跳到主要内容

minimax-pdf 标准

Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.

在 GitHub 打开

安装方式

cp -r skills/minimax-pdf ~/.claude/skills/minimax-pdf

把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同,Claude Code 默认是 ~/.claude/skills/

整仓一次性获取:git clone --depth 1 https://github.com/pengfeiqiao/kunpeng.git

依赖与权限

  • 无需 API Key
  • 无需联网
  • 依赖外部命令:node npm python python3 pip playwright npx go
  • 以上为按正文与 frontmatter 自动推断的信号,仅供参考;安装前建议先阅读原文。

SKILL.md 正文

来源 pengfeiqiao/kunpeng@bf8a8ac · 许可 MIT · 内容未修改

minimax-pdf

Three tasks. One skill.

Read design/design.md before any CREATE or REFORMAT work.


Route table

User intentRouteScripts used
Generate a new PDF from scratchCREATEpalette.py → cover.py → render_cover.js → render_body.py → merge.py
Fill / complete form fields in an existing PDFFILLfill_inspect.py → fill_write.py
Reformat / re-style an existing documentREFORMATreformat_parse.py → then full CREATE pipeline

Rule: when in doubt between CREATE and REFORMAT, ask whether the user has an existing document to start from. If yes → REFORMAT. If no → CREATE.


Route A: CREATE

Full pipeline — content → design tokens → cover → body → merged PDF.

bash scripts/make.sh run \
  --title "Q3 Strategy Review" --type proposal \
  --author "Strategy Team" --date "October 2025" \
  --accent "#2D5F8A" \
  --content content.json --out report.pdf

Doc types: report · proposal · resume · portfolio · academic · general · minimal · stripe · diagonal · frame · editorial · magazine · darkroom · terminal · poster

TypeCover patternVisual identity
reportfullbleedDark bg, dot grid, Playfair Display
proposalsplitLeft panel + right geometric, Syne
resumetypographicOversized first-word, DM Serif Display
portfolioatmosphericNear-black, radial glow, Fraunces
academictypographicLight bg, classical serif, EB Garamond
generalfullbleedDark slate, Outfit
minimalminimalWhite + single 8px accent bar, Cormorant Garamond
stripestripe3 bold horizontal color bands, Barlow Condensed
diagonaldiagonalSVG angled cut, dark/light halves, Montserrat
frameframeInset border, corner ornaments, Cormorant
editorialeditorialGhost letter, all-caps title, Bebas Neue
magazinemagazineWarm cream bg, centered stack, hero image, Playfair Display
darkroomdarkroomNavy bg, centered stack, grayscale image, Playfair Display
terminalterminalNear-black, grid lines, monospace, neon green
posterposterWhite bg, thick sidebar, oversized title, Barlow Condensed

Cover extras (inject into tokens via --abstract, --cover-image):

  • --abstract "text" — abstract text block on the cover (magazine/darkroom)
  • --cover-image "url" — hero image URL/path (magazine, darkroom, poster)

Color overrides — always choose these based on document content:

  • --accent "#HEX" — override the accent color; accent_lt is auto-derived by lightening toward white
  • --cover-bg "#HEX" — override the cover background color

Accent color selection guidance:

You have creative authority over the accent color. Pick it from the document's semantic context — title, industry, purpose, audience — not from generic "safe" choices. The accent appears on section rules, callout bars, table headers, and the cover: it carries the document's visual identity.

ContextSuggested accent range
Legal / compliance / financeDeep navy #1C3A5E, charcoal #2E3440, slate #3D4C5E
Healthcare / medicalTeal-green #2A6B5A, cool green #3A7D6A
Technology / engineeringSteel blue #2D5F8A, indigo #3D4F8A
Environmental / sustainabilityForest #2E5E3A, olive #4A5E2A
Creative / arts / cultureBurgundy #6B2A35, plum #5A2A6B, terracotta #8A3A2A
Academic / researchDeep teal #2A5A6B, library blue #2A4A6B
Corporate / neutralSlate #3D4A5A, graphite #444C56
Luxury / premiumWarm black #1A1208, deep bronze #4A3820

Rule: choose a color that a thoughtful designer would select for this specific document — not the type's default. Muted, desaturated tones work best; avoid vivid primaries. When in doubt, go darker and more neutral.

content.json block types:

