Agent skill

iMandalArt Mandala Cards

by twhsi in twhsi/skills

Turns source material into a pure-text 3x3 iMandalArt 2.2 card with a five-character center and eight labeled surrounding angles, laid out with hard line breaks.

No licenceAuto-check passedKnowledge Management

Install iMandalArt Mandala Cards

skills CLI
$ npx skills add twhsi/skills --skill imandalart -a claude-code

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

GitHub CLI
$ gh skill install twhsi/skills imandalart --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/twhsi/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/imandalart .claude/skills/imandalart && 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
imandalart
GitHub stars
259
Token cost
~3k tokens
SKILL.md length
1,565 words
Files
10 (incl. scripts, references)
Skills in repo
18
Repo updated
First seen
Licence
None found

At a glance

Turns source material into a pure-text 3x3 iMandalArt 2.2 card with a five-character center and eight labeled surrounding angles, laid out with hard line breaks.

  • Works in 7 steps: Read the source material first. If the… → Identify the central thought and… → Orthogonally decompose the material into… → …
  • Compressing an article or note into one 3x3 index card of eight angles
  • SKILL.md covers Purpose, Default Deliverable, Three Kings 2.2 Integration and 2.2 Card Contract, plus 10 more sections
  • Runs Python scripts from its folder

What it does

The skill reads a source (a file, JSON, note, article or pasted text), compresses its central thought into one five-Han-character center line, and splits the material into eight orthogonal angles. Each angle gets a four-character title prefixed Ⓐ through Ⓗ and two five-character lines of content. The center axis shows ◎◎◎◎◎, the center line, then ◎◎◎◎◎ again, and the finished card is exactly 11 text lines.

Only the card is returned, not an essay, and it is explicitly not a Markdown table, a visible-border card, an HTML-only artifact or an 81-cell Mandala. In chat surfaces such as ChatGPT, Claude, Gemini, Codex or Discord it is wrapped in a fenced text block so line breaks and full-width spaces survive. For direct TheBrain insertion or clipboard use it is emitted raw.

The skill sits first in a three-step publishing chain that continues with BIRD 2.2 addresses and an A4 Booklet 2.2, and it keeps the の字型 positions so those later stages can reuse them. The folder includes a Python card script, a style reference and sample cards in JSON, HTML and PNG.

When your agent uses it

  • Compressing an article or note into one 3x3 index card of eight angles
  • Making a text card that pastes cleanly into TheBrain or a chat window
  • Requests that mention iMandalArt, の字型 or 井字號 ordering

Example prompts

  • “Make an iMandalArt card from the meeting notes in ./notes/q3-review.md.”
  • “Turn this article into a 3x3 Mandala index card with Ⓐ-Ⓗ angles.”
  • “Create an iMandalArt card for my reading goals, in の字型 order.”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read the source material first. If the user provides a file path, JSON, note, article, or pasted text, inspect the content before…
  2. Identify the central thought and compress it into one five-Han-character center line.
  3. Orthogonally decompose the material into eight surrounding angles. Avoid synonym-only repeats.
  4. Give each surrounding angle a four-Han-character title directly prefixed by Ⓐ through Ⓗ.
  5. Write two modern, plain-language five-Han-character lines for each surrounding cell.
  6. Render the center as ◎◎◎◎◎, one five-Han-character center line, then ◎◎◎◎◎.
  7. Render the final answer as the 11-line 3x3 card only.

What it can do on your machine

Read from SKILL.md and the folder at commit 287d0f4. 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 1 file in scripts/ (Python), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

iMandalArt Mandala Cards loads about 3k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 133 tokens; SKILL.md has 1,565 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.6k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,565 words (~3,003 tokens).

“Use this skill to turn any source material into one iMandalArt 2.2 pure-text 3x3 card.”

— opening of SKILL.md by twhsi
name
imandalart

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files (scripts, references) in skills/imandalart of twhsi/skills.

  • SKILL.md
  • agents/openai.yaml
  • references/imandalart-style.md
  • references/skill-card.json
  • sample-2016-goal.json
  • sample-cells.json
  • sample-hypercard.html
  • sample-hypercard.png
  • sample-paper.html
  • scripts/imandalart_card.py

Open the folder on GitHubat commit 287d0f4

Compare with similar skills

iMandalArt Mandala Cards 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.

iMandalArt Mandala Cards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
iMandalArt Mandala Cards this skilltwhsi/skills259—~3kAutomated safety check: PassNone
Bulletmindsickn33/agentic-awesome-skills47k1 repos~916Automated safety check: PassMIT
Whole-Book Explainer Noteslijigang/ljg-skills7.5k—~1kAutomated safety check: PassMIT
ljg-qa Question Chain Extractorlijigang/ljg-skills7.5k—~590Automated safety check: PassMIT
YouTube Transcript ReformatterPrismer-AI/PrismerCloud1.6k2 repos~905Automated safety check: PassMIT
Ray Obsidian Vault Setupimraywang/rayskills159—~625Automated safety check: PassCustom licence

Similar skills

  • Bulletmind

    sickn33/agentic-awesome-skills

    Convert input into clean, structured, hierarchical bullet points for summarization, note-taking, and structured thinking.

