微信扫一扫把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。
Systematic review Phase 5 — Data extraction form design, execution, missing data handling, and outcome harmonization for EM/critical care SRs. Use when the user needs an extraction form, help with mis…
Non-meta-analytic synthesis methods per Cochrane Handbook Ch 12. Use when meta-analysis is not possible and alternative synthesis is needed. Three acceptable methods: summarizing effect estimates, com…
Prospective approaches to accumulating evidence per Cochrane Handbook Ch 22. Use when the user needs prospective meta-analysis (PMA), trial sequential analysis (TSA), cumulative meta-analysis, or livi…
Systematic review Phase 6 — Risk of bias assessment using RoB 2.0, ROBINS-I, QUADAS-2, QUIPS, and JBI tools for EM/critical care SRs. Use when the user needs to assess study quality, select the correc…
Systematic review Phase 10 — Living review maintenance, search updates, and new evidence integration for EM/critical care SRs. Use when the user wants to update their review with new evidence, set up …
>
You must use this when conducting PRISMA-standard systematic reviews, protocol development, or Risk of Bias assessment.
Search IEEE Xplore, arXiv, and Google Scholar for papers on a user-specified research topic, score verified candidates, and produce a sourced shortlist of up to ten papers. Use when the user asks for …
Systematic review Phase 8 — GRADE assessment and Summary of Findings for EM/critical care SRs. Use when the user needs to rate certainty of evidence, generate a Summary of Findings (SoF) table, apply …
Handle patient-reported outcomes (PROs) in systematic reviews per Cochrane Handbook Ch 18. Use when included studies use patient-reported outcomes like quality of life, pain, function, or symptom scal…
Systematic review Phase 2 — Protocol writing and PROSPERO registration for EM/critical care SRs. Use when the user needs a full PRISMA-P-compliant protocol, PROSPERO field mapping, timeline estimation…
Systematic review Phase 3 — Literature search, string construction, database translation, deduplication, and PRISMA-S compliance for EM/critical care SRs. Use when the user needs to build, test, or re…
Systematic review Phase 9 — PRISMA 2020 compliant manuscript writing for EM/critical care SRs with journal-specific formatting. Use when the user needs to write the full manuscript, any section (abstr…
Use when any workflow stage fails — simulation, analysis, plotting, post-processing, or environment setup — before proposing fixes
Create or refine TikZ figures for technical papers and slides. Use when Codex needs to add a new diagram, improve an existing figure, align a visual with manuscript notation, or iteratively compile an…
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable …
Structured interpretation of SR results per Cochrane Handbook Ch 15. Use when the user needs to interpret meta-analysis results, compute NNT, re-express SMDs, assess applicability, or draw conclusions…
Systematic review Phase 1 — PICO development and topic formulation for EM/critical care. Use when the user wants to define their research question, build a PICO(S) framework, identify eligibility crit…
Handle non-standard RCT designs in SRs per Cochrane Handbook Ch 23. Use when included studies include cluster RCTs, crossover trials, stepped-wedge designs, equivalence/non-inferiority trials, or mult…
Systematic review Phase 7 — Statistical synthesis, meta-analysis, and heterogeneity assessment for EM/critical care SRs with live R code execution. Use when the user needs to pool data, calculate effe…
Quality assurance and testing protocols for statistical software
Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Se…
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for populat…
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100…