paper-eli5listed

Rewrite someone else's research paper into plain English — section by section, paragraph by paragraph, 1:1. Same headings, same paragraph order; nothing summarized, merged, dropped, or reordered; only the language changes (smart-newcomer register, jargon translated on first use). Accepts a local PDF/markdown/text path, an arXiv URL or bare ID, or any other web URL. Equations, tables, and inline math stay verbatim with an "in plain words" gloss, and every display equation also gets a "named form" — the same equation re-emitted with each variable replaced by what it actually is, plus a `where:` legend — with math normalized to canonical `$…$` / `$$…$$` so `/paper-gloss` can typeset it; figures become placeholders with rewritten captions; the references section passes through untouched. Output lands in the current repo at docs/papers/<slug>-eli5.md (papers/ if no docs/; beside the input outside a repo) and is sent to Kyle. Use whenever Kyle types /paper-eli5, or says "eli5 this paper", "simplify this paper", "pl
ksdisch/claude-config · ★ 0 · Data & Documents · score 70

Install: claude install-skill ksdisch/claude-config

# Paper ELI5 — a plain-English rewrite that mirrors the paper 1:1 Take a research paper written for field experts and produce a full rewrite a smart newcomer can read — same sections, same paragraphs, same order. This is a translation, not a summary and not a review. The enemy is **summarization drift**: long rewrites quietly start merging and dropping paragraphs. The skeleton ledger below exists to make that impossible. Lineage note: this is the read-someone-else's-paper aid. NOT `/research-paper` (writes up Kyle's own finished projects) and NOT `/seed-hunt` (picks the next project). The name `paper-companion` stays reserved for a possible future interactive companion. After the input paper is known there are no stops; when running unattended, the global unattended rules apply. ## Parse `$ARGUMENTS` - **Local path** ending `.pdf` / `.md` / `.txt` → the paper. Read PDFs via the Read tool in ≤20-page chunks. - **arXiv URL or bare ID** (e.g. `2402.01234`, an `arxiv.org/abs/…` link) → normalize to `arxiv.org/pdf/<id>`, download to `/tmp` (never commit a PDF into a repo), read as PDF. - **Any other URL** → fetch clean markdown via the `obsidian:defuddle` skill; fall back to WebFetch. - **Remaining words** are operator notes: register tweaks ("even simpler"), an output path override, emphasis. Notes never override the Hard constraints. - **No argument** → ask which paper. Unattended with no or ambiguous input → report the ambiguity as the outcome; don't guess. ##