    47k GitHub starsUsed in 1 repo~916 tokens
    Knowledge ManagementAuto-check passed
  • Whole-Book Explainer Notes

    lijigang/ljg-skills

    Explains a whole book to someone who has not read it, keeping its specific content and showing how its threads connect, and saves the result as an Org note.

    7.5k GitHub stars~1k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Turns an article, paper or book into a directed chain of sharp questions and four-part answers that retraces the author's reasoning, saved as an org-mode note.

    7.5k GitHub stars~590 tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed
  • YouTube Transcript Reformatter

    Prismer-AI/PrismerCloud

    Fetches a YouTube transcript with a helper script and reshapes it into chapters, summaries, X threads, blog posts or timestamped quotes.

    1.6k GitHub starsUsed in 2 repos~905 tokens
    Knowledge ManagementAuto-check passed
  • Ray Obsidian Vault Setup

    imraywang/rayskills

    Sets up, audits or incrementally upgrades a local Obsidian vault for knowledge work and content production, without overwriting or moving existing notes.

    159 GitHub stars~625 tokensUpdated 18 days ago
    Knowledge ManagementAuto-check passed
  • Video Lens

    kar2phi/video-lens

    Fetch a YouTube transcript and generate an executive summary, key points, and timestamped topic list as a polished HTML report.

    113 GitHub stars~8.2k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check: notes

More from twhsi/skills

All 18 skills in this repo
  • Compiles notes, outlines, PDFs or BIRD and iMandalArt content into an eight-page mini book, with upright page PDFs, a reading PDF, an editable DOCX and an A4 landscape print sheet.

    259 GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Assigns and checks Luhmann-style codes for book manuscript notes and Obsidian card folders without renumbering existing notes.

    259 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Turns scheduling requests into Fantastical events or reminders on macOS, previewing the parsed item in the app first and adding it only when you confirm.

    259 GitHub stars~688 tokensUpdated 2 mo ago
    Auto-check passed
  • Applies a formal address protocol to manuscript text and TheBrain thoughts, assigning each a stable address, structured index, and verified links.

    259 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Todays Daily Plan

    twhsi/skills

    Write spoken daily planning notes into an Obsidian Mandala Grid day-plan Markdown file.

    259 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Converts an EPUB card book into an Obsidian folder with one Markdown file per card, keyword cards, navigation links and an optional shareable zip.

    259 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed

Questions about iMandalArt Mandala Cards

What does iMandalArt Mandala Cards do?

Turns source material into a pure-text 3x3 iMandalArt 2.2 card with a five-character center and eight labeled surrounding angles, laid out with hard line breaks. The skill reads a source (a file, JSON, note, article or pasted text), compresses its central thought into one five-Han-character center line, and splits the material into eight orthogonal angles. Each angle gets a four-character title prefixed Ⓐ through Ⓗ and two five-character lines of content.

When should I use iMandalArt Mandala Cards?

iMandalArt Mandala Cards fits situations like: compressing an article or note into one 3x3 index card of eight angles; making a text card that pastes cleanly into TheBrain or a chat window; requests that mention iMandalArt, の字型 or 井字號 ordering.

How do I install iMandalArt Mandala Cards in Claude Code?

Run `npx skills add twhsi/skills --skill imandalart -a claude-code`. Or copy the skill folder (skills/imandalart in twhsi/skills) into .claude/skills/imandalart in your project. Claude Code loads it when a task matches its description.

How do I install iMandalArt Mandala Cards in Codex?

Run `npx skills add twhsi/skills --skill imandalart -a codex`. Or copy the skill folder (skills/imandalart in twhsi/skills) into .agents/skills/imandalart in your project. Codex loads it when a task matches its description.

Can I use iMandalArt Mandala Cards 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 twhsi/skills --skill imandalart -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/imandalart, .gemini/skills/imandalart, .github/skills/imandalart and .opencode/skills/imandalart in your project.

What does iMandalArt Mandala Cards need to run?

Going by SKILL.md and its folder, iMandalArt Mandala Cards needs Python for the scripts in its folder.

Does iMandalArt Mandala Cards access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is iMandalArt Mandala Cards 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 iMandalArt Mandala Cards use?

No licence was found for iMandalArt Mandala Cards or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does iMandalArt Mandala Cards use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.6k tokens, read only when the agent opens those files.

What are the alternatives to iMandalArt Mandala Cards?

Skills that share tags, products or a category with iMandalArt Mandala Cards: Bulletmind (sickn33/agentic-awesome-skills, 47k stars), Whole-Book Explainer Notes (lijigang/ljg-skills, 7.5k stars), ljg-qa Question Chain Extractor (lijigang/ljg-skills, 7.5k stars) and YouTube Transcript Reformatter (Prismer-AI/PrismerCloud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains iMandalArt Mandala Cards?

twhsi (a GitHub user) maintains it in twhsi/skills, which has 259 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on July 21, 2026.

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