3,489 件 ・ 関連度順
概要と使いどころ
Use this skill when creating new UI from scratch, doing a visual design pass, or when output risks looking like generic AI-generated design. Trigger words: UI 作成, デザイン, 画面を作る, 見た目を良く, デザイン改善, ランディング, ヒーロー, おしゃれに, AIっぽい, design pass.
Transform transcripts, conversations, or raw notes into shareable content — either multiple social posts OR a single long-form article. Learns style from user's published content. Handles transcripts of any length (tested up to 5500+ lines / 90+ min). Use when user: (1) provides transcript/conversation/recording and wants social content, (2) asks to "turn recording/notes into posts", (3) mentions generating content from recordings/notes, (4) needs multiple publishable pieces from single source, (5) asks to write an article from a transcript — e.g. "write an article/long-form", "organize into an article", "write up this session", "turn this talk into a blog post", "deep dive". Social mode outputs 2-15 ready-to-publish pieces. Article mode outputs a structured long-form piece (3000-10000+ chars) written section-by-section.
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。
Guide for training outputs, metrics logging, logtree reports, tracing/profiling, and debugging training runs. Use when the user asks about training logs, metrics, debugging, tracing, profiling, timing, Gantt charts, or understanding training output files.
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。
Convergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.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。
Convergence loop that iteratively improves work until quality thresholds are met. Use when: (1) "refine this", "make this better", "iterate on this", (2) After /analyst gives a REVISE verdict, (3) Output quality is below 8/10, (4) "run the refinery loop on this". Reads analyst reviews from system/reviews/. Generates, scores, diagnoses, rewrites, re-scores. Stops when all dimensions >= 8/10 or diminishing returns detected. Outputs to system/refinery-log.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。
Senior engineering analyst for code review, plan review, and automation review. Use when: (1) "review this", "analyze the code", "check this plan", (2) After implementation to verify quality, (3) "is this good enough?", (4) Before marking a task complete, (5) Reviewing a blueprint from /architect, (6) Reviewing output from /refinery. Four-lens review: architecture, code quality, reliability, performance. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
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 after changing prompts, skills, the compiler, or editorial policies — or when the user asks to measure edit quality, run regression evals, check agreement with approved edits, or says '評価して', '一致率を測って', 'eval を回して'. Compares agent output against human-approved golden projects.
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
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。
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
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。
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
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。
ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'` to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square, correlation, power), tooluniverse-image-analysis (microscopy, colony, fluorescence, dose-response, .tif — including ANOVA / Dunnett / power-analysis on image-derived measurements), tooluniverse-epigenomics (DNA methylation, CpG, m6A, MeRIP-seq, bisulfite, ChIP-seq, chromatin), tooluniverse-sequence-analysis (FASTQ, Trimmomatic, BWA, samtools, coverage), tooluniverse-variant-analysis (VCF, VAF, SNP, mutation), tooluniverse-phylogenetics (treeness, PhyKIT, parsimony), tooluniverse-single-cell (scRNA, h5ad, scanpy), tooluniverse-crispr-screen-analysis (MAGeCK, sgRNA), tooluniverse-proteomics-analysis (mass spec, TMT). Use for CSV/Excel/VCF/FASTA/h5ad and any biology/chemistry/medicine analysis 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。
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR 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。
Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result files, and the criteria JSON written alongside a --record recording — and runs the metrics module (metrics_manager.py) to compute custom measurements over a recorded run offline, without the simulator. Use when the user asks "did the scenario pass", "why did it fail", "summarise these results", "compare these runs", or wants distance/speed/lane metrics from a recording.
