スキルを探す

マシン上の git worktree とローカルブランチを横断で棚卸しし、マージ済みかを判定して安全に削除する。「worktree を整理して」「マージ済みブランチを消して」「worktree を全部リストして」等の依頼時、/worktree-audit 実行時に使用。境界: 単一 worktree の作成・片付け手順は context/worktree-guide.md、コードベースの監査は codebase-review。

Turn vague preferences about employers into criteria that can actually be used to choose between them: for each one, what would have to be seen to confirm it, whether it comes from firsthand experience or from an untested assumption, whether it is a must, a nice-to-have, or something to avoid, and which pairs of criteria pull against each other while both being treated as required, then test the set against real candidates. Use when a new graduate is working out what to select employers on, when someone who has decided to move needs criteria for where to apply, or when a stated axis like "a place I can grow" needs to be made checkable; do not use to recommend an industry, job, or employer, to score or rank candidates, or to judge someone's stated preferences.

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。

Explore possible next roles from a user's actual tasks, interests, and constraints, including adjacent roles and changes within their current workplace. Build evidence-linked career hypotheses, identify unknown duties and requirements, and propose small ways to test them. Use when someone does not know what work to pursue or asks what they could do beyond their current job; do not diagnose aptitude, rank careers, or predict salary or hiring success.

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。

Keep GPT-5.6 and other coding-agent work proportional to the request by locking scope, choosing the smallest sufficient implementation, matching verification to risk, and stopping when success is proven. Use for implementations, bug fixes, refactors, reviews, or maintenance where scope creep, speculative abstractions, unrelated cleanup, repeated test runs, unnecessary dependencies, or polishing beyond the request are risks.

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。

Shakes your mental models with critical rigor, challenges assumptions, exposes blind spots, and provides multi-perspective insights as a strict thinking mentor. Deliberately breaks format conventions to stimulate genuine cognitive discomfort. Use when you want to stress-test an idea, shake your mental model, ask to challenge my assumptions, find blind spots, deepen my thinking, or request critical review with phrases like yusaburi or what do you think of this plan.

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。

社員が申請したソフトウェア・SaaS・クラウドサービスの社内利用可否を、企業のIT/セキュリティ統制の観点から調査・評価するスキル。「〇〇のセキュリティ評価をして」「〇〇は社内で使っても大丈夫？」「このSaaSのセキュリティチェックをして」「新しいツールの導入審査をして」「〇〇と△△どちらが安全？」のような依頼で必ず使うこと。「セキュリティ」という言葉がなくても、特定のツール・サービスの社内導入可否・利用申請・リスク判断が話題になったら使う。Web検索で一次情報（プライバシーポリシー、利用規約、セキュリティホワイトペーパー、第三者認証）を収集し、6分野18項目のチェックリストに基づく3段階リスク評価付きの日本語レポート（Markdownファイル）と、ワークフロー（稟議）システムの承認コメント欄に貼れる短文サマリーを生成する。

有馬記念分析システムのアーキテクチャ/レイヤー境界レビュー。docs/ARCHITECTURE.md のレイヤー構成（commands / domain / repositories / models / features / constants / database / utils / types）に対し、レイヤーディレクトリの意味と配置、参照系(queries)と更新系(aggregates)の分離、DB 接続の注入可能性とテスト容易性、リッチドメインモデルの維持（commands 肥大・ドメイン貧血症）、重み・閾値の constants 単一定義、ファイル配置と命名語彙の一致、不要な抽象化、種別分岐のポリモーフィズム化、生成引数の凝集（5個以上は分割シグナル）を検証。純粋性・依存方向の逆流・DB 接続の生成箇所は lint が error で担保するため扱わない。Use when user says 'アーキテクチャレビュー', 'レイヤー境界チェック', 'review architecture', or '依存方向の確認'.

スコアリング / ML のドメイン正しさのレビュー。SCORE_WEIGHTS の単一定義と合計1.0・ドキュメント追随、スコアリングと ML の10要素の一致（手書きで並ぶ全箇所の同時更新）、未来情報リーク（as-of カットオフを通していない取得経路の新設）、値域0〜100とゼロ除算、データ欠損時の既定値、学習・予測の決定性と再現性、JRA 枠番割当規則、バックテスト指標（1位的中率・上位3頭精度・順位相関・ROI）の計算を検証。Use when user says 'スコアリングレビュー', 'review scoring', 'ML レビュー', 'スコア計算チェック', '特徴量チェック', or 'バックテスト検証'.

