287 件 ・ 関連度順
概要と使いどころ
Design and implement adaptive testing systems using Item Response Theory (IRT). Use when working with computerized adaptive tests (CAT), psychometric assessment, ability estimation, question calibration, test design, or IRT models (1PL/2PL/3PL). Covers test algorithms, stopping rules, item selection strategies, and practical implementation patterns for K-12, certification, placement, and diagnostic assessments.
日本語の概要は準備中です。原文の説明を表示しています。
协作校准 / 认知校准 / 问题脑暴：当用户有模糊感受说不清问题、方案越补越复杂、想挑战假设、 想重新定义问题、想知道成熟领域里怎么叫这个问题时使用。 可用中文唤起："帮我想想""先聊一下""一起脑暴""我感觉有问题但不清楚是什么" "先别执行，帮我看清问题""挑战我的假设""这个方案是不是想错了""帮我做认知校准" "双向钢人""钢人论证一下""正反最强论证，给我明确判断"。 也适用于：用户直接说"帮我做 X 功能""接入 Y 平台"但背景复杂、或对话早期感觉方向可能跑偏时， AI 主动识别并建议进入脑暴模式。 这里的“挑战假设”主要指问题定义、目标、约束和领域定位层面的假设；如果问题已确认且用户已有具体方案、 计划、架构或决策要压力测试，应转用 grill-me。不用于翻译、摘要、格式整理、单文件小改等简单执行任务。
日本語の概要は準備中です。原文の説明を表示しています。
复杂探索资产化 / Complex Exploration：当用户面对复杂、不确定、多轮迭代的产品策略、Roadmap、商业化定价、竞品定位、复杂 PRD 前置探索、项目复盘或方法论沉淀任务时使用。它先判断任务类型，暴露隐含假设，重构真正问题，规划探索路径和中间产物，并在结束后沉淀认知、结构、方法论、工具和影响力资产。不用于简单润色、翻译、摘要、明确执行任务；问题只需早期认知校准时优先用 ai-collaboration-calibration，已有方案要压力测试时用 grill-me，系统专题研究用 research-topic-compiler。
日本語の概要は準備中です。原文の説明を表示しています。
决策调研 / Decision-Driven Research：当用户面对一个具体决策需要找信息时使用——「有没有现成方案」 「怎么接入 X 平台」「这个技术可行吗」「业界怎么做 Y」「选 A 还是 B」「桌面端应该怎么定位」 「高级版和基础版怎么拉开差异」「这个产品方向对不对」。 核心行为：先框定研究层级和问题类型，再锚定决策问题，枚举竞争假设，主动找反对证据， 用排除逻辑给出有立场的结论。支持技术选型、产品策略、商业判断、竞品定位等所有需要做决定的调研。 可用中文唤起：「帮我调研」「有没有现成方案」「这个怎么接」「技术上可行吗」「帮我选一个」 「这个产品方向对不对」「我们应该怎么定位」「行业怎么做」。 与 research-topic-compiler 的边界：需要最终选择、推荐、排除理由、置信度和颠覆条件时用这个； 如果目标是长期学习、候选池沉淀或 Research Project，用 research-topic-compiler，再把 Candidate Backlog 交回本 Skill 做最终决策。 只有发现一个会实质改变结论、可研究且可关闭的证据 gap 时，才向 research-topic-compiler 发出精确 Return Request。 不用于：问题还没定义清楚时（先用 ai-collaboration-calibration L4-fuzzy 脑暴）。
日本語の概要は準備中です。原文の説明を表示しています。
设计脑暴 / 实现前方案校准：当用户想把已基本成立的想法、功能方向或产品问题，在写 PRD、画 mockup 或进入开发计划前，先比较方案、确认取舍、对齐 UI/视觉约束，并收敛成可执行设计 spec 时使用。 可用中文唤起：“先脑暴一下方案”“先不要写 PRD，帮我设计几种路径”“参考 brainstorming 把这个需求变成设计 spec” “实现前先讨论设计”。问题还没定义清楚时先用 ai-collaboration-calibration；已有方案要压力测试时用 grill-me； 直接写 PRD 时用 prd-architect；grill-me 返回精确设计 gap 时，本 Skill 只输出 Design Delta。
日本語の概要は準備中です。原文の説明を表示しています。
方案拷问 / 压力测试：当用户有一个产品方案、架构设计、计划或决策，想被连续追问、反方挑战、 压测取舍和失败模式时使用。可用中文唤起：“拷问我的方案”“压力测试这个设计”“帮我问 hard questions” “这个方案哪里会翻车”“grill me”。目标是一问一答把决策树走清楚，不是直接替用户写最终方案。 跨 Skill 运行时只输出 Challenge/Critic Handoff，并把一个 gap 返回最小责任节点；不重写完整方案。 如果用户还不知道真正问题是什么，先用 ai-collaboration-calibration；如果用户要标准 PRD 交付准备度评审， 用 prd-review。
日本語の概要は準備中です。原文の説明を表示しています。
Use when loading, listing, composing, or validating graded evaluation rubrics — PASS/WARN/FAIL grading with weighted criteria and balanced PASS/FAIL anchor examples. Triggers on /mk:rubric, "load rubric", "compose rubric preset", "validate rubric", or evaluator-style code review that needs anchor-grounded judgments.
