Use when `evidence-review` has screened includes and needs a schema-aligned extraction table.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
evidence-review 在 screening 后进入 extraction（C4），需要把纳入论文按字段落到 CSV 以支持后续 synthesis。Transforms screened include rows plus protocol schema into the analysis table used by evidence-review.
Required:
papers/screening_log.csvoutput/PROTOCOL.mdOptional:
papers/paper_notes.jsonlpapers/extraction_table.csvThe table must:
paper_id, title, year, url)notes, not in schema columnsscripts/run.py should:
include rowsoutput/PROTOCOL.md还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Internal template for creating or refactoring a skill into the repository's reference-first shape. **Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill. **Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.
中文简介正在准备中。当前显示原文说明。
Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
中文简介正在准备中。当前显示原文说明。
Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
中文简介正在准备中。当前显示原文说明。
Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
中文简介正在准备中。当前显示原文说明。
Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.
中文简介正在准备中。当前显示原文说明。
Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.
中文简介正在准备中。当前显示原文说明。