Skip to content

PlutoLei/paperbanana-skill

paperbanana

Verified

Generate and revise academic figures, data plots, or image slides through a configured PaperBanana backend; inspect their automated review status.

FileKindSize
SKILL.mdskill md727 B
examples/ablation_brats_figure.pngbinary566.5 KB
examples/bio_signaling_pathway.pngbinary15.2 MB
examples/chinese_calligraphy.pngbinary2.4 MB
examples/data_lakehouse.pngbinary15.4 MB
examples/editable-demo/README.mdmarkdown2.5 KB
examples/editable-demo/editable-demo.pptxbinary87.8 KB
examples/editable-demo/research-brief/README.mdmarkdown3.2 KB
examples/editable-demo/research-brief/preview-manifest.jsonconfig1.1 KB
examples/editable-demo/research-brief/research-brief.pptxbinary126.7 KB
examples/editable-demo/research-brief/slide-spec.jsonconfig13.6 KB
examples/editable-demo/slide-spec.jsonconfig4.8 KB
examples/game_theory_influence_diagram.pngbinary915.4 KB
examples/mamba_architecture.pngbinary648.7 KB
examples/nlp_rag_pipeline.pngbinary14.9 MB
examples/pipeline_architecture.pngbinary896.0 KB
examples/previews/README.mdmarkdown1.1 KB
examples/previews/ablation_brats_figure.webpbinary50.7 KB
examples/previews/bio_signaling_pathway.webpbinary40.3 KB
examples/previews/chinese_calligraphy.webpbinary66.0 KB
examples/previews/data_lakehouse.webpbinary42.5 KB
examples/previews/editable-demo.webpbinary47.6 KB
examples/previews/game_theory_influence_diagram.webpbinary55.3 KB
examples/previews/mamba_architecture.webpbinary67.4 KB
examples/previews/manifest.jsonconfig6.8 KB
examples/previews/nlp_rag_pipeline.webpbinary54.7 KB
examples/previews/pipeline_architecture.webpbinary37.6 KB
examples/previews/rag_pipeline.webpbinary52.5 KB
examples/previews/research-brief-01.webpbinary49.2 KB
examples/previews/research-brief-02.webpbinary39.3 KB
examples/previews/research-brief-03.webpbinary55.1 KB
examples/previews/routing-comparison--A2_gemini.webpbinary88.3 KB
examples/previews/routing-comparison--A2_openai.webpbinary103.3 KB
examples/previews/routing-comparison--D2_gemini.webpbinary79.0 KB
examples/previews/routing-comparison--D2_openai.webpbinary66.4 KB
examples/previews/routing-comparison--G2_gemini.webpbinary66.0 KB
examples/previews/routing-comparison--G2_openai.webpbinary169.6 KB
examples/previews/slide_deck_workflow.webpbinary59.0 KB
examples/previews/slide_flywheel_01_cover.webpbinary64.3 KB
examples/previews/slide_flywheel_04_model.webpbinary71.2 KB
examples/previews/slide_flywheel_07_ai_tools.webpbinary82.9 KB
examples/previews/slide_flywheel_10_summary.webpbinary61.5 KB
examples/previews/slide_scrna_workflow.webpbinary48.8 KB
examples/previews/textmamba3d_architecture.webpbinary80.6 KB
examples/previews/transformer_architecture.webpbinary53.0 KB
examples/previews/unet_mamba_segmentation.webpbinary54.3 KB
examples/rag_pipeline.pngbinary686.2 KB
examples/routing-comparison/A2_gemini.pngbinary1.4 MB
examples/routing-comparison/A2_openai.pngbinary813.9 KB
examples/routing-comparison/D2_gemini.pngbinary1.2 MB
examples/routing-comparison/D2_openai.pngbinary1.3 MB
examples/routing-comparison/G2_gemini.pngbinary2.4 MB
examples/routing-comparison/G2_openai.pngbinary1.6 MB
examples/slide_deck_workflow.pngbinary502.1 KB
examples/slide_flywheel_01_cover.pngbinary932.2 KB
examples/slide_flywheel_04_model.pngbinary1.1 MB
examples/slide_flywheel_07_ai_tools.pngbinary1.1 MB
examples/slide_flywheel_10_summary.pngbinary1.2 MB
examples/slide_scrna_workflow.pngbinary1.2 MB
examples/textmamba3d_architecture.pngbinary491.3 KB
examples/transformer_architecture.pngbinary789.5 KB
examples/unet_mamba_segmentation.pngbinary11.7 MB
scripts/validate-repository.pyscript3.1 KB

scripts/validate-repository.py

View on GitHub
#!/usr/bin/env python3
"""Check skill metadata and packaged local Markdown/HTML references, without network."""
import argparse
import json
import os
from pathlib import Path
import re
from urllib.parse import unquote, urlsplit

import yaml


def validate(root: Path) -> list[str]:
    errors = []
    ignored = {".git", "node_modules", ".venv", "__pycache__", ".claude"}
    for current, directories, names in os.walk(root):
        directories[:] = [d for d in directories if d not in ignored and not (Path(current) / d).is_symlink()]
        for name in sorted(names):
            file = Path(current) / name
            if file.is_symlink():
                continue
            relative = file.relative_to(root)
            if name in {"marketplace.json", "plugin.json"} and ".claude-plugin" in file.parts:
                try:
                    json.loads(file.read_text())
                except (ValueError, OSError) as exc:
                    errors.append(f"{relative}: invalid manifest: {exc}")
            if file.suffix != ".md":
                continue
            text = file.read_text()
            if name == "SKILL.md":
                match = re.match(r"\A---\r?\n(.*?)\r?\n---(?:\r?\n|$)", text, re.S)
                try:
                    if not match:
                        raise ValueError("missing YAML frontmatter")
                    data = yaml.safe_load(match.group(1))
                    if not isinstance(data, dict):
                        raise ValueError("frontmatter must be a mapping")
                    for key in ("name", "description"):
                        if not isinstance(data.get(key), str) or not data[key].strip():
                            raise ValueError(f"{key} must be a nonempty string")
                except (yaml.YAMLError, ValueError) as exc:
                    errors.append(f"{relative}: {exc}")
            # Fenced examples are instructions, not references in this document.
            prose = re.sub(r"(?ms)^```[^\n]*\n.*?^```[^\n]*(?:\n|$)", "", text)
            links = re.findall(r"\[[^\]\n]*\]\(([^)\n]+)\)", prose)
            links += re.findall(r"(?:src|href)=[\"']([^\"']+)[\"']", prose)
            for raw in links:
                target = raw.strip().split(' "', 1)[0].strip("<>")
                parsed = urlsplit(target)
                if parsed.scheme or parsed.netloc or not parsed.path:
                    continue
                path = (file.parent / unquote(parsed.path)).resolve()
                if not path.is_relative_to(root):
                    errors.append(f"{relative}: reference leaves bundle: {target}")
                elif not path.exists():
                    errors.append(f"{relative}: missing local reference: {target}")
    return errors


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("root", nargs="?", default=str(Path(__file__).resolve().parents[1]))
    args = parser.parse_args()
    failures = validate(Path(args.root).resolve())
    for failure in failures:
        print(f"FAIL: {failure}")
    if failures:
        raise SystemExit(1)
    print("Skill YAML, plugin JSON and local document references are valid.")
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall