# Paper Ingest

> Normalize `_raw/` into extracted chunks, `index.md`, and `summary.md`, and register the paper in `_index/`. Use when the user asks to ingest a PDF, `sources/<id>/`, generate extracted chunks or a cited summary, or complete paper intake.

- Skill: `l4pislazuli/paper-ingest` (Agent Skill)
- Install (CLI): `npx skillmds@latest add l4pislazuli/paper-ingest`
- Raw SKILL.md: https://api.skillmd.com/api/skills/l4pislazuli/paper-ingest/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: L4pisLazuli (https://skillmd.com/u/l4pislazuli)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/l4pislazuli/paper-ingest

---


# Paper ingest

When a PDF exists under `sources/<source-id>/original/`, run the full set below.
Extraction details: read `/paper-extract` when math or algorithms are broken, `_raw/` is missing or the main task, or Marker / OCR / arXiv math is in play.

Templates: `_templates/source-index.md`, `_templates/summary.md`. Also `_templates/study-note.md`, `_templates/question-bank.md`, `_templates/algorithm.md`, `_templates/repro-readme.md` as mode requires.

Replace every `{{...}}` in copied templates (`source-id`, `title`, `mode`, `date`). Do not copy unused placeholder text into real notes.

## Steps

1. Confirm `source-id` and `mode` (`study` / `survey` / `both`). Ask if unspecified
2. Confirm extraction inputs (`/paper-extract`)
   - If `_raw/` exists, use it as the primary input
   - If missing, ask the user to run Marker (full text); for math, use the reference priority (arXiv source first). Continue only after inputs are ready
   - Do not full-read the PDF to fill `extracted/` (short checks and missing-page fills only)
3. Normalize `_raw/` into section chunks `extracted/NN-<section-slug>.md`
   - About 300–500 lines per file
   - Add block IDs per `/paper-extract` (one ID = one block; unique in the file)
   - Figures/tables: captions only; note "See original for figure"
   - Do not change meaning. Mark doubtful extractions with `[extraction uncertain]`
   - For survey/both, if math or algorithms are broken, follow `/paper-extract` (arXiv source → Mathpix → page image + vision); on failure, follow that fallback and mark `[extraction uncertain]` (never an arbitrary source)
4. Generate `index.md` from `_templates/source-index.md`. Set `mode` from step 1. Keep only Artifact links that match `mode`
5. Generate `summary.md` from `_templates/summary.md` (every claim must be cited per `CLAUDE.md`). Set the same `mode`
6. Register the paper in `_index/MOC.md` and `_index/keywords.md`. MOC `status` must match `index.md` frontmatter. On first paper, delete the `(none yet)` row
7. If mode is study/both, prepare `study/` stubs from `_templates/study-note.md` and `_templates/question-bank.md`. If survey/both, prepare `survey/algorithm.md` from `_templates/algorithm.md` and `survey/repro/README.md` from `_templates/repro-readme.md`
8. Set `status` to `ready` on `index.md`, `summary.md`, and any stubs created in step 7 (unless extraction is still incomplete: then `extracting`)

## Done when

- `extracted/` chunks exist via `_raw/` or an explicit exception path
- Block IDs in each `extracted/` file are unique
- `index.md` / `summary.md` exist; every `#^` citation resolves to a block ID that exists in the target file
- No `{{...}}`, `…`, or other template wording remains in generated files
- Unused study/survey Artifact links were removed
- Frontmatter `mode` matches the confirmed mode; `status` is `ready` (or `extracting` if still incomplete); `authors` / `year` / `venue` are filled only from the paper
- The paper is listed in `_index/` with the same `mode` and `status`
- Citations point only to `extracted/` (never `_raw/`)