$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill manuscript-ingestUse when paper-review needs a canonical manuscript text artifact before claim extraction. Trigger: ingest paper, manuscript text, provide paper, paper.md, 输入论文, 导入稿件, 审稿输入. Use when: You are running the paper-review pipeline and need output/PAPER.md before `claims-e
| 1 | # Manuscript Ingest |
| 2 | |
| 3 | Transforms a manuscript source file into the canonical text artifact used by `paper-review`. |
| 4 | |
| 5 | ## Inputs |
| 6 | |
| 7 | One manuscript source from the workspace, typically: |
| 8 | - `inputs/manuscript.md` |
| 9 | - `inputs/manuscript.txt` |
| 10 | - `inputs/manuscript.pdf` |
| 11 | |
| 12 | ## Output |
| 13 | |
| 14 | - `output/PAPER.md` |
| 15 | |
| 16 | ## Script boundary |
| 17 | |
| 18 | `scripts/run.py` should: |
| 19 | - find the simplest available manuscript source |
| 20 | - extract faithful text |
| 21 | - write the full text to `output/PAPER.md` |
| 22 | |
| 23 | It should not summarize, critique, or reformat the manuscript into a review. |
| 24 | |
| 25 | ## Contract |
| 26 | |
| 27 | The output must preserve: |
| 28 | - paper body text |
| 29 | - section headings when available |
| 30 | - page markers when extractable |
| 31 | |
| 32 | ## Acceptance |
| 33 | |
| 34 | - `output/PAPER.md` exists |
| 35 | - it contains the manuscript body rather than only title/abstract |
| 36 | |
| 37 | ## Non-goals |
| 38 | |
| 39 | - claim extraction |
| 40 | - evidence auditing |
| 41 | - review writing |