suzheng/k2f

k2f-quotation

Create client-ready sales quotations from scope notes, line items, rates, and terms—structured so buyers can compare options, accept, or convert to an invoice without rework.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/suzheng/k2f --skill k2f-quotation

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

K2F Quotation — AI-Native Aesthetic Design

Purpose

Teach agents to blueprint commercial quotations before layout: a scannable offer story, reconciled pricing, explicit boundaries (what is in / out), and design intent that foregrounds value, total, and validity—without inventing rates, deliverables, or legal terms the user did not supply.

Built on K2F

This skill produces quotations as .K2F packages. 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 (parties, scope roles, option tiers, totals)—not pixel coordinates—while the engine compiles layout, typography, and theme into consistent output across PDF and other formats.

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

When to Use

  • Drafting a new quote from a brief, RFP excerpt, discovery notes, or a rate card.
  • Rebuilding a generic AI quote so scope, math, and validity read as one coherent offer.
  • Presenting good / better / best tiers or optional add-ons the user already defined.

Workflow

Step 1. Generate the contentanddesign.md

Single blueprint for semantic content and aesthetic intent. Use labeled blocks the k2f skill can map to regions later.

Sub-steps

  1. Quote type & decision frame — Fixed price, time-and-materials cap, milestone-based, or tiered packages. Note currency, locale formatting, tax treatment (inclusive/exclusive/unknown), and whether this is binding or indicative. Omit sections the type does not need (e.g., skip acceptance block on a rough ballpark).
  1. Party & identity — Seller and client names, addresses, contacts, logo intent. Registration or tax IDs only if user provided. Never fabricate signatures or authorized signatory names.
  1. Reference metadata — Quote number, issue date, valid-until date (or explicit validity rule). Project name, RFP/PO reference, version (v1, v2). One currency for the whole document; flag missing validity before layout.
  1. Offer narrative (assertion, then evidence) — One short block states what the client gets and why this price (outcome-oriented, not marketing fluff). Follow with evidence: line table, tier summary, or milestone list—not long prose that repeats table rows. If the user pasted client requirements, keep verbatim ask in a distinct subsection and map your priced response beside it; do not merge RFP text into line descriptions.
  1. Line-item architecture — Table-first. Per row: deliverable or SKU label, qty, unit, unit price, line total. Group sections (implementation, licensing, support) only when user data already splits that way. Optional add-ons and alternates as labeled blocks—not hidden footnotes. Discounts as explicit lines or documented percent rules.
  1. Totals story (write the math) — Subtotal → taxes/fees with labeled rates → quote total → optional “from” pricing when tiers exist. State rounding (per line vs document). If inputs conflict, mark NEEDS USER CONFIRMATION instead of guessing.
  1. Boundaries & terms — Inclusions, exclusions, assumptions, dependencies on client inputs. Payment or deposit milestones verbatim from user. Acceptance steps, change-order pointer, and warranty/support only if supplied. No invented liability caps or SLA numbers.
  1. Design intent — Tone, hierarchy, density, palette for the engine:
  • Tone: confident, precise B2B; persuasive through clarity, not hype.
  • Hierarchy: quote title + number in header; scope headline and quote total strongest; line table secondary; validity and exclusions visible without hunting.
  • Density: readable table rhythm; right-align money; tabular numerals; at most one short assumptions block on the main view.
  • Palette: restrained neutrals, one accent on total and primary CTA (e.g., “Accept by …”); WCAG AA; tier columns visually parallel for comparison.

Rules & constraints

  • Acceptance gate: no send-ready blueprint without quote number, dates, currency, reconciled total, and stated validity.
  • Separation gate: narrative, priced facts, and legal/assumption notes stay in distinct labeled sections—readers must not confuse interpretation with committed scope.
  • Traceability gate: every figure and deliverable ties to user input or a formula written in the doc; mark missing tax or FX explicitly.
  • Honesty gate: no fabricated upsells, cross-sells, or “this also covers …” unless the user said so.

Common failure modes

  • Paragraph pricing → rewrite as rows with qty, unit, and amount.
  • Buried total or missing valid-until → promote in metadata and design intent.
  • RFP prose pasted into line items → split verbatim ask vs priced response.
  • Tier options unequal or incomparable columns → align units, term length, and subtotals per tier.
  • Invented rates, VAT, or payment terms → strip; use TBD — user must supply.
  • Marketing superlatives with no scoped deliverable → replace with measurable inclusion lines.

Quality checklist

  • [ ] Parties and IDs match user-supplied data only.
  • [ ] Line math reconciles to subtotal and total under stated rounding.
  • [ ] Valid-until and version align with narrative (no stale dates).
  • [ ] Inclusions/exclusions do not contradict line items.
  • [ ] Design intent names emphasis for scope headline, total, validity, and table.
  • [ ] Optional tiers are comparable; primary recommendation is obvious if user named one.

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 the quotation from the blueprint, apply roles from design intent, verify, and export the client-ready deliverable.

관련 작업

같은 저장소의 Skills

더 많은 Skills

모든 Skills
suzheng
커뮤니티

k2f-menu

Turn venue notes, dish lists, and brand cues into a scannable food or beverage menu with clear categories, consistent item anatomy, and mood-matched visual intent—not a flyer, recipe book, or website sitemap. Use when the user asks for a restaurant menu, café menu, bar or wine list, catering sheet, room-service card, tasting menu, or seasonal insert for hospitality print or PDF. Create menus with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-

1시간 설치 수
48
GitHub Stars
3
업데이트
10월 30일
suzheng
커뮤니티

k2f-business-report

Create executive-ready business reports from KPIs, sales or operational data, and stakeholder notes—with prioritized findings, trend context, and actionable recommendations. Use when the user asks for a business report, performance analysis, business review, KPI dashboard narrative, weakness analysis, or strategic improvement report from business data. Create business reports with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI age

1시간 설치 수
48
GitHub Stars
3
업데이트
10월 30일
suzheng
커뮤니티

k2f-aesthetic-ms-word

Create polished, general-purpose Microsoft Word documents with clear structure, typed content blocks, and strong visual hierarchy for any brief. Use when the user asks for Microsoft Word, MS Word, a Word document, DOCX, .docx, a beautiful or professional Word doc, an editable Word handoff, or to beautify Word formatting. Create Microsoft Word documents 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

1시간 설치 수
43
GitHub Stars
3
업데이트
10월 30일
suzheng
커뮤니티

k2f

Create, design, edit, validate, and export elegant Word (docx), editable PDF, fillable AcroForm PDF, and Adobe InDesign (IDML) documents with K2F. Use when creating aesthetic Word, fillable PDF, AcroForm, IDML, or InDesign documents with AI agents, such as menus, certificates, planners, invitations, or worksheets and much more. K2F is a mature file format designed for AI agents to design and edit elegant aesthetic documents precisely and effortlessly. It has a rich ecosystem.

1시간 설치 수
36
GitHub Stars
3
업데이트
10월 30일