日本語の概要は準備中です。原文の説明を表示しています。
Quality control for flow, spectral, and mass cytometry - time-based anomaly cleaning (flowAI, flowCut, PeacoQC, flowClean), margin/boundary event removal, signal-drift detection, dead-cell exclusion, CyTOF Gaussian/DNA/event-length checks, instrument calibration/standardization (MESF, CS&T, peak-2), and batch-level outlier flagging. Use when assessing acquisition quality, choosing a cleaning tool, ordering QC relative to compensation, deciding margin removal before density-based steps, or flagging problematic samples before clustering or differential analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Delimits putative species boundaries from molecular data within the de Queiroz 2007 unified-lineage framework using ASAP (Puillandre 2021 successor to ABGD), mPTP C++ (Kapli 2017 successor to bPTP; bPTP is Python NOT R), GMYC single/multi-threshold (Pons 2006; Fujisawa 2013), multilocus BPP v4 with prior calibration from data (NOT defaults; Yang 2015), SNAPP + BFD* for SNP delimitation, DELINEATE (Sukumaran 2021) speciation-process modeling to address Sukumaran & Knowles 2017 PNAS critique that MSC delimits structure not species, integrative-taxonomy congruence (Padial 2010; Carstens 2013), Dsuite for introgression testing before sister claims (Malinsky 2021), and Meyer & Paulay 2005 barcoding-gap-absence caveat. Use when delineating species from DNA barcoding data, resolving cryptic complexes, choosing among ASAP/mPTP/BPP/DELINEATE, calibrating BPP priors, distinguishing introgression from ILS, or applying the Sukumaran-Knowles oversplitting correction.
日本語の概要は準備中です。原文の説明を表示しています。
Detects differential alternative splicing between conditions using rMATS-turbo (binomial LRT on junction counts), leafcutter (Dirichlet-multinomial GLM on intron clusters), MAJIQ V3 deltapsi/HET (Bayesian posterior on LSVs), SUPPA2 (empirical-null on TPM-derived PSI), or Shiba (junction-imbalance-corrected, 2025 SOTA at low coverage). Reports FDR-corrected significance and delta PSI effect sizes. Tools differ in statistical model, annotation dependence, calibration regime, and replicate-count requirements. Use when comparing splicing patterns between treatment groups, tissues, or disease states.
日本語の概要は準備中です。原文の説明を表示しています。
Processes eDNA metabarcoding from raw paired-end reads to species tables, navigating ASV (DADA2, UNOISE3) vs OTU (swarm v2) decision (Callahan 2017 vs Schloss multi-copy-16S critique), marker/primer choice (Leray COI, MiFish 12S, 515F/806R 16S, ITS2) with primer-specific bias, OBITools3 v3 command-name break (obi stats plural; .tar.gz taxonomy), tag-jumping with dual-indexing (Schnell 2015; NovaSeq 10x MiSeq), decontam as screening-not-classifier (Davis 2018), read-counts-not-abundance critique (Lamb 2019), site-occupancy modeling (Ficetola 2015), Naive-Bayes calibration limits (Bokulich 2018), and eDNA decay (Strickler 2015). Use when going from raw eDNA FASTQ to species tables, picking marker + denoising pipeline, deciding whether read counts represent abundance, applying occupancy modeling, configuring OBITools3 v3, or interpreting decontam output. Not for clinical 16S microbiome (see microbiome/amplicon-processing).
日本語の概要は準備中です。原文の説明を表示しています。
Map N6-methyladenosine (m6A) RNA modifications at single-nucleotide resolution using miCLIP (Linder 2015), miCLIP2 + m6Aboost machine learning (Kortel 2021), GLORI (Liu 2023, antibody-free chemical conversion), DART-seq (Meyer 2019, APOBEC1-YTH fusion), m6Anet (nanopore direct RNA), or MeRIP-seq with calibration. Use when distinguishing antibody-based from antibody-free m6A detection methods, applying the DRACH motif constraint, reconciling cross-method disagreements (DART 44% in DRACH vs GLORI), or detecting m6Am at the cap.
日本語の概要は準備中です。原文の説明を表示しています。
Identifies essential genes from CRISPR-Cas9 fitness screens using BAGEL2 (Kim & Hart 2021 Genome Med), a Bayesian classifier scoring per-gene Bayes Factors via log-likelihood ratios over per-sgRNA fold changes, calibrated against CEGv2 core-essentials (Hart 2017 G3, ~684 genes) and NEGv1 non-essentials (Hart 2014, ~927 genes). Covers the fc + bf + pr workflow, the linear-extrapolation improvement over BAGEL1 truncation, multi-target off-target correction, tumor-suppressor sensitivity (BAGEL2 detects enrichment), and BF calibration (BF >6 ≈ 90% posterior per Hart 2017; ~5% FDR by BAGEL convention). Use when classifying essential vs non-essential genes, calibrating BAGEL2 thresholds against PR curves, identifying tumor suppressors alongside essentials, comparing BAGEL2 hits to MAGeCK / drugZ, or generating publication-quality essentiality calls.
