pdf

Estrellas10

Forks2

Actualizado16 de junio de 2026 a las 11:28

Use this Canvas-owned clean-room skill for PDF work where layout, extraction, generation, forms, page operations, or visual verification matter. Trigger for reading PDFs beyond plain text, creating PDFs, merging, splitting, rotating, watermarking, extracting tables or images, filling forms, OCR handoff, and final PDF QA.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Fuente

canvascoding

canvascoding/canvas-notebook

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

2 archivos

SKILL.md

readonly

name	pdf
description	Use this Canvas-owned clean-room skill for PDF work where layout, extraction, generation, forms, page operations, or visual verification matter. Trigger for reading PDFs beyond plain text, creating PDFs, merging, splitting, rotating, watermarking, extracting tables or images, filling forms, OCR handoff, and final PDF QA.
license	Canvas Notebook Sustainable Use License

PDF Workflows

This skill covers PDF creation, inspection, extraction, page operations, forms, and visual QA in Canvas Notebook. It is a clean-room Canvas skill; do not copy vendor skill material, hidden prompts, or proprietary helper code into this folder.

Core Contract

Treat rendered pages as the source of truth for layout-sensitive tasks.
Use text extraction for content discovery, not as proof that a PDF looks correct.
Keep source PDFs immutable unless the user explicitly asks to overwrite them.
Return only the final requested artifact unless the user asks for extracted intermediates.
Use deterministic scripts for repeated operations, but keep them project- or workspace-local unless they are intentionally added to this skill later.

Recommended Tools

pypdf for merge, split, rotate, metadata, encryption, simple form filling, and page-level operations.
pdfplumber for text, coordinates, tables, and layout-aware inspection.
reportlab for creating new PDFs.
Poppler tools such as pdfinfo, pdftoppm, and pdftocairo for rendering and page diagnostics.
OCR tools only when available and required; if OCR dependencies are missing, explain the blocker instead of pretending scanned text was read.

Workflow

Classify the task: read/review, generate, page operation, form filling, extraction, redaction, OCR, or repair.
Make a working copy for destructive operations.
Use the simplest reliable library for the operation. Avoid manipulating raw PDF bytes manually.
Render updated pages to PNG and inspect alignment, margins, clipping, legibility, form values, signatures/watermarks, and page order.
If a visual issue appears, repair the source operation and re-render.

Common Tasks

Extract text: start with pdfplumber; preserve page numbers and note extraction uncertainty for scanned or complex PDFs.
Extract tables: use pdfplumber table strategies and validate against rendered pages.
Create a PDF: use reportlab; define margins, fonts, section hierarchy, tables, and pagination explicitly.
Merge or split: use pypdf; verify page count and order with pdfinfo and rendered thumbnails.
Fill forms: inspect AcroForm fields first, write a copy, flatten only if requested or necessary, then render filled pages.
Redact: do not cover text with a black rectangle alone. Remove or rewrite underlying content where possible, then verify extraction and rendering.

Final Checks

Latest rendered pages match the requested content and order.
Text is readable at normal zoom and no content is clipped.
Page size, orientation, margins, headers, footers, and numbering are correct.
Any extraction, OCR, or redaction limitations are stated clearly.

Más de este repositorio

mismo repositorio

create-plugin

canvascoding/canvas-notebook

Create, update, validate, and package Canvas Plugins. Use when users want to build a Canvas plugin, bundle multiple skills into a plugin, define plugin metadata, add icons or logos, declare recommended Composio, Canvas Email, or MCP connectors, prepare a marketplace entry, or submit a plugin to the Canvas Plugin Store.

2026-07-1010

greploop

canvascoding/canvas-notebook

Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until it reaches the repository's configured Greptile merge threshold with zero unresolved actionable comments, or until the five-review maximum is reached. Triggers Greptile review, fixes all actionable comments, pushes/re-shelves, re-triggers review only for new head SHAs unless a 5/5 score is already published, and repeats. Use when the user wants to optimize a PR/MR/CL against Greptile's code review standards without creating runaway review loops.

2026-06-2910

release-publisher

canvascoding/canvas-notebook

Publish a new Canvas Notebook release. Use this skill whenever the user asks to bump a version, prepare release notes, update CHANGELOG.md, create or push a git tag, publish a GitHub Release, deploy, or automate the release workflow. This skill covers the full release sequence for this repository: inspect commits/tags, push completed product-code commits first when authorized, confirm the pushed code has built on GitHub, choose the next calendar version, update package and CLI versions, update the changelog, run the required local build, commit, push the release commit, wait for the remote Build and Push worker on the pushed branch, tag, push the tag, and publish the release.

2026-06-2910

opensrc

canvascoding/canvas-notebook

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.

2026-06-2910

marp-slides

canvascoding/canvas-notebook

Create, edit, review, preview, and export polished Marp Markdown slide decks in Canvas Notebook. Use when the user wants Markdown-native presentations, `.marp.md` or `.slides.md` files, version-controlled decks, Marp PDF/image/PPTX/HTML export, speaker notes, dashboard-style slides, data cards, or better looking decks that should remain close to plain text.

2026-06-1910

algorithmic-art

canvascoding/canvas-notebook

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

2026-06-1610

name	pdf
description	Use this Canvas-owned clean-room skill for PDF work where layout, extraction, generation, forms, page operations, or visual verification matter. Trigger for reading PDFs beyond plain text, creating PDFs, merging, splitting, rotating, watermarking, extracting tables or images, filling forms, OCR handoff, and final PDF QA.
license	Canvas Notebook Sustainable Use License

PDF Workflows

Core Contract

Treat rendered pages as the source of truth for layout-sensitive tasks.
Use text extraction for content discovery, not as proof that a PDF looks correct.
Keep source PDFs immutable unless the user explicitly asks to overwrite them.
Return only the final requested artifact unless the user asks for extracted intermediates.
Use deterministic scripts for repeated operations, but keep them project- or workspace-local unless they are intentionally added to this skill later.

Recommended Tools

pypdf for merge, split, rotate, metadata, encryption, simple form filling, and page-level operations.
pdfplumber for text, coordinates, tables, and layout-aware inspection.
reportlab for creating new PDFs.
Poppler tools such as pdfinfo, pdftoppm, and pdftocairo for rendering and page diagnostics.
OCR tools only when available and required; if OCR dependencies are missing, explain the blocker instead of pretending scanned text was read.

Workflow

Classify the task: read/review, generate, page operation, form filling, extraction, redaction, OCR, or repair.
Make a working copy for destructive operations.
Use the simplest reliable library for the operation. Avoid manipulating raw PDF bytes manually.
Render updated pages to PNG and inspect alignment, margins, clipping, legibility, form values, signatures/watermarks, and page order.
If a visual issue appears, repair the source operation and re-render.

Common Tasks

Extract text: start with pdfplumber; preserve page numbers and note extraction uncertainty for scanned or complex PDFs.
Extract tables: use pdfplumber table strategies and validate against rendered pages.
Create a PDF: use reportlab; define margins, fonts, section hierarchy, tables, and pagination explicitly.
Merge or split: use pypdf; verify page count and order with pdfinfo and rendered thumbnails.
Fill forms: inspect AcroForm fields first, write a copy, flatten only if requested or necessary, then render filled pages.
Redact: do not cover text with a black rectangle alone. Remove or rewrite underlying content where possible, then verify extraction and rendering.

Final Checks

Latest rendered pages match the requested content and order.
Text is readable at normal zoom and no content is clipped.
Page size, orientation, margins, headers, footers, and numbering are correct.
Any extraction, OCR, or redaction limitations are stated clearly.