外部データ取得と取り込み経路のセキュリティレビュー。JRA 以外のホストへ取りに行かせない URL 検証（SSRF）、スクレイピングの作法（User-Agent・リクエスト間隔・タイムアウト）、外部由来 HTML/JSON を無検証で DB に入れない、クエリを Kysely で組み立て生の SQL 文字列を増やさないこと、CLI 由来のファイルパスの扱い、生成物（*.db / data/extracted-*.json / data/jra-page.html）と .env をコミットさせないことを検証。Use when user says 'セキュリティレビュー', 'review security', 'セキュリティチェック', 'SSRF確認', or 'SQLインジェクション確認'.

review-all を実行し、指摘内容をコードに反映、bun run c / bun run lint / bun test で自己検証し、CONVERGED/NOT_CONVERGED の収束判定付き完了レポートを /tmp/arima-review-fix-result.md に出力する。レビュー→修正→検証→レポートを一気通貫で行うスキル。スコープ引数は /review-all と同じ（wt / PR #N / vs:<branch> / range / ファイル列挙）。review-fix-loop からの自動呼び出し（mode=non-interactive）にも対応。Use when user says 'レビューして直して', 'review and fix', '自動修正', 'レビュー反映', or when invoked by review-fix-loop.

全 8 レビュースキル（arch/code/scoring/security/test/naming/recovery/comments）を並列実行し、統合レポートを出力するオーケストレーションスキル。レビュー範囲は引数で指定可能（wt=作業ツリー / PR #N / pr:N / vs:<branch> / git range / ファイル列挙、デフォルトは比較ブランチとの差分）。Use when user says '全レビュー実行', 'review all', '一括レビュー', '総合チェック', 'PR レビュー', or '<branch> との差分レビュー'.

テスト品質のレビュー（bun:test）。`bun test` の全通過、エンティティのビルダー直接検証と createTestDb による実 SQLite E2E の使い分け、実ネットワーク（JRA）非依存、回帰テストの存在（ImportData の一致条件・枠番の JRA 割当規則・生年計算）、回帰テストの削除/skip 化の禁止、新機能・バグ修正へのテスト追随、契約の検証 vs 実装詳細への過剰結合、console spy と一時ファイルの後始末を検証。Use when user says 'テストレビュー', 'review test', 'テスト品質チェック', or 'カバレッジ確認'.

Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL fingerprint stability, compare a spoofed profile against a real browser, or find out whether a browser profile is self-consistent.

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。

Check whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent fingerprint, using liarjs as a library against a Page you already have - navigator.webdriver, HeadlessChrome tokens, worker versus main-thread identity, patched-API integrity, WebGL versus WebGPU GPU identity. Use when asked whether an automated browser looks like a normal one, when a headless setup or a stealth plugin's effect needs measuring rather than assuming, or when an assertion on fingerprint quality belongs in a test suite.

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。

Compares Hi-C contact maps between conditions across the right scale -- differential bin-pair contacts (multiHiCcompare, diffHic), differential A/B compartments (dcHiC), differential TAD boundaries (delta insulation), and differential loops (diffloop, DiffHiChIP) -- with distance-stratified between-sample normalization, replicate-aware NB-GLM FDR, HiCRep SCC reproducibility gating, and CNV correction for cancer/aneuploid samples. Use when comparing Hi-C between treatment and control, finding differential contacts/compartments/boundaries/loops, normalizing two maps of unequal depth, choosing a replicate-aware test, gating replicates with SCC, or correcting copy-number artifacts before a tumor-vs-normal comparison.

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 set operations on genomic intervals - intersect (-wa/-wb/-wo/-wao/-loj/-c/-v/-u), subtract (-A), merge (-d, -c/-o), complement, cluster, multiinter, unionbedg, map, and groupby - with bedtools (CLI) and pybedtools/pyranges/bioframe (Python). Covers the sorted-input contract and the -sorted chromosome-order footgun, reciprocal/fractional overlap (-f/-F/-r/-e) and the A-vs-B asymmetry, -split for spliced/BED12/BAM features, and jaccard/fisher as mechanics only. Use when finding overlapping or unique regions between BED/peak/feature files, building consensus peaksets, removing blacklisted regions, transferring annotation values onto intervals, or computing interval-set similarity; route overlap-significance testing to overlap-significance.

