菜单
Cluster, deduplicate, generalize, and rank proof-pattern SkillCandidates or SkillCards extracted from multiple papers. Use when a coding agent should synthesize single-paper extractions into a domain method map, merged SkillCards, and a synthesis report for an AI4Math skill library.
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
| name | cross-paper-skill-synthesizer |
| description | Cluster, deduplicate, generalize, and rank proof-pattern SkillCandidates or SkillCards extracted from multiple papers. Use when a coding agent should synthesize single-paper extractions into a domain method map, merged SkillCards, and a synthesis report for an AI4Math skill library. |
Use this skill after multiple papers have been processed by paper-to-skill-extractor. The goal is to build a domain method map and library-ready SkillCards, not to summarize papers.
Accept any mix of:
extractions/<paper_id>/skill_candidates.jsonextractions/<paper_id>/skill_cards/*.yamlhuman_feedback_state.json from the research project.human_feedback_state.json exists, read focus_updates, negative_preferences, skill_decisions, and next_step_directives before clustering.domain_method_map.yaml, merged SkillCards, and synthesis_report.md.synthesis_report.md, explain which user feedback affected merge, reject, or library-readiness decisions.Read only as needed:
references/synthesis_rules.md: clustering, merging, and safety rules.references/schemas.md: required output fields.Use the templates:
assets/domain_method_map.template.yamlassets/merged_skill_card.template.yamloutputs/<research_project_id>/synthesized_skills/
├── domain_method_map.yaml
├── merged_skill_cards/
│ └── <skill_name>.yaml
└── synthesis_report.md
needs_human_review.ready_for_library, needs_human_review, too_specific, duplicate, and unsafe_generalization.skill_decisions when grouping, merging, rejecting, or marking skills for revision.Before finishing, confirm:
paper.md files.domain_method_map.yaml records clusters, representative skills, and statuses.Route AI4Math paper-reading tasks to the appropriate bundled skill package.
Use when extracting reusable AI4Math research skills from papers, especially PDF-to-SkillCard workflows, paper triage, PDF preparation, proof-pattern extraction, and cross-paper SkillCard synthesis for a coding-agent-neutral paper-to-skill workflow.
Search for papers that may provide new methods, new theory, sharper bounds, different assumptions, proof techniques, lower bounds, abstractions, or cross-domain transfers for a math research direction. Use when a coding agent should look beyond nearest-neighbor related work and generate innovation_candidates.json with reasons and risks.
Download open-access research-paper PDFs selected from reading_plan.json, candidate_papers.json, or innovation_candidates.json. Use when a coding agent should save paper.pdf, metadata.json, and a bilingual download report for confirmed paper IDs without bypassing paywalls, and before PDF-to-Markdown conversion or paper-to-skill extraction.
Extract reusable mathematical research skills from Markdown papers, especially proof-pattern skills such as descent lemmas, inequality relaxations, telescoping bounds, error decompositions, Lyapunov arguments, concentration bounds, Galerkin/Cea arguments, Aubin-Nitsche duality, and Lax-Milgram well-posedness. Use when a coding agent is asked to turn a math paper, proof, theorem section, convergence analysis, stability analysis, or error analysis into SkillCandidate JSON, SkillCard YAML, or a paper-to-skill report without relying on external LLM APIs.
Run the complete AI4Math paper-to-skill workflow from a user-provided PDF or Markdown paper. Use when a coding agent should preserve the original paper, convert PDF to paper.md when needed, extract proof-pattern SkillCandidates and SkillCards with line evidence, and optionally route reviewed cards into cross-paper synthesis.