677 件 ・ 関連度順
概要と使いどころ
Create well-structured GitHub issues following the Epic > Feature > Task/Bug hierarchy. Uses GitHub issue types (not labels) and relationships to connect related issues. Invoke with /github-issue.
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。
Generates automated test oracles to verify correct software behavior. Creates assertion-based oracles (expected values), property-based oracles (invariants), differential oracles (comparing implementations), and metamorphic oracles (input transformations). Use when you need to generate assertions for test cases, identify invariants that should always hold, compare new vs legacy implementations, create metamorphic test relationships, validate function correctness, or improve test coverage with better verification strategies. Supports Python (pytest, unittest, hypothesis) and Java (JUnit, property testing).
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。
Generate test cases using metamorphic testing by applying transformations based on metamorphic properties. Use when you need to expand test suites, test programs without oracles, validate mathematical or algorithmic properties, or detect subtle bugs through input-output relationships. The skill takes a program, original test cases, and metamorphic properties as input, generates new test cases by applying transformations, executes tests, verifies outputs satisfy properties, reports violations and anomalies, and outputs an expanded test suite with property coverage summary. Supports multiple programming languages and property types.
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。
Performs abstract interpretation to produce summarized execution traces and high-level program behavior representations. Highlights key control flow paths, variable relationships, loop invariants, function summaries, and potential runtime states using abstract domains (intervals, signs, nullness, etc.). Use when analyzing program behavior, understanding execution paths, computing loop invariants, tracking variable ranges, detecting potential runtime errors, or generating program summaries without concrete execution.
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。
Select, build, and validate Blender deformation and motion-control systems including Simple Deform, Curve, Lattice, Mesh Deform, Shrinkwrap, Surface Deform, Armature, shape keys, hooks, constraints, and drivers. Use when an object must bend, twist, taper, follow a path, conform to a surface, deform smoothly, articulate, or move through controlled mechanical relationships.
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。
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.
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。
Evaluate, compare, and manage vendor relationships. Trigger with "evaluate this vendor", "compare vendors", "vendor review", "should we renew", "RFP", or when the user is making procurement or vendor decisions.
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。
| Type-safe ORM for Cloudflare D1 databases using Drizzle. Use when: building D1 database schemas, writing type-safe SQL queries, managing migrations with Drizzle Kit, defining table relations, implementing prepared statements, using D1 batch API, or encountering D1_ERROR, transaction errors, foreign key constraint failures, or schema inference issues.
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。
Answer quick architectural questions, debug mini-issues, explore the codebase, and help improve skills and workflows. Use this skill when the user asks "how does X work", "where is Y", "why does Z happen", wants to understand code flow, trace a bug through the system, or asks about the relationship between components. Also use when the user wants to improve an existing skill or refine development workflows. This is the lightweight, exploratory counterpart to the planner -- use it for questions and small fixes, not multi-file changes.
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 the big picture around a topic or software repository by identifying its boundaries, layers, actors, components, relationships, flows, history, fault lines, and open questions, then explain how the pieces fit together and where to look next. Use when a user asks to understand a whole field, domain, technology, ecosystem, industry, codebase, architecture, unfamiliar repo, or phrases such as "give me the big picture", "map the landscape", "how does this all fit together?", "help me get oriented", or "what am I missing?"
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。
Build structured knowledge graphs from unstructured text by extracting entities, mapping relationships, generating graph triples, and visualizing the result. Use when the user requests knowledge graph creation or provides relevant inputs for this workflow.
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。
Design normalized database schemas with tables, relationships, indexes, and constraints for any application domain. Use when the user requests database schema design or provides relevant inputs for this workflow.
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。
Perform systematic exploratory data analysis to understand dataset structure, distributions, relationships, and anomalies before modeling. Use when a dataset is new, its quality is unknown, or the user requests open-ended profiling; use data-analysis instead for a defined hypothesis or decision question.
