Agent skill

Pinepaper

by madhvantyagi in madhvantyagi/Gnos

Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity.

MITAuto-check passedDevelopment

Install Pinepaper

skills CLI
$ npx skills add madhvantyagi/Gnos --skill pinepaper -a claude-code

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

GitHub CLI
$ gh skill install madhvantyagi/Gnos pinepaper --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/madhvantyagi/Gnos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pinepaper .claude/skills/pinepaper && 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
pinepaper
GitHub stars
336
Token cost
~1k tokens
SKILL.md length
532 words
Files
5 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity.

  • Works in 6 steps: Write a short scene brief: claim,… → Read the current tool schema. Use… → Call pinepaper_agent_start_job with the… → …
  • Tasks that involve Diagrams
  • SKILL.md covers Choose the visual job, Build through the MCP server and Hand off a checked artifact
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pinepaper is an agent skill from madhvantyagi/Gnos. Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/charts-and-quantities.md`, `references/diagrams.md` and `references/interaction-and-export.md`).

It sits in Development, covering Diagrams. It works with Model Context Protocol. The repository describes itself as: Teaching harness , help you to learn anything , It teaches like real teacher , design curriculum , generate videos , simulations , images , pdfs , tracks your learning style etc. The licence is MIT.

When your agent uses it

  • Tasks that involve Diagrams

Example prompts

  • “/pinepaper”

Workflow steps

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

  1. Write a short scene brief: claim, objects, source of quantities, units,
  2. Read the current tool schema. Use pinepaper_tool_guide for a tool family
  3. Call pinepaper_agent_start_job with the canvas preset and a description
  4. Use one pinepaper_agent_batch_execute for the base scene when its
  5. Run pinepaper_validate_scene. Inspect the initial state and a meaningful
  6. Call pinepaper_agent_end_job, inspect its final image, then export through

What it can do on your machine

Read from SKILL.md and the folder at commit 2e42b62. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Pinepaper loads about 1k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 532 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from madhvantyagi/Gnos at commit 2e42b62, republished under its MIT licence (© madhvantyagi). 532 words, ~1,011 tokens.

Download SKILL.mdSave it as .claude/skills/pinepaper/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
pinepaper
description
Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity.

Pinepaper

Use the pinepaper MCP server for a composed diagram or scene whose parts must stay linked or change together. For a mathematical curve or coordinate construction, follow the graph rules in representation choices and use JSXGraph when they fit. Start with the selected subject guide and the block brief. Name the question the learner should answer from the scene. Keep the same objects, symbols, units, and example as the surrounding lesson.

Choose the visual job

  • For a fixed relationship or boundary, read diagrams. Use Excalidraw when a quick static sketch is enough.
  • For a plotted quantity, curve, or linked numerical view, read charts and quantities. Keep exact values in a table or reproducible calculation.
  • For ordered states, physical motion, waves, or a model such as heat transfer, read motion and models.
  • For learner controls or any finished file, read interaction and export. Choose the export before building features that the format cannot preserve.

One lesson may combine a diagram, graph, and motion around the same state. Each view must reveal a different part of the explanation. Do not make the learner infer which curve, arrow, or moving object corresponds to a number in the text.

Build through the MCP server

  1. Write a short scene brief: claim, objects, source of quantities, units, what changes, and the expected output file. Decide what the learner will predict or compare.
  2. Read the current tool schema. Use pinepaper_tool_guide for a tool family or pinepaper_query_capabilities for a specific missing capability. The server schema wins over examples in these files.
  3. Call pinepaper_agent_start_job with the canvas preset and a description of the teaching claim. Plan positions and labels at the size the learner will see in the course viewer.
  4. Use one pinepaper_agent_batch_execute for the base scene when its operations cover the job. Reuse its $0, $1, and later item references. Call a specialized tool, such as pinepaper_create_chart, pinepaper_equation_path, or pinepaper_physics, when the scene needs that capability. Do not approximate a chart or physical rule with decorative movement. Check the returned result of every operation.
  5. Run pinepaper_validate_scene. Inspect the initial state and a meaningful changed state with a screenshot or playback. Check labels, scales, arrow meanings, clipping, and whether the graph and motion agree. Repair failed operations or unwired relations before finishing.
  6. Call pinepaper_agent_end_job, inspect its final image, then export through pinepaper_agent_export or the specialized export tool required by the deliverable. Open the exported file. A correct editor scene is not proof that its export works.
Show full SKILL.md (118 more words)Show less

Use named tools for ordinary production. Use pinepaper_execute_custom_code only for a bounded scene behavior the tool surface cannot express, and check the generated values against the lesson's model. A visually plausible model is still a model. Label measured data, sourced data, assumptions, and simulated outputs distinctly.

