Agent skill

Noteworthy

Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration.

MITAuto-check passedData & Analytics

Install Noteworthy

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a claude-code

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

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy --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/sihooleebd/noteworthy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/noteworthy .claude/skills/noteworthy && 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/

Paste into Claude Code

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .claude/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sihooleebd/noteworthy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/noteworthy .agents/skills/noteworthy && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .agents/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sihooleebd/noteworthy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/noteworthy .cursor/skills/noteworthy && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .cursor/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/sihooleebd/noteworthy.git --path .claude/skills/noteworthy

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sihooleebd/noteworthy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/noteworthy .gemini/skills/noteworthy && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .gemini/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/sihooleebd/noteworthy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/noteworthy .github/skills/noteworthy && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .github/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add sihooleebd/noteworthy --skill noteworthy -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install sihooleebd/noteworthy noteworthy --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sihooleebd/noteworthy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/noteworthy .opencode/skills/noteworthy && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "noteworthy" agent skill from https://github.com/sihooleebd/noteworthy/tree/master/.claude/skills/noteworthy into .opencode/skills/noteworthy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "noteworthy", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: noteworthy
GitHub stars: 120
Token cost: ~2k tokens
SKILL.md length: 807 words
Files: 5
Skills in repo: 1
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration.

Editing .typ files in a Noteworthy project
SKILL.md covers The room is the document; the…, Deploying templates and modules, Rendering a page to look at it and Blocks, plus 2 more sections
Calls git, rsync and curl
Drawing a figure with shape/graph/canvas

What it does

Noteworthy is an agent skill from sihooleebd/noteworthy. Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration. Use when editing .typ files in a Noteworthy project, drawing a figure with shape/graph/canvas, adding a block or cross-reference, changing templates/module, or deploying to a running Noteworthy server. Covers the one rule that is not guessable: a live document is a CRDT room and the file is only its export.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `reference/blocks.md`, `reference/geometry.md` and `reference/plotting.md`).

It sits in Data & Analytics, covering Data visualization. It works with Python and Model Context Protocol. The repository describes itself as: A powerful academic framework for typst. The licence is MIT.

When your agent uses it

Editing .typ files in a Noteworthy project
Drawing a figure with shape/graph/canvas
Cross-reference
Changing templates/module

Example prompts

“/noteworthy”

What it can do on your machine

Read from SKILL.md and the folder at commit c900d3a. 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
Shell commands in SKILL.md call:
- git
- rsync
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, rsync and curl, 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

Noteworthy loads about 2k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 807 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~127
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from sihooleebd/noteworthy at commit c900d3a, republished under its MIT licence (© sihooleebd). 807 words, ~2,008 tokens.

Download SKILL.mdSave it as .claude/skills/noteworthy/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: noteworthy
description: Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration. Use when editing .typ files in a Noteworthy project, drawing a figure with shape/graph/canvas, adding a block or cross-reference, changing templates/module, or deploying to a running Noteworthy server. Covers the one rule that is not guessable: a live document is a CRDT room and the file is only its export.

Noteworthy

A Typst framework for educational documents. templates/templater.typ re-exports everything; a content file imports that one path and nothing else.

config/     hierarchy.json, metadata.json, constants.json, schemes/
content/    <chapter>/<page>.typ          the document itself
templates/  templater.typ, core/, module/

Blocks, covers and layouts come in unqualified; everything else is a namespace: canvas, shape, graph, data, combi, dsa, timeline, trees.

typst

#import "../../templates/templater.typ": *

The room is the document; the file is its export

A Noteworthy server holds each open file as a Yjs CRDT room. While a room is live it is authoritative, and it rewrites the file within a debounce of every edit.

So writing the file behind a live room's back does not edit the document. The room's next save puts the old text back over what was written, and nobody connected ever sees the change. This is the single most expensive mistake to make here — it looks like it worked, and reverts a few seconds later.

Edit through the room instead. When the noteworthy MCP server is connected:

tool	for
`list_documents`	what exists, and which files someone has open right now
`read_document`	the live text when a room holds it, the file otherwise
`edit_document`	replace old→new; a delta through the room, so an open editor keeps its cursor, scroll and undo
`append_document`	add at the end, same way
`render_document`	render the book, a chapter or a page and hand back the pages as images (`format: "pdf"` also leaves the PDF on the server)
`check_document`	compile the book and return typst's diagnostics

edit_document refuses an old_string that appears zero times, or more than once without replace_all — same rule whether it goes through a room or to a file nobody has open.

Without the MCP server, editing files directly is only safe when no server is running against that project.

