「sci」の検索結果

Apply systematic root cause analysis and debugging methodologies to diagnose and fix bugs, test failures, and unexpected behavior. Use when encountering production issues, investigating test failures, diagnosing performance problems, tracing error sources through call stacks, analyzing logs and stack traces, reproducing inconsistent bugs, debugging race conditions, investigating memory leaks, or applying scientific method to problem-solving before proposing fixes.

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。

Route communication modes, learning workflows, retrospectives, output discipline, and perspective shifts to focused productivity skills.

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。

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

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。

Strict routing mode for prompts prefixed with `(best)`. USE FOR: any turn where the user explicitly wants the safest, smallest-context, highest-discipline execution path. This skill must route into context-budget-guard first, then continue into the task-specific 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。

Idiomatic Go - package and interface design, error wrapping, table-driven tests, generics, the modern standard library (slices/maps/cmp/errors.Join), current syntax, and logging discipline. Use when writing, reviewing, or refactoring any Go code, especially code drifting toward Java/Spring shapes (deep layer trees, generic repositories, heavy frameworks) - even if the user never says "idiomatic". Distilled from spf13/go-skills and adapted to this repo.

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。

Orchestrator for spec-driven development (SDD) — the discipline of writing executable specs before code, with a constitution above them and a hard cross-check gate before implementation. Mirrors GitHub Spec Kit / AWS Kiro slash-command shape. Routes /constitution, /specify, /clarify, /plan, /tasks, /analyze, /implement to the right leaf skill. Load when the user says "spec-driven development", "SDD", "specs-first workflow", "run the spec loop", "/specify a feature", "/plan from this spec", "do spec-driven for this", "GitHub Spec Kit workflow", "Kiro workflow", or invokes any SDD-style slash command. Single entry point for all SDD workflows.

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 this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer 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 before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.

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。

Simulate transcription factor perturbation effects on cell state in silico with CellOracle and Dynamo, and predict transcriptional responses to genetic perturbations with GEARS, scGen, and CPA. Covers the direction-not-magnitude principle, local-linear validity, the GRN/velocity error it inherits, baseline discipline (mean and additive baselines), and the validation gap. Use when predicting TF knockout or overexpression effects, ranking driver TFs for fate transitions, or planning perturbation experiments. For GRN construction see multiomics-grn; for experimental Perturb-seq see single-cell/perturb-seq.

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。

Analyzes alternative splicing at single-cell resolution. The first decision is library chemistry — 10X 3' is fundamentally limited (RT primes from poly-A, R2 falls in 3' UTR, <0.1 junction read per cell per AS event). Plate-based full-length methods (Smart-seq3, FLASH-seq, VASA-seq, STORM-seq) and single-cell long-read (MAS-Iso-seq, scISOr-Seq2) are the chemistries that give per-cell isoform structure. Tools include MARVEL (R, Smart-seq integrated), BRIE2 (Bayesian PSI with regulatory features and ELBO_gain test), scQuint (junction-cluster, plate-based; not for 10X), SpliZ (annotation-free Z-score), Psix (graph-smoothness regulated AS), and Sierra (alternative polyadenylation, often confused with AS). Use when analyzing isoform usage in scRNA-seq, identifying cell-type-specific splicing, or determining whether scRNA-seq chemistry supports splicing analysis at all.

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。

Audit required bioinformatics command-line tools against Lmod or Environment Modules on Linux HPC clusters, resolve executable and version requirements, and reproducibly deploy missing software through a site-approved EasyBuild, Spack, Bioconda/micromamba, Apptainer, binary, or source-build workflow. Use when Codex must inspect module availability, diagnose a missing or wrong-version bioinformatics tool, install scientific software on Slurm/PBS clusters, publish or validate modulefiles, or produce an auditable and rollback-ready cluster software deployment.

