Use when the user asks for a CV, curriculum vitae, academic vita, faculty application CV, or multi-page career record. Create cvs with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2

1h installs
20
GitHub stars
5
Updated
Nov 7
suzheng
Community

k2f-sales-deck

Turn discovery notes, proposals, and product proof into buyer-ready sales decks with a prospect-centered story, one objective per meeting, and evidence-backed slides. Use when the user asks for a sales deck, demo presentation, proposal deck, executive briefing, or sales slides (not a fundraising pitch deck or generic company overview). Create sales decks with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them foc

1h installs
19
GitHub stars
5
Updated
Nov 7
suzheng
Community

k2f-exam-paper

Design formal exam papers—midterms, finals, unit tests, or take-home assessments—from a syllabus, rubric, past papers, or source readings, with weighted coverage, unambiguous calls for response, and intentional answer space. Use when the user asks for an exam paper, test, quiz, final, midterm, or printable assessment to distribute to students. Create exam papers with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets

1h installs
8
GitHub stars
5
Updated
Nov 7