メニュー
Run comprehensive literature search for Research Harness. Trigger on phrases like "literature-search", "/literature-search", "文献检索", "系统检索论文", "帮我搜相关论文", or equivalent requests to search, shortlist, and ingest relevant papers.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Maintain and debug the Research Harness Zotero plugin adapter. Trigger on Zotero side panel, Zotero reader, Zotero copy/clipboard, local RH API bridge, PDF attachment, RH-to-Zotero sync, seed-paper previews, plugin restart/dev-refresh, or requests to align Zotero plugin behavior with RH CLI/MCP skills without duplicating existing research workflow skills.
Expand from seed papers by following references and citations inside Research Harness workflows. Trigger on phrases like "citation-trace", "/citation-trace", "引用追踪", "沿引用链扩展", or equivalent requests to grow a paper set from one or more seed papers.
Extract core claims from papers for Research Harness evidence structuring. Trigger on phrases like "claim-extraction", "/claim-extraction", "提取论文声明", "claim extract", or equivalent requests to identify key claims, evidence, assumptions, and limitations from ingested papers.
Decide whether a research stage has enough evidence to advance in Research Harness. Trigger on phrases like "evidence-gating", "/evidence-gating", "证据门控", "现在能推进吗", or equivalent requests to check whether current literature, claims, and artifacts justify moving to the next stage.
Improve Research Harness manuscript figures and visual evidence. Use when a paper/PDF has low-quality figures, placeholder fbox/minipage diagrams, blurry PNGs, weak visual evidence, missing publication-ready graphics, figure/table quality review blockers, or requests to use Codex/ImageGen/GPT Image to generate academic paper figures.
Evaluate and replay final_bundle PDF/LaTeX quality for Research Harness project-level self-evolution. Trigger on phrases like "final bundle quality", "PDF quality replay", "LaTeX quality gate", "AAAI PDF QA", "final_bundle_quality", or equivalent requests to scan publication bundles, classify layout/encoding/recompile defects, and decide whether a skill can be promoted.
| name | literature-search |
| description | Run comprehensive literature search for Research Harness. Trigger on phrases like "literature-search", "/literature-search", "文献检索", "系统检索论文", "帮我搜相关论文", or equivalent requests to search, shortlist, and ingest relevant papers. |
| public_suite | research |
| task_type | discovery |
| data_access_level | local+external |
| inputs | topic scope, time range, venue/domain constraints, topic_id |
| outputs | ranked paper candidates, ingestion decisions, frontier evidence |
| gates | ingestion requires topic_id; frontier claims need academic and industry signals |
| artifact_schemas | paper_pool, frontier_attention_evidence |
| estimated_runtime | 10-45 min |
Use this skill for broad paper discovery.
~/code/research-harness/docs/agent-guide.md if topic context is unclear.paper_search or rhub-compatible search flow.When the search supports a paper, survey, or topic-validation task, include a frontier-attention pass:
Papers must be ingested under the topic; non-paper sources should be recorded
in a frontier_attention_evidence artifact with URL, date, source type, and
the claim they support.