Communitygithub.com

PDF

Usa esta habilidad siempre que el usuario quiera hacer cualquier cosa con archivos PDF. Esto incluye leer o extraer texto/tablas de PDFs, combinar o fusionar varios PDFs en uno, dividir PDFs, rotar páginas, agregar marcas de agua, crear nuevos PDFs, rellenar formularios PDF, cifrar/descifrar PDFs, extraer imágenes y OCR en PDFs escaneados para hacerlos buscables. Si el usuario menciona un archivo .pdf o pide producir uno, usa esta habilidad.

¿Qué es PDF?

La habilidad PDF proporciona una guía completa para el procesamiento de documentos PDF utilizando bibliotecas de Python (pypdf, pdfplumber, reportlab) y herramientas de línea de comandos (pdftotext, qpdf, pdftk). Está diseñada para asistentes de IA y desarrolladores que necesitan automatizar tareas comunes con PDF, como extraer texto y tablas, fusionar y dividir documentos, rotar páginas, agregar marcas de agua, crear PDFs desde cero, realizar OCR en documentos escaneados, proteger con contraseña y extraer imágenes. La habilidad incluye ejemplos de código prácticos, tablas de referencia rápida y enlaces a documentación más detallada (como `reference.md` y `forms.md`) para casos de uso avanzados como el llenado de formularios PDF. Soporta múltiples plataformas y bibliotecas, y enfatiza las mejores prácticas, como evitar caracteres Unicode de subíndice/superíndice en ReportLab y en su lugar usar etiquetas XML.

Compatible con✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/pdf

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Guía de Procesamiento de PDF

Resumen

Esta guía cubre las operaciones esenciales de procesamiento de PDF utilizando bibliotecas de Python y herramientas de línea de comandos. Para características avanzadas, bibliotecas de JavaScript y ejemplos detallados, consulta reference.md. Si necesitas rellenar un formulario PDF, lee forms.md y sigue sus instrucciones.

Inicio Rápido

from pypdf import PdfReader, PdfWriter

# Leer un PDF
reader = PdfReader("document.pdf")
print(f"Páginas: {len(reader.pages)}")

# Extraer texto
text = ""
for page in reader.pages:
    text += page.extract_text()

Bibliotecas de Python

pypdf - Operaciones Básicas

Fusionar PDFs

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

Dividir PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

Extraer Metadatos

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Título: {meta.title}")
print(f"Autor: {meta.author}")
print(f"Asunto: {meta.subject}")
print(f"Creador: {meta.creator}")

Rotar Páginas

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # Rotar 90 grados en sentido horario
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber - Extracción de Texto y Tablas

Extraer Texto con Diseño

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

Extraer Tablas

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Tabla {j+1} en página {i+1}:")
            for row in table:
                print(row)

Extracción Avanzada de Tablas

import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # Verificar si la tabla no está vacía
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combinar todas las tablas
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Crear PDFs

Creación Básica de PDF

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Agregar texto
c.drawString(100, height - 100, "¡Hola Mundo!")
c.drawString(100, height - 120, "Este es un PDF creado con reportlab")

# Agregar una línea
c.line(100, height - 140, 400, height - 140)

# Guardar
c.save()

Crear PDF con Varias Páginas

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet

doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []

# Agregar contenido
title = Paragraph("Título del Informe", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("Este es el cuerpo del informe. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# Página 2
story.append(Paragraph("Página 2", styles['Heading1']))
story.append(Paragraph("Contenido para la página 2", styles['Normal']))

# Construir PDF
doc.build(story)

Subíndices y Superíndices

IMPORTANTE: Nunca uses caracteres Unicode de subíndice/superíndice (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) en PDFs de ReportLab. Las fuentes integradas no incluyen estos glifos, lo que hace que se muestren como cuadros negros sólidos.

En su lugar, usa las etiquetas de marcado XML de ReportLab en objetos Paragraph:

from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet

styles = getSampleStyleSheet()

# Subíndices: usa la etiqueta <sub>
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])

# Superíndices: usa la etiqueta <super>
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])

Para texto dibujado con canvas (no objetos Paragraph), ajusta manualmente el tamaño de la fuente y la posición en lugar de usar subíndices/superíndices Unicode.

Herramientas de Línea de Comandos

pdftotext (poppler-utils)

# Extraer texto
pdftotext input.pdf output.txt

# Extraer texto preservando el diseño
pdftotext -layout input.pdf output.txt

# Extraer páginas específicas
pdftotext -f 1 -l 5 input.pdf output.txt  # Páginas 1-5

qpdf

# Fusionar PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Dividir páginas
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# Rotar páginas
qpdf input.pdf output.pdf --rotate=+90:1  # Rotar página 1 a 90 grados

# Eliminar contraseña
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

pdftk (si está disponible)

# Fusionar
pdftk file1.pdf file2.pdf cat output merged.pdf

# Dividir
pdftk input.pdf burst

# Rotar
pdftk input.pdf rotate 1east output rotated.pdf

Tareas Comunes

Extraer Texto de PDFs Escaneados

# Requiere: uv pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convertir PDF a imágenes
images = convert_from_path('scanned.pdf')

# OCR de cada página
text = ""
for i, image in enumerate(images):
    text += f"Página {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

Agregar Marca de Agua

from pypdf import PdfReader, PdfWriter

# Crear marca de agua (o cargar una existente)
watermark = PdfReader("watermark.pdf").pages[0]

# Aplicar a todas las páginas
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

Extraer Imágenes

# Usando pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix

# Esto extrae todas las imágenes como output_prefix-000.jpg, output_prefix-001.jpg, etc.

Protección con Contraseña

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Agregar contraseña
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Referencia Rápida

TareaMejor HerramientaComando/Código
Fusionar PDFspypdfwriter.add_page(page)
Dividir PDFspypdfUn archivo por página
Extraer textopdfplumberpage.extract_text()
Extraer tablaspdfplumberpage.extract_tables()
Crear PDFsreportlabCanvas o Platypus
Fusionar desde línea de comandosqpdfqpdf --empty --pages ...
OCR de PDFs escaneadospytesseractConvertir a imagen primero
Rellenar formularios PDFpdf-lib o pypdf (ver forms.md)Ver forms.md

Próximos Pasos

  • Para uso avanzado de pypdfium2, consulta reference.md
  • Para bibliotecas de JavaScript (pdf-lib), consulta reference.md
  • Si necesitas rellenar un formulario PDF, sigue las instrucciones en forms.md
  • Para guías de solución de problemas, consulta reference.md

Esta habilidad es creada y mantenida por Anthropic. Incluida aquí sin modificaciones, excepto por los metadatos del frontmatter y la capitalización de los enlaces a reference.md/forms.md, que en el repositorio original están en mayúsculas; consulta LICENSE.txt para los términos.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

alphagenome

Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

analytical-method-validation

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

arbor

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g.

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

astropy

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

autoskill

Observe the user

benchling-integration

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

bgpt-paper-search

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

bids

>

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g.

cellxgene-census

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

citation-management

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

clinical-reports

Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.

Skills relacionados