Hand off a checked artifact

Return the file, MIME type, title, purpose, source or model assumptions, and one learner question to the lesson coordinator. The coordinator alone updates the lesson and registers the artifact. Check the export in the course viewer before calling it ready. If the server is unavailable, use its diagnostic report when available, make one error-based correction, and report the remaining limitation. Never describe an unmade scene as finished.

© madhvantyagi, 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 4 other files (references) in skills/pinepaper of madhvantyagi/Gnos.

  • SKILL.md
  • references/charts-and-quantities.md
  • references/diagrams.md
  • references/interaction-and-export.md
  • references/motion-and-models.md

Open the folder on GitHubat commit 2e42b62

Compare with similar skills

Pinepaper 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.

Pinepaper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pinepaper this skillmadhvantyagi/Gnos336—~1kAutomated safety check: PassMIT
Bpmn WorkflowWellApp-ai/Well345—~1.4kAutomated safety check: PassMIT
Excalidraw Skillyctimlin/mcp_excalidraw2.5k—~4.6kAutomated safety check: PassMIT
GitDiagram Repository Overviewahmedkhaleel2004/gitdiagram18k—~427Automated safety check: PassMIT
Drawio Diagram BuilderWill-hxw/drawio-diagram-builder412—~5.9kAutomated safety check: PassMIT
Drawiobahayonghang/drawio-skills286—~4.1kAutomated safety check: NotesMIT

Similar skills

  • Bpmn Workflow

    WellApp-ai/Well

    Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

    345 GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Excalidraw Skill

    yctimlin/mcp_excalidraw

    Excalidraw canvas toolkit for creating, editing, and refining diagrams on a live canvas.

    2.5k GitHub stars~4.6k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • GitDiagram Repository Overview

    ahmedkhaleel2004/gitdiagram

    Explains the architecture of a public GitHub repository through GitDiagram: how the code is organized, the main components with paths, and a Mermaid diagram.

    18k GitHub stars~427 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Drawio Diagram Builder

    Will-hxw/drawio-diagram-builder

    Create, edit, replicate, and iteratively refine editable research and technical diagrams in diagrams.net/draw.io (.drawio XML) from prompts, papers, repositories, screenshots, or existing diagrams.

    412 GitHub stars~5.9k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Drawio

    bahayonghang/drawio-skills

    Create, edit, replicate, import, and export draw.io diagrams with an offline YAML-first workflow: architecture, network topologies, flowcharts, UML/ER, org charts, Mermaid/CSV conversion, existing…

    286 GitHub stars~4.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Mermaid Diagrams

    veelenga/claude-mermaid

    Creating and refining Mermaid diagrams with live reload. An agent skill from veelenga/claude-mermaid.

    214 GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from madhvantyagi/Gnos

All 12 skills in this repo
  • Course Design

    madhvantyagi/Gnos

    Design and revise a course's goal, progression, prerequisites, and sources.

    336 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Course Viewer

    madhvantyagi/Gnos

    Show an enrolled course and its lessons. An agent skill from madhvantyagi/Gnos.

    336 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Khan Academy

    madhvantyagi/Gnos

    Find a Khan Academy video fast and add it only on a strong match.

    336 GitHub stars~814 tokensUpdated yesterday
    Auto-check passed
  • Learner Tracking

    madhvantyagi/Gnos

    Record what the learner does and adapt the course to it in real time.

    336 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Lesson Design

    madhvantyagi/Gnos

    Develop the current topic into a connected lesson. An agent skill from madhvantyagi/Gnos.

    336 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Manim Voice Animation

    madhvantyagi/Gnos

    Make Manim teaching animations with narration and subtitles when motion helps a concept.

    336 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

Questions about Pinepaper

What does Pinepaper do?

Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity. Pinepaper is an agent skill from madhvantyagi/Gnos. Build and check Pinepaper MCP diagrams, charts, motion, and interactive models when a lesson needs linked visual states or a changing quantity.

When should I use Pinepaper?

Pinepaper fits situations like: tasks that involve Diagrams.

How do I install Pinepaper in Claude Code?

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

How do I install Pinepaper in Codex?

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

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

What does Pinepaper need to run?

SKILL.md names no scripts, command-line tools or credentials: Pinepaper is instructions for the agent only.

Does Pinepaper 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 Pinepaper 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 Pinepaper use?

Pinepaper 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 Pinepaper use?

About 1k tokens (SKILL.md is roughly 4k 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 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Pinepaper?

Skills that share tags, products or a category with Pinepaper: Bpmn Workflow (WellApp-ai/Well, 345 stars), Excalidraw Skill (yctimlin/mcp_excalidraw, 2.5k stars), GitDiagram Repository Overview (ahmedkhaleel2004/gitdiagram, 18k stars) and Drawio Diagram Builder (Will-hxw/drawio-diagram-builder, 412 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pinepaper?

madhvantyagi (a GitHub user) maintains it in madhvantyagi/Gnos, which has 336 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

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