Agent skill

Minimax PDF

by poco-ai in poco-ai/poco-claw

A skill your agent uses when visual quality and design identity matter for a PDF.

MITAuto-check passedDocuments & Office

Install Minimax PDF

skills CLI
$ npx skills add poco-ai/poco-claw --skill minimax-pdf -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install poco-ai/poco-claw minimax-pdf --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/poco-ai/poco-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/backend/assets/skills/minimax-pdf .claude/skills/minimax-pdf && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
minimax-pdf
GitHub stars
1.4k
Used in
6 other repos
Token cost
~2.1k tokens
SKILL.md length
709 words
Files
12 (incl. scripts)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when visual quality and design identity matter for a PDF.

  • Visual quality and design identity matter for a PDF
  • SKILL.md covers Read design/design.md before…, Route table, Route A: CREATE and Route B: FILL, plus 2 more sections
  • Runs Python, Shell and JavaScript scripts from its folder; calls bash, python3 and pip
  • Tasks that involve PDF

What it does

Minimax PDF is an agent skill from poco-ai/poco-claw. 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…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts (for example `README.md`, `design/design.md` and `scripts/cover.py`).

It sits in Documents & Office, covering PDF, Typography and Design systems. It works with MiniMax and Stripe. The repository describes itself as: A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the… The licence is MIT.

When your agent uses it

  • Visual quality and design identity matter for a PDF
  • Tasks that involve PDF
  • Tasks that involve Typography

Example prompts

  • “make a PDF”
  • “generate a report”
  • “write a proposal”
  • “/minimax-pdf”

Requirements

  • Python 3
  • Node.js
  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit f4055e6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (Python, Shell and JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • python3
    • pip
    • npm
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, npm and npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Minimax PDF loads about 2.1k tokens when it runs. Until then it costs about 217 tokens; SKILL.md has 709 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~217
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from poco-ai/poco-claw at commit f4055e6, republished under its MIT licence (© poco-ai). 709 words, ~2,138 tokens.

Download SKILL.mdSave it as .claude/skills/minimax-pdf/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
minimax-pdf
description
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.
license
MIT
metadata.version
1.0
metadata.category
document-generation

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
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.

Show full SKILL.md (275 more words)Show less

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:

json
{"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.

bash
# 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
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
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

© poco-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts) in backend/assets/skills/minimax-pdf of poco-ai/poco-claw.

  • SKILL.md
  • README.md
  • design/design.md
  • scripts/cover.py
  • scripts/fill_inspect.py
  • scripts/fill_write.py
  • scripts/make.sh
  • scripts/merge.py
  • scripts/palette.py
  • scripts/reformat_parse.py
  • scripts/render_body.py
  • scripts/render_cover.js

Open the folder on GitHubat commit f4055e6

Used in 6 other repositories

We found 6 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in poco-ai/poco-claw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Minimax PDF next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Minimax PDF compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minimax PDF this skillpoco-ai/poco-claw1.4k6 repos~2.1kAutomated safety check: PassMIT
Design Craftkipperacademy/skillpper149—~3.8kAutomated safety check: PassNone
Popular Web Designsyc-software/qm15k—~2.9kAutomated safety check: PassMIT
Popular Web DesignsTommy-yw/RunbookHermes5461 repos~2.4kAutomated safety check: PassMIT
Minimax PDFnexu-io/open-design100k—~296Automated safety check: PassApache-2.0
Transilience Report Styletransilienceai/communitytools563—~6.3kAutomated safety check: PassMIT

Similar skills

  • Design Craft

    kipperacademy/skillpper

    Opinionated product-design skill for building, reviewing, polishing, and iterating on landing pages, apps, dashboards, AI products, design systems, and brand touchpoints.

    149 GitHub stars~3.8k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Popular Web Designs

    yc-software/qm

    54 real-world design systems (Stripe, Linear, Vercel, Notion, Apple…) as ready-to-paste HTML/CSS — exact colors, typography, components, and spacing for styling a page after a known brand.