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。
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official 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。
OpenAI API (developers.openai.com) の Responses API リファレンス。 text generation, embeddings, structured outputs, streaming, function calling, programmatic tool calling, conversation state, prompt caching, reasoning models, background mode, compaction, multi-agent。 webhooks, error codes, rate limits, Realtime API server controls。 公式 SDK (Python / JavaScript(JS) / .NET / Java / Go / Ruby), openai CLI。 Chat Completions / Assistants からの移行, deprecations。
OpenAI Apps SDK / ChatGPT plugins (developers.openai.com/plugins) のリファレンス。 ChatGPT 内で動くアプリを MCP サーバーとして公開する側の API。 window.openai, useOpenAiGlobal, registerAppTool, ui://widget, _meta, openai/outputTemplate, OAuth 認証, Checkout API, 接続テスト・審査・申請。
Claude Code (code.claude.com) の拡張機能リファレンス。 Agent Skills (SKILL.md), slash commands, output styles, subagents, agent teams, agent view, workflows, routines, scheduled tasks, hooks (PreToolUse / PostToolUse), plugins, plugin marketplace, MCP 設定 (.mcp.json / claude mcp add), managed MCP, channels (--channels / claude/channel push events, webhook / telegram / discord / imessage), tools-reference, advisor, ultrareview。
Claude Agent SDK (code.claude.com/docs/en/agent-sdk) の TypeScript / Python リファレンス。 query(), ClaudeAgentOptions / Options, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, slash commands, tool search, hosting / observability。
Claude API (platform.claude.com) の Messages API リファレンス。 streaming (SSE), thinking (adaptive) / effort, prompt caching, context editing, compaction, structured outputs, Message Batches, token counting, vision / PDF, Files API, citations, embeddings (Voyage AI)。 errors, rate limits, beta headers, Amazon Bedrock / Vertex AI / Foundry 経由アクセスを含む。
AVFoundation / AVKit / PhotoKit リファレンス。 AVPlayer, AVPlayerViewController, VideoPlayer, AVPlayerItem, AVMutableComposition, AVCaptureSession, AVCaptureDevice, AVCapturePhotoOutput, AVAudioEngine, AVAudioSession, AVAudioPlayer, AVSpeechSynthesizer, PHAsset, PHImageManager, PhotosPicker, PHPhotoLibrary。
修正完了後に agent-review-kit でレビューHTMLを生成し、ユーザーがブラウザで書いた差分コメントを Codex または Claude Code の同一セッションで受け取り、回答・修正・resolve を未解決0件まで繰り返すレビューループ。AIレビューの指摘を add-comment でブラウザ上のコメントとして表示し、ユーザーが返信した指摘だけ修正する「AIレビューモード」も含む。実装プラン・設計書などの任意HTMLを publish-html でレンダリング済みのまま表示し、要素クリック・テキスト範囲でコメントを受け取る「HTMLレビューモード」も含む。他のレビュースキルの結果の出力先として agent-review-kit が指定された場合も、このスキルを読んで AI レビューモードの手順に従うこと。Use when the user wants to review changes in a browser (GitHub-like diff review), review a rendered HTML doc (plan/design doc) in a browser, iterate on fixes with inline comments, or display AI review findings as browser comments (output target: agent-review-kit).
Analyzes pooled CRISPR screens with MAGeCK (Li et al 2014), covering count generation (mageck count), the RRA two-condition workflow (mageck test using alpha-RRA over per-sgRNA negative-binomial p-values), the MLE multi-condition workflow (mageck mle with explicit design matrix and beta-score output), normalization choice (median vs total vs control-sgRNA vs spike-in), sgRNA efficiency injection, paired-sample testing, time-course design, drug-screen versus dropout-screen design matrices, MAGeCKFlute and MAGeCK-VISPR downstream visualization, and decision logic for when to use MAGeCK vs JACKS / BAGEL2 / drugZ / Chronos. Use when running a fresh CRISPR screen analysis, picking RRA vs MLE for the experimental design, choosing a normalization method from QC signatures, debugging MLE convergence failure or NaN beta scores, comparing MAGeCK output across tools, or building a batch-aware multi-cell-line / multi-condition MLE design matrix.
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。
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR 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。
Review a GitHub pull request from multiple perspectives in parallel, output only findings, then let the user pick which to fix in the same session. Use when the user asks to review a PR by number, mentions "PRレビュー" / "PR review" with a number, or invokes `/pr-review <number>`. Fans out subagents for absolute-rules, stop-slop, security, architecture, code-quality, testing, and ai-antipattern.