日本語の概要は準備中です。原文の説明を表示しています。
Prioritizes rare-disease variants from trio/quad WES/WGS with de novo (DeNovoGear, Triodenovo), compound-heterozygous phasing (WhatsHap), mosaic VAF tiering, phenotype-driven ranking (Exomiser, Phen2Gene, AMELIE), ClinGen gene-disease validity gating, and ACMG SF v3.2 secondary findings reporting. Use when running diagnostic exome / genome pipelines, identifying candidate Mendelian disease genes, screening for incidental findings, or auditing VUS reclassification cycles. The ACMG/AMP classification framework (PVS1 decision tree, Pejaver PP3/BP4 calibration, Tavtigian point system) is in clinical-databases/acmg-classification.
日本語の概要は準備中です。原文の説明を表示しています。
Calculates tumor mutational burden from WES/WGS/panel data with Friends of Cancer Research harmonization equations, per-assay calibration (FDA 10/Mb = 7.8 TSO500 = 8.4 OncomineTML), synonymous/indel/germline filtering, hypermutator tiering, blood TMB, and integration with HLA-LOH and neoantigen quality (Luksza 2017 fitness). Use when assessing ICI eligibility under tumor-specific cutoffs (McGrail 2021), comparing tissue vs bTMB, or auditing TMB-H reporting against ESMO 2024 and FDA pembrolizumab pan-tumor 2020.
日本語の概要は準備中です。原文の説明を表示しています。
Constructs and validates polygenic risk scores using LDpred2-auto, SBayesRC, MegaPRS, PRS-CS, PROSPER, MUSSEL, BridgePRS, JointPRS, PRSmix, or PGS Catalog Calculator with ancestry-aware reference panels (HapMap3, UKB-LD), ancestry-conditional calibration, and PRS-RS reporting standards. Use when computing PRS for cohorts, applying absolute-risk transformation, assessing cross-ancestry portability (Martin 2017 / Ding 2023 continuous ancestry), or auditing PRS manuscripts against the 22-item PRS-RS reviewer checklist.
日本語の概要は準備中です。原文の説明を表示しています。
Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.
日本語の概要は準備中です。原文の説明を表示しています。
Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness
日本語の概要は準備中です。原文の説明を表示しています。
Use when shaping an engineering hiring loop — stages, take-home vs live, calibration, bar-raiser, signal-vs-noise audit. Triggers on 'design our interview loop', 'audit our hiring bar'.
日本語の概要は準備中です。原文の説明を表示しています。
[Debugging] Use when analyzing or optimizing performance bottlenecks: database queries, N+1 fan-out, indexing, API latency, memory/GC, concurrency and pool saturation, algorithmic complexity (O(n²)), network/protocol round trips, frontend rendering and Core Web Vitals, caching, and distributed/resilience paths. Calibration constants and domain laws (latency ladder, Little's Law, utilization knee, CWV thresholds, symptom→cause triage) live in references/performance-knowledge.md.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a user edits or criticizes generated copy and you need to extract durable writing-style rules instead of merely remembering surface words.
日本語の概要は準備中です。原文の説明を表示しています。
GStack CSO method for broad infrastructure-first security posture review, threat areas, severity calibration, and safe remediation scope.
日本語の概要は準備中です。原文の説明を表示しています。
Draft and revise evidence-grounded academic manuscripts with adaptable author preferences. Use for section writing, implementing structural edits, claim calibration, citation-integrated prose, prose cleanup, standalone review excerpts, and LaTeX template migration. Use paper-review for critique or author responses, and paper-figures-tables for final visual artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Knowledge base from the NIST/SEMATECH e-Handbook of Statistical Methods (NIST HB 151) — the practical statistics reference for engineering, metrology, and quality. Use for: exploratory data analysis and the four univariate assumptions (4-plot); measurement process characterization including bias/precision, calibration designs, gauge R&R, and ISO/GUM uncertainty budgets; production process characterization (stability vs. capability); process modeling and regression (LS/WLS/NLS/LOESS); design of experiments (screening, fractional/factorial, response-surface, Taguchi); statistical process control (Shewhart/CUSUM/EWMA charts, capability indices, acceptance sampling); product/process comparisons (hypothesis tests and confidence intervals for 1/2/3+ groups, ANOVA, multiple comparisons); and reliability (lifetime & repair-rate models, accelerated testing, reliability growth). Scope limits: this is applied frequentist statistics for measurement and quality — it does NOT reproduce the per-distribution formula galleries, worked case studies, datasets, plot images, or Dataplot/R code of the original web Handbook (those are described, not copied); it is thin on modern machine learning, Bayesian methods beyond conjugate reliability priors, time-series/forecasting, and Bayesian experimental design.
日本語の概要は準備中です。原文の説明を表示しています。