pdf-text-extractor

SKILL.md

Optionally collect full-text snippets to deepen evidence beyond abstracts.

This skill is intentionally conservative: in many survey runs, abstract/snippet mode is enough and avoids heavy downloads.

When you cannot/should not download PDFs (restricted network, rate limits, no permission), provide PDFs manually and run in “local PDFs only” mode.

下載 PDF（如果有）並提取純文本以支持全文證據，編寫“papers/fulltext_index.jsonl”和“papers/fulltext/*.txt”。 **觸發**：PDF下載、全文、摘錄文本、論文/pdf、全文抽取、下載PDF。 **使用時**：`queries.md`設置`evidence_mode: fulltext`（或者你明確需要全文證據）並希望紙質筆記/聲明提供更有力的證據。 **如果**: `evidence_mode: Abstract`（默認）則跳過；或者您不希望進行下載/提取（成本/權限/時間）。 **網絡**：全文下載通常需要網絡（除非您手動在 `papers/pdfs/` 中提供 PDF 緩存）。 **Guardrail**：服務器下載到 `papers/pdfs/`；默認不覆蓋現有文本抽取（除非顯式要求重提取）。 來源：willoscar/research-units-pipeline-skills。

查看原文