BlockUsageKey fields
h1Section heading + accent ruletext
h2Subsection headingtext
h3Sub-subsection (bold)text
bodyJustified paragraph; supports <b> <i> markuptext
bulletUnordered list item (• prefix)text
numberedOrdered list item — counter auto-resets on non-numbered blockstext
calloutHighlighted insight box with accent left bartext
tableData table — accent header, alternating row tintsheaders, rows, col_widths?, caption?
imageEmbedded image scaled to column widthpath/src, caption?
figureImage with auto-numbered "Figure N:" captionpath/src, caption?
codeMonospace code block with accent left bordertext, language?
mathDisplay math — LaTeX syntax via matplotlib mathtexttext, label?, caption?
chartBar / line / pie chart rendered with matplotlibchart_type, labels, datasets, title?, x_label?, y_label?, caption?, figure?
flowchartProcess diagram with nodes + edges via matplotlibnodes, edges, caption?, figure?
bibliographyNumbered reference list with hanging indentitems [{id, text}], title?
dividerAccent-colored full-width rule—
captionSmall muted labeltext
pagebreakForce a new page—
spacerVertical whitespacept (default 12)

chart / flowchart schemas:

{"type":"chart","chart_type":"bar","labels":["Q1","Q2","Q3","Q4"],
 "datasets":[{"label":"Revenue","values":[120,145,132,178]}],"caption":"Q results"}

{"type":"flowchart",
 "nodes":[{"id":"s","label":"Start","shape":"oval"},
          {"id":"p","label":"Process","shape":"rect"},
          {"id":"d","label":"Valid?","shape":"diamond"},
          {"id":"e","label":"End","shape":"oval"}],
 "edges":[{"from":"s","to":"p"},{"from":"p","to":"d"},
          {"from":"d","to":"e","label":"Yes"},{"from":"d","to":"p","label":"No"}]}

{"type":"bibliography","items":[
  {"id":"1","text":"Author (Year). Title. Publisher."}]}

Route B: FILL

Fill form fields in an existing PDF without altering layout or design.

# Step 1: inspect
python3 scripts/fill_inspect.py --input form.pdf

# Step 2: fill
python3 scripts/fill_write.py --input form.pdf --out filled.pdf \
  --values '{"FirstName": "Jane", "Agree": "true", "Country": "US"}'
Field typeValue format
textAny string
checkbox"true" or "false"
dropdownMust match a choice value from inspect output
radioMust match a radio value (often starts with /)

Always run fill_inspect.py first to get exact field names.


Route C: REFORMAT

Parse an existing document → content.json → CREATE pipeline.

bash scripts/make.sh reformat \
  --input source.md --title "My Report" --type report --out output.pdf

Supported input formats: .md .txt .pdf .json


Environment

bash scripts/make.sh check   # verify all deps
bash scripts/make.sh fix     # auto-install missing deps
bash scripts/make.sh demo    # build a sample PDF
ToolUsed byInstall
Python 3.9+all .py scriptssystem
reportlabrender_body.pypip install reportlab
pypdffill, merge, reformatpip install pypdf
Node.js 18+render_cover.jssystem
playwright + Chromiumrender_cover.jsnpm install -g playwright && npx playwright install chromium

质量与来源

所属仓库
pengfeiqiao/kunpeng
仓库星标
99
最近更新
2 天前
采集时间
今天
commit
bf8a8ac8c6d3
内容指纹
sha256:8b0497ddd27da14
文件路径
skills/minimax-pdf/SKILL.md

同仓库其它 Skill

查看全部 49 个
anchor-frame-production
建立参考分工、锚定图变体、局部核验与版本记录,用于普通对话、画布和工坊的连续镜头创作。
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端
blender-clay-previz
用户提到白模/白膜/运镜预演/previs 时使用。调用本机 Blender 无界面渲染极简白模场景与运镜视频,用于验证构图遮挡、空间调度与动作时机,也可作为 AI 视频生成的全能参考。
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端
blender-modeling
在 Blender 中新建或修改可编辑模型、材质、灯光及场景工程。适用于产品建模、场景搭建、已有 blend 修改与渲染;纯白模运镜使用 blender-clay-previz。
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端
canvas-project-manager
画布能力由 canvas 工具契约提供,本文件仅保留操作顺序和数据安全约束。
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端
car-commercial-storyboard
汽车TVC、品牌片、汽车文案剧本、车辆资产与图片/视频提示词、分镜及Blender白模运镜。按人物叙事、生活观察、产品演示、造型光影等意图选择方法,维护车型身份与驾驶安全带连续性;不处理购车行情或维修问答。
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端
car-model-generation
专业的汽车3D模型图片生成技能,使用Gemini API生成高质量汽车展示图片,并通过豆包AI进行质量分析和优化。 使用场景:汽车品牌宣传片、车型展示、汽车广告素材生成。 关键词:汽车模型、车型图、汽车展示图、AI生图、Gemini
pengfeiqiao/kunpeng 99 原文
Codex CLIMCP 客户端

相似 Skill

更多「办公」
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
smart-search
基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时,尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时,务必使用此 skill
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
deeptutor-cli
终身个性化辅导系统:根据学习者情况持续调整教学方式。
精选 HKUDS/DeepTutor 4.1 万 仓库简介
Codex CLIMCP 客户端