Results for “sequon-analysis”

Performs differential expression analysis on bulk RNA-seq or pseudo-bulk count matrices with QC, PCA, and contrast testing.

選択肢(A/B/C)の深掘り比較→淘汰→推奨で判断負担を下げ判断の質を上げるスキル。5段階（L1固定3点/L1.5案拡張Diverge・自動/L2評価軸マトリクス/L3複数LLM弁証論/L4過去判断照合）。 「比較して」「深掘りして」「メリデメ教えて」「お勧めは？」「徹底的に」「過去の判断と照合」「前にどう決めたっけ」「/sentaku」等で発火。teian(浅)の深掘り要求を受け取り、brainstorming(深:設計全体)と棲み分け。

Estimate cell state transitions from unspliced/spliced mRNA dynamics using scVelo, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data.

Use when performing nucleotide-nucleotide similarity searches to identify homologs, annotate sequences, or compare query sequences against nucleotide databases.

Queries and manages Seq structured log servers via the Seq HTTP API, covering log search, signals, alerts, dashboards, retention policies, and API key management.

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Analyzes email sequence performance metrics. Evaluates open rates, click rates, reply rates, and conversion by step. Identifies drop-off points, benchmarks against industry averages, and recommends optimizations.

Analyze content sequences from page structure to determine whether each should be default content or a specific block, and validate block selection for AEM Edge Delivery Services imports.

Train, evaluate, export, and run inference for pose classification models using ST-GCN on skeleton keypoint sequences.

Use when you need to perform quality control analysis on high-throughput sequencing data (fastq, bam, sam, or fast5 files) to identify potential problems before downstream analysis.

Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.

Optimize PostgreSQL queries, configure replication, and implement advanced database features with EXPLAIN analysis, JSONB operations, extension usage, and VACUUM tuning.

Perform survival analysis and time-to-event modeling in Python using scikit-survival, including Cox models, random survival forests, gradient boosting, survival SVMs, and evaluation metrics like concordance index and Brier score.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Perform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.

Analyze biological sequences, alignments, phylogenetic trees, and diversity metrics (alpha/beta, UniFrac) with ordination (PCoA) and PERMANOVA for microbiome and community ecology data.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md. Identifying inconsistencies, duplications, ambiguities, and underspecified items.

Perform time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using a scikit-learn compatible Python toolkit.

Analiza datos en bases de datos relacionales con consultas SQL eficientes y legibles, incluyendo joins, window functions, CTEs y subqueries, para extraer insights directamente de la base de datos.

Runs time series machine learning tasks—classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search—using the scikit-learn compatible aeon toolkit.

Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files. Use when working with .xlsx, .xlsm, .xls, .ods, .csv, or .tsv files; answering questions from a workbook; auditing formulas or data quality; comparing sheets or versions; producing pivots, charts, forecasts, or summary workbooks; repairing malformed tables; or validating that spreadsheet edits and calculations are accurate.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Recursive self-improving holon λ(ο,Κ,Σ).τ' for knowledge compounding and schema evolution. USE WHEN learning, improving, optimizing, assessing, reflecting, debugging, synthesizing, or refining—whether human, AI, or organizational. Triggers on /learn, /compound, /improve, /refine, /optimize, /assess, /reflect, "lessons learned", "best practices", "continuous improvement". Preserves Κ-monotonicity, η≥4, homoiconicity.

Maps intrusion activity to the Lockheed Martin Cyber Kill Chain framework to identify adversary phase completion, detection gaps, and defensive controls for post-incident analysis and prevention.

Seven-role depersonalised panel review of framework artefacts (KUD, criterion bank, LT definition, crosswalk, scope-and-sequence) in sequential-isolation mode. Gate rule mean>=88 AND no role<70.

Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.

Optimizes SQL queries, designs database schemas, and troubleshoots performance issues using execution plan analysis, indexing strategies, and set-based operations.

Orchestrates a complete bulk RNA-seq differential-expression study from raw FASTQ reads through QC, alignment, quantification, differential expression, pathway enrichment, and publication figures.

沈墨（悬疑剧虚构）认知与表达框架（压缩蒸馏）：创伤反杀叙事、时代灰雾、钢琴意象 触发：漫长的季节 等。虚构；禁止犯罪模仿

Guides creating a Sequoia-style 12-slide pitch deck with slide-by-slide instructions, storytelling principles, and 30 anticipated VC questions with answer strategies.

Builds statistical plots with the seaborn Python library and pandas DataFrame integration, on attractive matplotlib-based defaults. Use for quick exploration of distributions, relationships, and categorical comparisons — box plots, violin plots, swarm/strip plots, KDE/histograms, pair plots, joint plots, regression plots, correlation heatmaps, and faceted small multiples (relplot/displot/catplot/lmplot). For interactive/hover/zoom charts defer to alterlab-plotly; for exact journal/manuscript styling (column widths, point fonts, CMYK, vector export) defer to alterlab-scientific-viz; for low-level custom matplotlib figures defer to alterlab-matplotlib (seaborn integrates with it for fine-tuning). Part of the AlterLab Academic Skills suite.

Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.

Analyzes Zeek conn.log connection intervals using statistical methods to detect C2 beaconing patterns, flagging periodic connections with low jitter.

Generates four improved variations of any installed skill, scores them against a weighted rubric, and applies the winning version while preserving the original.