    15k GitHub stars~2.9k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Popular Web Designs

    Tommy-yw/RunbookHermes

    54 production-quality design systems extracted from real websites.

    546 GitHub starsUsed in 1 repo~2.4k tokens
    Frontend & DesignAuto-check passed
  • Minimax PDF

    nexu-io/open-design

    Generate, fill, and reformat PDFs with a token-based design system and 15 cover styles.

    100k GitHub stars~296 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Transilience Report Style

    transilienceai/communitytools

    Threat Intelligence Report Design System — ReportLab-based PDF generation for A4 reports with Transilience branding, typography, and layout standards.

    563 GitHub stars~6.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • Pro Report Builder

    thatrebeccarae/claude-marketing

    Create polished HTML technical reports and multi-page documents for consulting deliverables.

    161 GitHub stars~3.6k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed

More from poco-ai/poco-claw

  • Minimax DOCX

    poco-ai/poco-claw

    Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET).

    1.4k GitHub starsUsed in 7 repos~3.9k tokens
    Auto-check passed
  • Minimax XLSX

    poco-ai/poco-claw

    Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv).

    1.4k GitHub starsUsed in 6 repos~2.1k tokens
    Auto-check passed
  • PPTX Generator

    poco-ai/poco-claw

    Generate, edit, and read PowerPoint presentations. An agent skill from poco-ai/poco-claw.

    1.4k GitHub starsUsed in 4 repos~2k tokens
    Auto-check passed
  • MiniMax multimodal model skill — use MiniMax Multi-Modal models for speech, music, video, and image.

    1.4k GitHub stars~7.6k tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Minimax PDF

What does Minimax PDF do?

A skill your agent uses when visual quality and design identity matter for a PDF. Minimax PDF is an agent skill from poco-ai/poco-claw. Use this skill when visual quality and design identity matter for a PDF.

When should I use Minimax PDF?

Minimax PDF fits situations like: visual quality and design identity matter for a PDF; tasks that involve PDF; tasks that involve Typography.

How do I install Minimax PDF in Claude Code?

Run `npx skills add poco-ai/poco-claw --skill minimax-pdf -a claude-code`. Or copy the skill folder (backend/assets/skills/minimax-pdf in poco-ai/poco-claw) into .claude/skills/minimax-pdf in your project. Claude Code loads it when a task matches its description.

How do I install Minimax PDF in Codex?

Run `npx skills add poco-ai/poco-claw --skill minimax-pdf -a codex`. Or copy the skill folder (backend/assets/skills/minimax-pdf in poco-ai/poco-claw) into .agents/skills/minimax-pdf in your project. Codex loads it when a task matches its description.

Can I use Minimax PDF in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add poco-ai/poco-claw --skill minimax-pdf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minimax-pdf, .gemini/skills/minimax-pdf, .github/skills/minimax-pdf and .opencode/skills/minimax-pdf in your project.

What does Minimax PDF need to run?

Going by SKILL.md and its folder, Minimax PDF needs Python, a shell and JavaScript for the scripts in its folder and the command-line tools its instructions call (bash, python3, pip, npm and npx). Our summary lists: Python 3; Node.js; A Bash shell.

Does Minimax PDF access the network?

SKILL.md contains no URLs. Its commands use pip, npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Minimax PDF safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Minimax PDF use?

Minimax PDF is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Minimax PDF use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Minimax PDF?

Skills that share tags, products or a category with Minimax PDF: Design Craft (kipperacademy/skillpper, 149 stars), Popular Web Designs (yc-software/qm, 15k stars), Popular Web Designs (Tommy-yw/RunbookHermes, 546 stars) and Minimax PDF (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minimax PDF?

poco-ai (a GitHub organization) maintains it in poco-ai/poco-claw, which has 1,354 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 22, 2026.

Source: poco-ai/poco-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.