菜单
Enrich paper metadata using LLM extraction. Extract table of contents (TOC), generate L3 paper-level conclusion cards, backfill abstracts, or refetch citation counts from APIs. Use when the user wants to build TOC, update L3, update citation data, or backfill missing abstracts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Adversarial but evidence-bound Reviewer
Plan a literature review before drafting. Build a lean evidence-bound, taste-gated package using references.bib, reference-map.json, review-plan.md, evidence-ledger.md, and table-figure-plan.md.
Draft a fact-grounded, taste-gated review manuscript from an approved lean planning package. Uses references.bib, reference-map.json, review-plan.md, evidence-ledger.md, and table-figure-plan.md; use only after plan is approved.
Understand the autor codebase at a high level. Use when the user asks how to use autor, what built-in skills it has, what features it supports, which workflow to choose, or wants a project overview before using other skills.
Write an exploratory literature review based on papers in an autor workspace. For approved review-article workflows, respect the canonical references.bib / reference-map.json / evidence-ledger contract produced by plan.
High-level orchestrator for iterative review planning and hypothesis evolution. Builds the current autor planning package, triggers targeted acquisition, maintains corpus layers, and stops before writing.
| name | enrich |
| description | Enrich paper metadata using LLM extraction. Extract table of contents (TOC), generate L3 paper-level conclusion cards, backfill abstracts, or refetch citation counts from APIs. Use when the user wants to build TOC, update L3, update citation data, or backfill missing abstracts. |
Use LLM to extract a table of contents (TOC) or generate an L3 paper-level conclusion card. L3 first tries to locate an explicit conclusion/summary section; if none exists, it synthesizes a constrained takeaway from abstract, results, discussion, table/caption text present in Markdown, and highlights. MinerU image attachments are not retained.
Note:
import-endnote/import-zoteroautomatically run toc + l3 + abstract backfill by default. The commands below are for selective enrichment — re-extracting specific papers, supplementing individual entries, or processing the entire library.
Determine the user's intent:
enrich-tocenrich-l3backfill-abstract (extracts from .md + LLM validation)refetch (re-queries APIs to fill in citation_count and related fields)Determine the scope:
--all--force to overwrite existing resultsRun the command:
Extract TOC:
autor enrich-toc [<paper-id> | --all] [--force]
Generate L3:
autor enrich-l3 [<paper-id> | --all] [--force]
Backfill abstracts:
autor backfill-abstract [--dry-run]
Refetch citation counts:
autor refetch [<paper-id> | --all] [--force]
User says: "Extract the conclusions for all papers."
→ Run enrich-l3 --all
User says: "Re-extract the TOC for Smith-2023-Survey."
→ Run enrich-toc "Smith-2023-Survey" --force
User says: "Backfill missing abstracts."
→ Run backfill-abstract, then index --rebuild
User says: "Refresh the citation counts."
→ Run refetch --all, then index --rebuild