OpenParable
Skip to content
← Back to skills

Manuscript Ingest

Documents
manuscript-ingest

Manuscript Ingest is an Agent Skill for documents published in the WILLOSCAR/research-units-pipeline-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use 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-extractor`. **Skip if**: `output/PAPER.md` already exists and looks like the full manuscript text. **Network**: none. **Guardrail**: Do not summarize or rewrite the paper; store the raw text (or a faithful extraction) so claims stay traceable.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/WILLOSCAR/research-units-pipeline-skills/blob/HEAD/.codex/skills/manuscript-ingest/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/manuscript-ingest, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Manuscript Ingest

Transforms a manuscript source file into the canonical text artifact used by paper-review.

Inputs

One manuscript source from the workspace, typically:

  • inputs/manuscript.md
  • inputs/manuscript.txt
  • inputs/manuscript.pdf

Output

  • output/PAPER.md

Script boundary

scripts/run.py should:

  • find the simplest available manuscript source
  • extract faithful text
  • write the full text to output/PAPER.md

It should not summarize, critique, or reformat the manuscript into a review.

Contract

The output must preserve:

  • paper body text
  • section headings when available
  • page markers when extractable

Acceptance

  • output/PAPER.md exists
  • it contains the manuscript body rather than only title/abstract

Non-goals

  • claim extraction
  • evidence auditing
  • review writing