Easypaper Paper From Metadata

Use this skill when the user wants to generate an academic paper from metadata. It handles both metadata collection and paper generation in one workflow.

Recommended Input

Have the user prepare a metadata JSON file that follows examples/meta.json. Treat that file as a schema/template reference, not as a runnable paper. For a runnable project-local sample, use examples/template/meta.json.

Load JSON as PaperGenerationRequest, then convert it to SDK inputs:

import json
from pathlib import Path
from easypaper import EasyPaper, PaperGenerationRequest

metadata_path = Path("metadata.json").resolve()
raw = json.loads(metadata_path.read_text(encoding="utf-8"))

def metadata_relative_path(value: str) -> str:
    candidate = Path(value).expanduser()
    if candidate.is_absolute():
        return str(candidate)
    return str((metadata_path.parent / candidate).resolve())

if not raw.get("materials_root"):
    raw["materials_root"] = str(metadata_path.parent)
if raw.get("template_path"):
    raw["template_path"] = metadata_relative_path(raw["template_path"])
if (
    isinstance(raw.get("code_repository"), dict)
    and raw["code_repository"].get("type") == "local_dir"
    and raw["code_repository"].get("path")
):
    raw["code_repository"]["path"] = metadata_relative_path(raw["code_repository"]["path"])

request = PaperGenerationRequest.model_validate(raw)
paper_metadata = request.to_metadata()
options = {
    "output_dir": request.output_dir,
    "save_output": request.save_output,
    "compile_pdf": request.compile_pdf,
    "figures_source_dir": request.figures_source_dir,