/a4-eight-page-booklet
Use A4 Eight Page Booklet 2.2 to create, write, repair, impose, and validate a printable A4 one-sheet eight-page mini book or zine from text, notes, images, BIRD Graph JSON, iMandalArt/九宮, FIRE, outlines, templates, or PDFs. Use whenever the user says A4八頁小書, 八頁小書, 八頁小冊, 八格小書,
$ npx -y skills add twhsi/skills --skill a4-eight-page-booklet --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/a4-eight-page-booklet
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use A4 Eight Page Booklet 2.2 to create, write, repair, impose, and validate a printable A4 one-sheet eight-page mini book or zine from text, notes, images, BIRD Graph JSON, iMandalArt/九宮, FIRE, outlines, templates, or PDFs. Use whenever the user says A4八頁小書, 八頁小書, 八頁小冊, 八格小書,
SKILL.md
a4-eight-page-booklet.SKILL.mdname: a4-eight-page-booklet
description: Use A4 Eight Page Booklet 2.2 to create, write, repair, impose, and validate a printable A4 one-sheet eight-page mini book or zine from text, notes, images, BIRD Graph JSON, iMandalArt/九宮, FIRE, outlines, templates, or PDFs. Use whenever the user says A4八頁小書, 八頁小書, 八頁小冊, 八格小書, A4一張八頁, 八頁在一頁, 8頁在一頁, 八張一頁, 一張紙變八頁, 摺頁書, 折頁小書, 迷你書, 小誌, zine, mini zine, booklet, 做成小書, 印成小書, 單張印出八頁, 幫我拼版, 八頁PDF, 合併八頁, 6-7-8-1/5-4-3-2排列, or asks for eight upright page PDFs, an eight-page reading PDF, an editable DOCX, or a correctly rotated A4 landscape print sheet.
A4 八頁 Eight Page Booklet 2.2
Compile source material into a reproducible paper thinking object. Version 2.2 is the Skill integration release; it keeps `BookletManifest 2.0` for backward compatibility, then renders every output from that manifest.
The 2.2 Skill remains in alpha while deterministic scripts are being implemented. Preserve the verified 1.x direct-PDF workflow as `legacy-direct`; do not claim script-backed validation when a named script is absent.
Three Kings 2.2 Integration
A4 Eight Page Booklet is the **paper publishing king** in the three-skill chain:
`iMandalArt 2.2 overview -> BIRD 2.2 seven Routes -> A4 Booklet 2.2 reading PDF + print sheet + DOCX`
- Put the iMandalArt center and overview on page 1 without changing its spatial identities.
- Put seven BIRD Routes on pages 2-8 and preserve source IDs, citations, addresses, and merge reasons.
- Deliver synchronized reading, printing, editing, preview, companion, and validation artifacts.
Output Contract
For a complete build, produce:
booklet-output/
├── booklet-manifest.json
├── companion.md
├── pages/page-01.pdf ... page-08.pdf
├── reading-8-pages.pdf
├── print-a4-landscape.pdf
├── editable-pages.docx
├── previews/contact-sheet.png
├── previews/print-imposition.png
└── validation-report.json
Keep all eight single-page PDFs upright. Generate the reading PDF in page order 1–8. Generate the A4 print sheet only after the single pages pass structural checks.
When the user requests a Japanese textbook listening booklet, all three learner-facing formats are mandatory:
1. `print-a4-landscape.pdf`: one A4 landscape sheet imposed for folding into eight pages. 2. `reading-8-pages.pdf`: eight upright pages in reading order for Voice Dream Reader. 3. `editable-pages.docx`: an editable eight-page Word file that opens cleanly in Apple Pages without blank pages.
Core Workflow
1. Inspect every supplied source before drafting. 2. Select one dominant content mode; combine modes only when the user or material requires it. 3. Normalize content into `BookletManifest 2.0`. Read [references/manifest-schema.md](references/manifest-schema.md) before creating or validating the manifest. 4. Preserve source IDs, BIRD addresses, verified deep links, citations, route references, and explicit ordering. 5. Draft eight page objects before rendering. Give each page one strong idea plus three to five short lines or one readable visual block. 6. Store long context, complete cards, citations, selection reasoning, and cross-route notes in `companion.md`. 7. Render eight upright single pages first. Use existing deterministic scripts when present; during alpha, use the PDF skill and preserve the manifest as the source of truth. 8. Merge pages 1–8 into the reading PDF. 9. Render a contact sheet, identify the visible booklet page number on every source page, then impose the A4 print sheet using the fixed physical map below. 10. Render previews and perform V1–V4 validation. Record results in `validation-report.json`; do not report a check as passed without current-run evidence.
Japanese Textbook Listening Mode
Use this mode for `みんなの日本語` and comparable lesson-based Japanese materials.
- Write every learner-facing page entirely in Japanese. Keep Chinese analysis, translations, and production notes in `companion.md`, not in the booklet.
- Use only genuine sentences found in the supplied lesson's sentence patterns, example sentences, dialogue, and Exercises A–J. Do not invent replacement examples when source sentences are available.
- Preserve question-answer pairs and dialogue turns as complete listening chunks. Mark their source section in the manifest.
- Page 1 must contain two iMandalArt nine-grids: a directory grid and a grammar/keyword index grid. Preserve the の字型 coordinates defined below.
- Pages 2–8 contain seven semantic learning Routes. Each page should have one short Japanese heading, one audible route cue, three to five authentic examples or dialogue turns, and one concise Japanese takeaway.
- Design for presbyopia: body text should normally be 16 pt or larger on upright A7 pages; headings 20–24 pt; avoid dense furigana and low-contrast gray. If the source cannot fit, reduce sentence count before reducing body text below 15 pt.
- Design for Voice Dream Reader: use true text, logical page order, simple punctuation, short headings, and one sentence or dialogue turn per paragraph. Do not use text rendered only as an image. Avoid decorative symbols that a speech engine will read aloud unnecessarily.
- Insert a short pause marker only when useful for shadowing. Prefer Japanese labels such as `聞きましょう`, `止めましょう`, and `声に出しましょう`; do not fill pages with repeated ellipses.
- The reading PDF and DOCX must follow the same page sequence and wording. The imposed print sheet may change placement and rotation only.
Source Types
Accept these source types:
- `text`: article, note, chapter, manuscript, reflection, or daily plan.
- `bird_graph`: Book, Route, Keyword, Context, Chunk, Node, and Edge data.
- `imandalart`: center plus eight cells, including standard and の字型 layouts.
- `fire`: Full-D, Index, Route, and Evolution notes.
- `outline`: Bike, Bonsai, Markdown, or another explicit hierarchy.
- `pdf_pages`: existing pages, templates, scans, or prior booklets.
- `mixed`: multiple source types with explicit source mapping.
Use only the
Read more
name: a4-eight-page-booklet description: Use A4 Eight Page Booklet 2.2 to create, write, repair, impose, and validate a printable A4 one-sheet eight-page mini book or zine from text, notes, images, BIRD Graph JSON, iMandalArt/九宮, FIRE, outlines, templates, or PDFs. Use whenever the user says A4八頁小書, 八頁小書, 八頁小冊, 八格小書, A4一張八頁, 八頁在一頁, 8頁在一頁, 八張一頁, 一張紙變八頁, 摺頁書, 折頁小書, 迷你書, 小誌, zine, mini zine, booklet, 做成小書, 印成小書, 單張印出八頁, 幫我拼版, 八頁PDF, 合併八頁, 6-7-8-1/5-4-3-2排列, or asks for eight upright page PDFs, an eight-page reading PDF, an editable DOCX, or a correctly rotated A4 landscape print sheet.
A4 八頁 Eight Page Booklet 2.2
Compile source material into a reproducible paper thinking object. Version 2.2 is the Skill integration release; it keeps `BookletManifest 2.0` for backward compatibility, then renders every output from that manifest.
The 2.2 Skill remains in alpha while deterministic scripts are being implemented. Preserve the verified 1.x direct-PDF workflow as `legacy-direct`; do not claim script-backed validation when a named script is absent.
Three Kings 2.2 Integration
A4 Eight Page Booklet is the **paper publishing king** in the three-skill chain:
`iMandalArt 2.2 overview -> BIRD 2.2 seven Routes -> A4 Booklet 2.2 reading PDF + print sheet + DOCX`
- Put the iMandalArt center and overview on page 1 without changing its spatial identities.
- Put seven BIRD Routes on pages 2-8 and preserve source IDs, citations, addresses, and merge reasons.
- Deliver synchronized reading, printing, editing, preview, companion, and validation artifacts.
Output Contract
For a complete build, produce:
booklet-output/ ├── booklet-manifest.json ├── companion.md ├── pages/page-01.pdf ... page-08.pdf ├── reading-8-pages.pdf ├── print-a4-landscape.pdf ├── editable-pages.docx ├── previews/contact-sheet.png ├── previews/print-imposition.png └── validation-report.json
Keep all eight single-page PDFs upright. Generate the reading PDF in page order 1–8. Generate the A4 print sheet only after the single pages pass structural checks.
When the user requests a Japanese textbook listening booklet, all three learner-facing formats are mandatory:
1. `print-a4-landscape.pdf`: one A4 landscape sheet imposed for folding into eight pages. 2. `reading-8-pages.pdf`: eight upright pages in reading order for Voice Dream Reader. 3. `editable-pages.docx`: an editable eight-page Word file that opens cleanly in Apple Pages without blank pages.
