메뉴
View paper content at different detail levels. L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), L4 (full text). Use when the user wants to read a paper, see its abstract, L3 takeaway, or full content.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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 | show |
| description | View paper content at different detail levels. L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), L4 (full text). Use when the user wants to read a paper, see its abstract, L3 takeaway, or full content. |
View the content of a specified paper in a layered structure. Supports four levels: L1 (metadata), L2 (abstract), L3 (paper-level conclusion card), and L4 (full text).
Parse user input and extract:
data/papers/)If the user is unsure of the paper ID, use /search first to locate the target paper.
Run the view command:
autor show "<paper-id>" --layer <N>
| Level | Content | Notes |
|---|---|---|
| L1 | Metadata | title, authors, year, journal, doi |
| L2 | Abstract | abstract |
| L3 | Paper-level conclusion card | takeaway, key findings, quantitative signals, limitations, and provenance when available |
| L4 | Full text | complete Markdown |
User says: "Show me the abstract of Smith-2023-TransformerSurvey."
→ Run show "Smith-2023-TransformerSurvey" --layer 2
User says: "Give me the full text of Zhang-2024-LLM."
→ Run show "Zhang-2024-LLM" --layer 4
User says: "What is the conclusion of this paper?" (paper ID already in context)
→ Run show "<paper-id>" --layer 3