paper-narrative

Outermost tier. Judge and reshape the story a paper's figures tell. Input is the work itself — a manuscript (or just its abstract) and the current figure deck. No hand-written brief required.

Setup (any agent, no API key)

This is a pure skill — kernel.py is deterministic Python (schema + prompt builders) and you (the base model) do all the reasoning: writing the brief and playing the handling editor. There is no host runtime and no LLM API. Load the helpers once per session in a Python cell:

exec(open("paper-narrative/kernel.py").read())   # path to this skill's kernel.py

Nothing auto-loads it outside Claude Science. Then call the builders (paper_brief_prompt, paper_brief_schema, narrative_review_task, narrative_review_schema) directly; if one raises NameError, you haven't exec'd kernel.py.