Deploying templates and modules

templates/ is not a document, so it is deployed rather than edited through a room. templates/module is a git submodule (noteworthy-modules).

bash

# commit in the submodule, then bump the pin in the parent repo
cd templates/module && git commit && git push
cd ../..        && git commit -am "Bump modules: ..." && git push

# --delay-updates: every file is staged and renamed at the end, so the project
# never sits half-updated.  Without it a watching tinymist compiles a tree where
# one file has landed and another has not, and reports unresolved imports.
rsync -a --delay-updates --exclude='.git' templates/module/ host:project/templates/module/

# reconcile ONLY the paths deployed.  An empty body means *every* live room,
# which reloads documents nobody asked you to touch.
curl -X POST http://host:8010/api/rooms/reload -H 'Content-Type: application/json' \
  -d '{"paths": ["templates/module/canvas/space.typ"]}'

Rendering a page to look at it

render_document is the short way, and it takes names: "8/2", "content/8/2.typ", "8" for a chapter, nothing for the book. Without the MCP server, compile through the parser yourself -- and either way look at the image before saying a figure works.

bash

typst compile templates/core/parser.typ out-{n}.png --root . --ppi 110 \
  --input 'chapter-folders=["8", "9"]' \
  --input 'page-folders={"8": ["1", "2"], "9": ["1"]}' \
  --input target=0/1        # index into chapter-folders / page-folders, not names

A red `?label` in a partial render is correct

A compile of one page or one chapter has no cross-page label map, so any @label whose target lives on another page renders as a red ?label.

This is intended and is not something to fix. Do not rewrite the reference, add the label locally, or report it as broken: it resolves in a full build, where the first pass has collected every label in the book. Render the whole book (render_document with no target) if you need to see it resolved.

Blocks

definition, theorem, example, note, notation, analysis, equation, solution, proof. Signature: #block-kind(title, number, label: "name")[body].

typst

#definition("Truncated Cone", label: "tcone")[ ... ]     // auto-numbered
#note("Why", auto, label: "why")[ ... ]                  // auto is the number slot
@tcone                                                    // renders "Definition 8.2.1"

Blocks nest, and a solution counts within the block containing it. A reference is drawn in that block kind's scheme colour.

Show full SKILL.md (330 more words)Show less

Figures

Canvases take objects as positional arguments; arrays of objects are fine.

typst

canvas.cartesian-canvas(size: (6, 4), x-domain: (0, 6), y-domain: (-3, 3), ..objects)
canvas.polar-canvas / trig-canvas / graph-canvas / blank-canvas   // blank: no axes
canvas.space-canvas(x-domain:, y-domain:, z-domain:, size:, elevation:, azimuth:,
                    projection: "orthographic" | "perspective", axis-dir: (y: -1))

module	what is in it	detail
unqualified	blocks, covers, layout, `@ref`	`reference/blocks.md`
`shape`	points, lines, circles, arcs, polygons, angles, braces, text, constructions, intersections	`reference/geometry.md`
`graph`	functions, parametric and polar curves, surfaces, vectors, tangents, Riemann sums	`reference/plotting.md`
`data`	series, CSV, tables, smooth curves	`reference/plotting.md`
`canvas`	the six canvases and the 3D camera	`reference/plotting.md`
`combi` `trees` `dsa` `timeline`	permutations, trees, arrays/stacks/graphs/grids, timelines	`reference/structures.md`

Read the reference file for the module you are using: the signatures there are taken from templates/module, which is ahead of the feature document in content/.

The 2D/3D rule

Every point-built shape takes (x, y) or (x, y, z). In a space canvas a two-component point lies on the ground plane and a three-component one is in space — so a parametric function is 3D exactly when it returns three numbers.

typst

shape.circle((0, 0, 1.5), radius: 1)                      // a ring at height 1.5
graph.parametric(t => (calc.cos(t), calc.sin(t), t / 2))  // a helix
graph.parametric(x => (x, 0, f(x)), domain: (a, b))       // a profile in the xz-plane

A circle is always flat on the ground plane. A ring perpendicular to an axis is a polyline or a parametric curve, not a circle.

Styling

style: (stroke: (dash: "dashed")) keeps the theme's paint and thickness — naming one part of a stroke keeps the rest. A bare colour (stroke: red) replaces outright.

A surface with a translucent colour is not stroked: stroking a facet in its own translucent fill doubles the alpha along every shared edge and the mesh shows up as a grid of lines. Opaque surfaces are stroked, to close antialiasing seams.

brace takes angle: — a direction on the page (0deg right, 90deg up) — and goes to whichever of its two sides points that way, measured after projection. Through a camera that is the only way to say which side you meant.

Checks worth making

Render and look at it. Overlapping labels and a figure that silently drew nothing both survive a clean compile.
An unknown named argument to a canvas is silently ignored, not an error (space-canvas panics on them; the flat ones do not).
check_document, or a compile, before leaving an edit behind.

Files

SKILL.md and 4 other files in .claude/skills/noteworthy of sihooleebd/noteworthy.

SKILL.md
reference/blocks.md
reference/geometry.md
reference/plotting.md
reference/structures.md

Open the folder on GitHubat commit c900d3a

Compare with similar skills

Noteworthy 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.

Noteworthy compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Noteworthy this skillsihooleebd/noteworthy	120	—	~2k	Automated safety check: Pass	MIT	10 days ago
Save Research Notebooknapjon/krisk	117	—	~702	Automated safety check: Pass	BSD-3-Clause	8 days ago
Replnteract/nteract	179	—	~1.4k	Automated safety check: Pass	BSD-3-Clause	today
Scientific Figure MakingChenLiu-1996/figures4papers	8.3k	—	~557	Automated safety check: Pass	Custom licence	3 days ago
Plot From ImageTrae1ounG/paper-plot-skills	869	1 repos	~868	Automated safety check: Pass	None	5 mo ago
Retentioneering Contributingretentioneering/retentioneering-tools	925	—	~1.8k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Save Research Notebook
napjon/krisk
Convert a completed data-analysis conversation into evidence-backed, reproducible living research through the Krisk MCP server.
117 GitHub stars~702 tokensUpdated 8 days ago
Data & AnalyticsAuto-check passed
Repl
nteract/nteract
Use nteract notebooks as a persistent Python REPL. An agent skill from nteract/nteract.
179 GitHub stars~1.4k tokensUpdated today
Data & AnalyticsAuto-check passed
Scientific Figure Making
ChenLiu-1996/figures4papers
Covers publication-ready matplotlib figures for academic papers, slides, and reports—bars, trends, scatter, heatmaps, and multi-panel layouts—with this…
8.3k GitHub stars~557 tokensUpdated 3 days ago
Data & AnalyticsAuto-check passed
Plot From Image
Trae1ounG/paper-plot-skills
Reproduce any academic paper figure from an uploaded image using accumulated style experience.
869 GitHub starsUsed in 1 repo~868 tokens
Data & AnalyticsAuto-check passed
Retentioneering Contributing
retentioneering/retentioneering-tools
Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal…
925 GitHub stars~1.8k tokensUpdated 2 days ago
Data & AnalyticsAuto-check passed
Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
113 GitHub starsUsed in 2 repos~1.5k tokens
Data & AnalyticsAuto-check passed

Works with

Questions about Noteworthy

What does Noteworthy do?

Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration. Noteworthy is an agent skill from sihooleebd/noteworthy. Write and edit Noteworthy documents — a Typst framework for textbooks, with blocks (definition/theorem/example/solution), 2D and 3D canvases, geometry, plotting, and live Yjs collaboration.

When should I use Noteworthy?

Noteworthy fits situations like: editing .typ files in a Noteworthy project; drawing a figure with shape/graph/canvas; cross-reference; changing templates/module.

How do I install Noteworthy in Claude Code?

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

How do I install Noteworthy in Codex?

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

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

What does Noteworthy need to run?

Going by SKILL.md and its folder, Noteworthy needs the command-line tools its instructions call (git, rsync and curl).

Does Noteworthy access the network?

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

Is Noteworthy 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. Review the folder before installing.

What licence does Noteworthy use?

Noteworthy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Noteworthy use?

About 2k tokens (SKILL.md is roughly 8k 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 Noteworthy?

Skills that share tags, products or a category with Noteworthy: Save Research Notebook (napjon/krisk, 117 stars), Repl (nteract/nteract, 179 stars), Scientific Figure Making (ChenLiu-1996/figures4papers, 8.3k stars) and Plot From Image (Trae1ounG/paper-plot-skills, 869 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Noteworthy?

sihooleebd (a GitHub user) maintains it in sihooleebd/noteworthy, which has 120 GitHub stars. The repository was last updated on September 29, 2026.

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

Install Noteworthy

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Noteworthy

The room is the document; the file is its export

Deploying templates and modules

Rendering a page to look at it

A red ?label in a partial render is correct

Blocks

Figures

The 2D/3D rule

Styling

Checks worth making

Files

Compare with similar skills

Similar skills

Save Research Notebook

Repl

Scientific Figure Making

Plot From Image

Retentioneering Contributing

Python Executor

Related

Questions about Noteworthy

A red `?label` in a partial render is correct