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。

Tests whether two genomic interval sets overlap (colocalize) more than expected by chance using a permutation test against a structured-genome null model. Covers bedtools fisher (analytic 2x2 screen), bedtools shuffle + jaccard permutation, GAT (isochore/GC-conditioned simulation with FDR), regioneR (flexible permutation, randomizeRegions vs circularRandomizeRegions, localZScore), LOLA (universe-relative Fisher against a region database), and GREAT/rGREAT (regulatory-domain binomial + hypergeometric for ontology-from-regions). Stresses the universe/background choice, matched background, blacklist exclusion, and multiple-testing control. Use when asking whether peaks/regions are enriched at enhancers/TFBS/features, scoring region-set colocalization or region-set enrichment, comparing CNV/SV concordance, or turning an overlap count into a defensible p-value.

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。

Compare cell-type composition and spatial features across conditions in IMC/MIBI cohorts with the patient as the experimental unit, covering pseudoreplication, per-patient aggregation, mixed models, compositional (Dirichlet/scCODA) differential abundance, diffcyt, per-image-to-patient spatial differential testing (SpaceANOVA), batch covariates, and FDR. Use when testing whether a cell type or spatial niche differs between groups, avoiding cell-level pseudoreplication, choosing a differential-abundance method, or correctly powering an IMC cohort comparison.

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。

Analyze spatial cell-cell interactions, neighborhoods, and niches in IMC/MIBI data with squidpy and imcRtools, covering neighborhood-enrichment permutation nulls, the abundance-vs-density confound, inhomogeneous Ripley's K, cellular-neighborhood discovery, graph-construction (contact vs proximity), and edge effects. Use when testing whether cell types co-locate, choosing a spatial null, building a neighbor graph, discovering tissue niches, or deciding whether a spatial pattern is real or a density/segmentation artifact.

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 differential expression on bulk RNA-seq count data with DESeq2's negative-binomial GLM, Wald and LRT testing, apeglm/ashr/normal LFC shrinkage, independent filtering, Cook's outlier handling, VST/rlog transforms, and design formulas including paired, batch, and interaction terms. Use when running bulk DE, choosing DESeq2 over edgeR or limma-voom, building a paired or interaction design, applying LFC shrinkage for ranking or GSEA, choosing Wald vs LRT, troubleshooting padj=NA, picking VST vs rlog, importing salmon/kallisto via tximport, or analyzing prokaryotic RNA-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。

Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against testing on a batch-corrected matrix, the choice between SVA/RUVg/RUVs/RUVr, the confounding non-identifiability problem, the single-cell boundary (Harmony/MNN are NOT for bulk), and the Goh 2017 harmonization critique. Use when designing a DE analysis with batch structure, troubleshooting batch-dominated PCA, choosing ComBat vs ComBat-seq, handling unknown batch via SVA, integrating across studies, or deciding when (rarely) to subtract batch.

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。

Compare gene co-expression and regulatory networks between biological conditions to find rewired relationships using DiffCorr, DiffCoEx, DINGO/iDINGO, and CoDiNA. Covers the differential-connectivity-is-not-differential-expression distinction, the pairwise multiple-testing explosion, marginal vs partial (direct) rewiring, and the underpowered-rewiring failure mode. Use when comparing co-expression networks between disease vs control, treatment, or developmental stages, or finding hub genes that rewire without changing mean expression. For single-condition modules see coexpression-networks; for differential expression of means see differential-expression/de-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。

Differential abundance (DA) and differential state (DS) analysis for flow and mass cytometry - tests which cell populations change in frequency or marker expression between conditions using diffcyt (edgeR/voom/GLMM for DA, limma/LMM for DS), with cydar, CITRUS, and compositional methods (sccomp, scCODA, DCATS) as alternatives. Covers the sample-is-the-experimental-unit principle, design/contrast and mixed-model formulas, compositionality of cluster proportions, and FDR across clusters. Use when comparing populations between groups, choosing a DA method, handling paired/batch designs, or deciding whether compositional correction is needed.

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。

Unsupervised clustering and cell-type identification for high-dimensional flow, spectral, and mass cytometry - FlowSOM, PhenoGraph, FlowSOM-via-CATALYST, with UMAP/tSNE for visualization. Covers the type-vs-state marker distinction (cluster on lineage, test state within clusters), over-provision-then-metacluster, the Weber-Robinson benchmark, seed dependence and metacluster stability, why embeddings are for looking not measuring, and median-heatmap annotation/merging. Use when discovering populations without predefined gates, choosing a clustering algorithm, selecting the number of metaclusters, or annotating clusters into cell 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。