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 carrier owner, CFO, or controller asks how to build an annual budget, monthly P&L model, cash flow forecast, scenario plan, or break-even analysis for a trucking operation. Covers revenue modeling, cost structures, capital planning, and the discipline of tracking actuals vs budget.

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。

The gate and path for any question an agent wants Arman to decide. Use when about to ask him anything, ending a turn on a question for him, writing 'needs Arman's decision', marking work blocked on him, or on /ask-arman. NOT for a step only he can perform (use a guided session).

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。

Expert knowledge of academic writing standards for peer-reviewed papers, including citation integrity, style compliance, clarity, and scientific writing best practices. Use when reviewing or editing academic manuscripts, papers, or research documentation.

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。

Search academic paper repositories (arXiv, Semantic Scholar) for scholarly articles in physics, mathematics, computer science, quantitative biology, AI/ML, and related fields

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。

Comprehensive toolkit for writing high-quality computer science research papers (conference, journal, thesis). Provides narrative construction guidance, sentence-level clarity principles (Gopen & Swan), academic phrasebank, CS-specific conventions, and section-by-section quality checklists. Use when assisting with academic paper writing, revision, or structure planning across all stages from drafting to submission.

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 writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manuscript, research writing, journal submission, or needs help with academic structure, formatting, or revision.

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。

Abracon MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Abracon timing devices, crystals, oscillators, RF components, or AbraconHandler.

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。

The science of learning through controlled experimentation. A/B testing isn't about picking winners—it's about building a culture of validated learning and reducing the cost of being wrong. This skill covers experiment design, statistical rigor, feature flagging, analysis, and building experimentation into product development. The best experimenters know that every test, positive or negative, teaches something valuable. Use when "a/b test, experiment, hypothesis, statistical significance, sample size, feature flag, variant, control, treatment, p-value, conversion rate, test winner, split test, experimentation, testing, statistics, feature-flags, hypothesis, growth, optimization, learning, validation" mentioned.

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 you need to apply Java concurrency best practices — including thread safety fundamentals, ExecutorService thread pool management, concurrent design patterns like Producer-Consumer, asynchronous programming with CompletableFuture, immutability and safe publication, deadlock avoidance, virtual threads and structured concurrency, scoped values, backpressure, cancellation discipline, and observability for concurrent systems. Part of the skills-for-java project

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。

Rust のコードを書く・直す・レビューするときに使う。所有権、借用、Clone/Copy derive、文字列型 (`String`, `&str`, `Cow`, `'static str`) の選び方を、安易な複製や過剰な lifetime 固定に寄せず、実際のデータ所有者と呼び出し境界に合わせて判断するためのスキル。

実装要求に、要求が答えていない設計判断が残るとき、または誤りが後段で黙って通る変更を扱うときに使う。具体的には、API・設定の与え方・データモデル・新しい型や概念・責務や層境界を決める必要がある、複数の実現方法から選ぶ設計判断がある、変更範囲を事前に局所化できない、認可・公開範囲・データ消失・外部送信のように誤りをテストや型検査で検出しにくい、のどれかに当たるタスクで発火する。原因と修正箇所が特定済みで期待結果と検証方法が明確な修正、既存パターンの適用、機械的な rename、CI/CD・ドキュメント・設定値・依存バージョンだけの変更では使わない。要求を出典付きの決定と質問に分解する解釈ゲート、判断の重さに応じた階層(直接実装 / 軽量 / 標準)の判定、subagent への分担、実物差分での検収、独立レビューをフェーズ順に管理するスキル。

テストの追加・修正・削除、または実装後の検証方針を判断するときに使う。タスクごとに反射的な回帰テストを増やさず、守るべき仕様、不安な仕様、実際に使われる経路、事前条件と事後条件を中心にテストを設計するためのスキル。

ドメインモデル、可視性、操作可能性、不変条件、層境界、API 設計に関わる実装時に使う。不正な状態や誤った呼び出し方を、型、関数の境界、ドメイン語彙で表し、正しい使い方が自然になる設計へ寄せるためのスキル。