Core Workflow
1. Inspect every supplied source before drafting. 2. Select one dominant content mode; combine modes only when the user or material requires it. 3. Normalize content into `BookletManifest 2.0`. Read [references/manifest-schema.md](references/manifest-schema.md) before creating or validating the manifest. 4. Preserve source IDs, BIRD addresses, verified deep links, citations, route references, and explicit ordering. 5. Draft eight page objects before rendering. Give each page one strong idea plus three to five short lines or one readable visual block. 6. Store long context, complete cards, citations, selection reasoning, and cross-route notes in `companion.md`. 7. Render eight upright single pages first. Use existing deterministic scripts when present; during alpha, use the PDF skill and preserve the manifest as the source of truth. 8. Merge pages 1–8 into the reading PDF. 9. Render a contact sheet, identify the visible booklet page number on every source page, then impose the A4 print sheet using the fixed physical map below. 10. Render previews and perform V1–V4 validation. Record results in `validation-report.json`; do not report a check as passed without current-run evidence.
Japanese Textbook Listening Mode
Use this mode for `みんなの日本語` and comparable lesson-based Japanese materials.
- Write every learner-facing page entirely in Japanese. Keep Chinese analysis, translations, and production notes in `companion.md`, not in the booklet.
- Use only genuine sentences found in the supplied lesson's sentence patterns, example sentences, dialogue, and Exercises A–J. Do not invent replacement examples when source sentences are available.
- Preserve question-answer pairs and dialogue turns as complete listening chunks. Mark their source section in the manifest.
- Page 1 must contain two iMandalArt nine-grids: a directory grid and a grammar/keyword index grid. Preserve the の字型 coordinates defined below.
- Pages 2–8 contain seven semantic learning Routes. Each page should have one short Japanese heading, one audible route cue, three to five authentic examples or dialogue turns, and one concise Japanese takeaway.
- Design for presbyopia: body text should normally be 16 pt or larger on upright A7 pages; headings 20–24 pt; avoid dense furigana and low-contrast gray. If the source cannot fit, reduce sentence count before reducing body text below 15 pt.
- Design for Voice Dream Reader: use true text, logical page order, simple punctuation, short headings, and one sentence or dialogue turn per paragraph. Do not use text rendered only as an image. Avoid decorative symbols that a speech engine will read aloud unnecessarily.
- Insert a short pause marker only when useful for shadowing. Prefer Japanese labels such as `聞きましょう`, `止めましょう`, and `声に出しましょう`; do not fill pages with repeated ellipses.
- The reading PDF and DOCX must follow the same page sequence and wording. The imposed print sheet may change placement and rotation only.
Source Types
Accept these source types:
- `text`: article, note, chapter, manuscript, reflection, or daily plan.
- `bird_graph`: Book, Route, Keyword, Context, Chunk, Node, and Edge data.
- `imandalart`: center plus eight cells, including standard and の字型 layouts.
- `fire`: Full-D, Index, Route, and Evolution notes.
- `outline`: Bike, Bonsai, Markdown, or another explicit hierarchy.
- `pdf_pages`: existing pages, templates, scans, or prior booklets.
- `mixed`: multiple source types with explicit source mapping.
Use only the
Three Kings 2.2: compress with iMandalArt, address with BIRD, and publish with an A4 eight-page booklet. iMandalArt, FIRE semantic analysis, planning, and publishing workflows for Claude Code, Codex, and mainstream LLM agents.
Repo: twhsi/skills
Other skills on twhsi-skills.
- /auto-luhmann-numberer
Assign, validate, normalize, and explain Luhmann/Zettelkasten-style project-note codes for Chinese book manuscripts, Obsidian Markdown folders, Mandala-Grid section files, HyperCard Markdown stacks, and project-note JSON to EPUB workflows. Use when Codex needs to scan folders
Open skill - /concise-key-points
Compress answers to the highest practical information density with minimal wording while preserving essential meaning. Use when the user asks for 言簡意賅, 講重點, Concise, 精簡回答, 簡潔回答, 只講重點, 直接回答, brief, TL;DR, or otherwise requests a concise key-points response.
Open skill - /epub-hypercard-obsidian
Convert EPUB card books into Obsidian-ready HyperCard Markdown folders and portable zip files. Use when Codex needs to turn an EPUB with XHTML chapters, table-of-contents cards, keyword index cards, backlinks, Luhmann/Zettelkasten numbers, or cross-links into one Markdown file
Open skill - /fantastical-calendar
Create Fantastical calendar events and reminders from Codex on macOS. Use when the user asks Codex to add, schedule, parse, preview, or send a meeting, appointment, task, reminder, time block, daily plan item, 行事曆, 日曆, 會議, 待辦, or 提醒 into Fantastical.
Open skill - /fire-analysis-card
Analyze Chinese notes, articles, manuscripts, and digital card-box material with FIRE 2.0: Full-D numbering, Index keyword webs, Route thinking paths, and Evolution over time. Use when Codex needs to prepare material for semantic search, turn temporary notes into permanent or
Open skill - /fire-card-to-epub
Convert FIRE analysis cards, Chinese knowledge notes, or project-note JSON into validated EPUB books with directory cards, chapter cards, keyword index cards, backlinks, and GitHub-shareable ebook assets. Use when Codex needs to teach or automate the path from
Open skill