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。
Think and work like an expert Medicinal Chemist. Use when a task calls for Medicinal Chemist judgment. Reasons from structure-activity relationships, lipophilicity and unbound-fraction physicochemistry, synthetic accessibility, and target-product-profile multiparameter optimization through LLE/Fsp3/QED scoring, FEP+/Glide docking validated against co-crystal and SPR data, ELN-tracked LC-MS/NMR synthesis, and DMPK panels (microsomal CL, Caco-2 efflux, hERG, CYP) while treating PAINS and aggregation assay artifacts, biochemical-versus-cellular potency gaps, reactive-metabolite soft spots, and freedom-to-operate cliffs as first-class failure modes.
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。
Think and work like an expert AI Researcher. Use when a task calls for AI Researcher judgment. Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchmark contamination, spurious correlations, and reward-model overoptimization as first-class failure modes.
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。
Track thought leaders and industry voices across LinkedIn, Twitter, and YouTube. Monitor publishing cadence, content themes, engagement patterns, and audience growth for competitive positioning and relationship-building intelligence.
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。
Track media coverage, press mentions, journalist activity, and industry narrative across news outlets, Twitter, and LinkedIn. Ideal for PR teams monitoring earned media, tracking campaign impact, and identifying journalist relationships.
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。
Research potential partners by analyzing company profiles, product fit, market positioning, team background, and mutual connections. Combines firmographic data, content analysis, and social signals for partnership qualification and relationship mapping.
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。
Find cross-database references between NCBI databases using Biopython Bio.Entrez (ELink). Use when navigating gene to protein/structure, sequence to publication, PubMed to GEO, BioProject to SRA runs, or discovering all link relationships for a record. Covers linkname semantics, cmd= variants, asymmetric link warnings, neighbor_history for >200 input IDs, and per-database link tables.
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 and exploration of RNA-seq count matrices before differential expression. Check for outliers, batch effects, and sample relationships. Use when assessing count matrix quality before DE 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。
Designs and analyzes combinatorial CRISPR screens covering paired-Cas9 (Big Papi, Najm 2018), enhanced AsCas12a multiplex (enCas12a, DeWeirdt 2021), in4mer 4-guide-array Cas12a (Esmaeili Anvar N et al 2024 Nat Commun 15:3577) and the Inzolia paralog-pair library, paralog-buffering detection (Dede 2020 Genome Biol; Thompson 2021 Cell Reports 36:109597), genetic-interaction (GI) scoring as observed_double_LFC minus expected_additive_double_LFC, synthetic-lethal and synthetic-rescue interaction interpretation, the half-of-essentiality buffered by paralogs phenomenon, multiplex screen statistical analysis with MAGeCK MLE interaction terms, and the relationship to single-cell combinatorial Perturb-seq. Use when designing a paralog or pathway-pair screen, choosing between paired-Cas9 (Big Papi) and Cas12a multiplex (Inzolia), interpreting genetic interaction scores, identifying synthetic-lethal targets for drug development, or scaling beyond single-gene CRISPR screens.
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。
Build weighted gene co-expression networks to identify modules of co-regulated genes and relate them to phenotypes using WGCNA and CEMiTool. Detects hub genes and module-trait relationships from bulk or single-cell expression data. Use when finding co-expression modules, identifying hub genes, or relating gene networks to clinical or experimental variables.
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。
Batch effect correction for CRISPR screens covering ComBat empirical-Bayes, RUV, SVA, control-sgRNA normalization, and the model-based alternative of including batch as a covariate in MAGeCK MLE or Chronos. Covers screen-specific batch sources (passage cohort, library lot, infection day, sequencing run, Cas9 lot, FBS lot), PCA + variance-decomposition diagnostic to decide if correction is needed, when correction harms biology by over-correcting condition into batch, limma removeBatchEffect for visualization-only correction, and relationship to multi-condition design matrices. Use when combining screens for joint analysis, when passage cohort confounds biology, when DepMap-style panels need Chronos with batch covariates, when picking ComBat vs RUV, or when correction harms biology and should be replaced with explicit covariate modeling.
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。
ESM2 protein language model for sequence scoring, embeddings, and plausibility checks. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai1-structure-prediction or boltz-structure-prediction. For QC thresholds, use protein-design-qc.
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。