Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`. **Trigger**: PDF download, fulltext, extract text, papers/pdfs, 全文抽取, 下载PDF. **Use when**: `queries.md` 设置 `evidence_mode: fulltext`（或你明确需要全文证据）并希望为 paper notes/claims 提供更强 evidence。
安装
npx skills add WILLOSCAR/research-units-pipeline-skills --skill pdf-text-extractornpx skills add WILLOSCAR/research-units-pipeline-skills --skill pdf-text-extractor -a claude-code -gnpx skills add WILLOSCAR/research-units-pipeline-skills --skill pdf-text-extractor -a codex -ggemini skills install https://github.com/WILLOSCAR/research-units-pipeline-skills.git --path .codex/skills/pdf-text-extractorgh skill install WILLOSCAR/research-units-pipeline-skills pdf-text-extractorgit clone --depth 1 https://github.com/WILLOSCAR/research-units-pipeline-skills /tmp/WILLOSCAR__research-units-pipeline-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/WILLOSCAR__research-units-pipeline-skills/.codex/skills/pdf-text-extractor ~/.claude/skills/pdf-text-extractor # Claude Code
cp -R /tmp/WILLOSCAR__research-units-pipeline-skills/.codex/skills/pdf-text-extractor ~/.agents/skills/pdf-text-extractor # Codex, Cursor, Gemini CLI, Copilot, OpenCode