이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/zjunlp/AutoSciRub.저장소 README를 불러오는 중…
수집된 skill 14개 중 14개를 표시합니다.
Map ResearchClawBench instructions, relevant public-source results, and supplied data into an executable evidence rubric. Use for experiment planning or repair while preserving complete comparisons, method fidelity, and figure semantics.
원문 언어: 영어
Recover relevant public papers, methods, comparison matrices, and result artifacts for a ResearchClawBench task with query-level provenance. Use after instruction extraction to resolve consequential protocol gaps without assuming any retrieved paper is the…
원문 언어: 영어
Extract instruction requirements and discriminative retrieval anchors for a ResearchClawBench task before literature or data analysis. Use to establish the original task contract and prevent later planning from omitting requested evidence.
원문 언어: 영어
Recover readable scientific PDF content with MinerU for the ResearchClawBench adaptation when relevant full text is missing or inadequate. Preserve equations and tables, cache derived text outside supplied inputs, and reuse reliable existing text.
원문 언어: 영어
Verify a ResearchClawBench report against original instructions, relevant public-source obligations, executed outputs, and figure semantics. Use after reporting and repairs to detect omitted experiments, weak substitutions, unsupported claims, and…
원문 언어: 영어
Run the ResearchClawBench adaptation of AutoSciRub from instruction extraction through public-source grounding, faithful experiments, report verification, and evidence repair. Use for a complete benchmark task or an authorized continuation.
원문 언어: 영어
Coordinate the full AutoSciRub workflow for autonomous scientific research tasks. Use when a user wants to turn an underspecified research instruction into an executable rubric, guide research execution, verify a report criterion by criterion, and run…
원문 언어: 영어
Verify a scientific report and supporting artifacts against an AutoSciRub executable rubric criterion by criterion. Use after execution has produced a report, code, results, tables, figures, or other artifacts, when Codex needs strict satisfaction labels,…
원문 언어: 영어
Synthesize a task-specific executable scientific rubric from an instruction-derived skeleton, literature grounding, and task-data profile. Use in AutoSciRub when Codex needs criteria with linked goals, data sources, required analyses, metrics, comparisons,…
원문 언어: 영어
Convert PDFs and paper-like documents into Markdown with MinerU before reading or analyzing them. Use when AutoSciRub or another scientific agent needs to inspect local or remote PDFs, equations, tables, or scanned papers where direct PDF text extraction…
원문 언어: 영어
Induce an instruction-derived scientific goal skeleton from a research task before reading literature, web sources, data details, code, or prior results. Use at the start of AutoSciRub when Codex needs atomic, traceable goals that state what the task should…
원문 언어: 영어
Ground an AutoSciRub rubric skeleton in scientific literature and authoritative documentation. Use after rubric_skeleton.json exists when a research agent needs goal-centered methods, protocols, metrics, baselines, controls, robustness checks, and evidence…
원문 언어: 영어
Perform one AutoSciRub targeted revision round using failed executable-rubric criteria and criterion-level verification feedback. Use when Codex needs to update a research artifact by adding missing experiments, comparisons, evidence, analysis, figures,…
원문 언어: 영어
Build a lightweight task-visible data and resource profile for AutoSciRub. Use after rubric skeleton and literature grounding when Codex needs to inspect available files, datasets, code, schemas, units, labels, tools, constraints, and goal feasibility before…
원문 언어: 영어
README를 불러오지 못했습니다. 아래의 저장소 Skill 목록은 계속 이용할 수 있습니다.