3,394 件 ・ 関連度順
概要と使いどころ
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
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 training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.
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 LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
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 comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
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。
Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug 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。
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
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。
When the user wants to optimize aerospace and defense supply chains, manage long lead-time components, handle MRO operations, or ensure AS9100 compliance. Also use when the user mentions "aerospace supply chain," "aviation manufacturing," "MRO supply chain," "AS9100," "aircraft parts," "defense procurement," "AOG support," "airworthiness," "ITAR compliance," "aerospace certification," or "aviation aftermarket." For general manufacturing, see production-scheduling. For quality, see quality-management.
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 review ads before launch by verifying hook strength, checking proof elements, evaluating CTA effectiveness, and assessing visual quality and authenticity. Use as final check before launching creative or when reviewing team submissions.
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 code for quality, security, and best practices. Use when the user asks for code review, wants feedback on their code, mentions reviewing changes, or asks about code quality.
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。
Content quality audit for both traditional SEO (E-E-A-T) and AI search (citability, structure, authority). Use when user says "content audit", "content quality", "E-E-A-T", "AI citability", "content analysis", or "is my content good for SEO".
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。
5-level verification pyramid: static→unit→Playwright E2E (homepage-first, 6bp)→AI visual→post-deploy. 8-check quality gate. Multi-agent testing (functional/security/a11y/performance). Playwright v1.59+ AI agents (Planner/Generator/Healer). WCAG 2.2 AA via axe-core v4.11. Percy+Chromatic visual regression. ADA Title II 2027/2028 deadlines.
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。
Why expensive, wasteful, effortful, or self-deprecating actions build trust and desire — Rory Sutherland on signalling. Use when the problem is credibility or desirability rather than meaning: the user asks 'why don't people trust us', 'how do we look more credible/committed/premium', 'is our guarantee/warranty worth it', 'should we spend on brand advertising', 'how do we justify a higher price', or wonders why a cheaper-looking competitor wins. Covers costly signals (advertising spend, guarantees, over-delivery), price-as-quality-signal (Veblen goods), and the Pratfall Effect (admitting a real flaw to gain trust). Inspired by Rory Sutherland's *Alchemy*. Routed to from psycho-logic. 日本語の相談（「信頼されない」「安心してもらえない」「強気な価格で売りたい」「広告費に意味はある？」）にも使う。中文咨询（“不被信任”“想以高价出售”“广告费有意义吗？”）也适用。
Quality control for IMC/MIBI data across pixel, channel, image, slide, and batch levels, covering Poisson-count SNR (cell-level Gaussian-mixture and empty-channel comparison), spillover-matrix QC (the three physical sources), drift and the missing EQ-bead analog, acquisition artifacts, and sample-of-origin batch effects. Use when deciding whether to keep or drop a channel, ROI, or slide, distinguishing a dim antibody from a failed one, reading a spillover matrix, or diagnosing batch-driven clustering before 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。
Turns Hi-C/Micro-C FASTQ into a deduplicated, filtered .pairs file with pairtools and decides whether the library worked. Covers the bwa mem -SP5M / bwa-mem2 / chromap --preset hic alignment idiom (mates mapped as independent single-end reads), pairtools parse vs parse2 and the walks-policy choice (5unique pairwise vs all for Pore-C/Micro-C concatemers), pair-type classification (keep UU and rescued UC), dedup (PCR vs optical/by-tile), select by pair_type/MAPQ/distance, restriction-fragment handling (restrict, Arima dual-enzyme, Micro-C/DNase fragment-free), and allele-specific phasing (pairtools phase to two coolers). The library-QC decision uses % long-range cis as the one-number quality metric, trans as the noise floor, orientation balance as fragment-map-free dangling-end/self-circle QC, and % duplicates as a complexity proxy. Use when processing Hi-C/Micro-C/Omni-C reads into pairs, judging library quality, handling multi-enzyme or restriction-agnostic protocols, or generating allele-specific contacts.
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。
Performs differential expression on bulk RNA-seq count data with edgeR's negative-binomial GLM and quasi-likelihood F-test framework. Covers DGEList construction, filterByExpr, TMM/TMMwsp normalization, robust dispersion estimation, glmQLFit/glmQLFTest, TREAT for magnitude-bounded hypotheses, contrasts via no-intercept designs, voom and voomWithQualityWeights for heterogeneous samples, and the edgeR v4 bias-corrected APL changes. Use when running bulk DE with edgeR, choosing edgeR over DESeq2 (small n, transcript DE via catchSalmon, large samples), needing TREAT for a fold-change-threshold hypothesis, troubleshooting v3-to-v4 reproducibility, building paired or interaction designs, or handling library-quality heterogeneity.
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。
Filter alignments by flags, mapping quality, and regions using samtools view and pysam. Use when extracting specific reads, removing low-quality alignments, or subsetting to target regions.
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。
ATAC-seq library quality control -- TSS enrichment, FRiP, fragment-size periodicity, library complexity (NRF/PBC1/PBC2), mitochondrial fraction, and ENCODE 4 thresholds. Use when assessing whether an ATAC-seq library passes ENCODE acceptance criteria, diagnosing transposition artefacts, comparing Omni-ATAC vs standard prep quality, or selecting which replicates to drop before peak calling.
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。
Validate alignment quality with insert size distribution, proper pairing rates, GC bias, strand balance, and other post-alignment metrics. Use when verifying alignment data quality before variant calling or quantification.
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。
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality 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。
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.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
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 continuous improvement principles to iteratively enhance processes, code quality, team practices, and system performance through small, incremental changes. Use when improving development processes, optimizing workflows, reducing waste, enhancing code quality over time, implementing retrospective learnings, or fostering a culture of continuous improvement.
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 dimension analysis and reporting for CJA. Use this skill whenever the user wants to analyze one or more dimensions — including cardinality, distribution/skew, trends, anomalies, data quality errors, comparisons, and forecasting. Also trigger when someone asks "what are the top values for...", "dimension health", "explore this dimension", "dimension dashboard", "dimension statistics", "data quality check on a dimension", "dimension cardinality", "dimension trends", "dimension skew", "dimension anomalies", "compare dimensions", or any similar request to understand what's inside a CJA dimension. Produces an interactive HTML dashboard or a markdown report. Works with the CJA MCP server.
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。