Phase 5 of disciplined development. Validates system against original requirements through system testing and user acceptance testing (UAT).
Score 70/100
Use after solution concepts exist to surface and prioritize assumptions behind outcomes, opportunities, or solution ideas and design experiments to test them.
Score 70/100
Research and add new strategic frameworks to the system (meta-skill). Use when user wants to add framework not in library; discovered new framework in their domain; asks "Can you…
Score 70/100
Gateway skill for research methodology - automatically loads relevant research skills based on task context
Score 70/100
Use when research phase is complete and you need to explore implementation
Score 70/100
Structures and writes discussion sections for academic papers and research reports. Use when writing a discussion section, interpreting research results, connecting findings to…
Score 70/100
The cosmic distance ladder from radar ranging to Hubble flow. Covers parallax, spectroscopic parallax, cluster main-sequence fitting, Cepheid and RR Lyrae period-luminosity…
Score 70/100
Эксперт анализа распределений. Используй для statistical distributions, data analysis и hypothesis testing.
Score 70/100
Statistical distribution fitting skill for input modeling in simulation and analysis.
Score 70/100
Differentially methylated region (DMR) detection using methylKit tiles, bsseq BSmooth, and DMRcate. Use when identifying contiguous genomic regions with methylation differences…
Score 70/100
DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.
Score 70/100
Efficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding architectural decisions, feature specs, and technical docs.
Score 70/100
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose…
Score 70/100
Конвертирует сырую документацию (MD/TXT файлы) из docs/documentation/ или любого пути в структурированные знания tech-research/cache/. Принимает файл или папку (рекурсивно).
Score 70/100
Create properly formatted documents for the knowledge base. Use when creating tasks, projects, bookmarks, companies, meetings, people, or research entries.
Score 70/100
Scan and catalog document collections with metadata extraction, categorization, and statistics. Use for auditing document libraries, preparing for knowledge base creation, or…
Score 70/100
Research and document write/create APIs of a source system to enable write-back testing functionality.
Score 70/100
Enforces online documentation research before any technical implementation. Use when implementing features to ensure code follows current best practices by researching official…
Score 70/100
Design of Experiments planning and analysis skill for factorial and response surface experiments.
Score 70/100
Display Collective Dogs activity summary. Shows which Dogs (Sefirot) have been most active during the session, with personality and statistics.
Score 70/100
MCP-powered domain research for requirements elicitation. Uses perplexity, context7, firecrawl, and other MCP servers to research domain knowledge, best practices, and industry…
Score 70/100
Use when formulating clinical research questions (PICOT framework), evaluating health evidence quality (study design hierarchy, bias assessment, GRADE), prioritizing…
Score 70/100
Oxford Nanopore basecalling with Dorado on University of Michigan HPC clusters (ARMIS2 and Great Lakes).
Score 70/100
Use when asked to research, compare, evaluate, or investigate any topic. Triggers: research this, compare options, evaluate alternatives, investigate, find the best, product…
Score 70/100
Validates code and provides physics reasoning for the 2-D injection-production doublet model using streamline methods.
Score 70/100
Product research for dropshipping businesses. Identify profitable products with reliable suppliers, healthy margins, and manageable competition.
Score 70/100
Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED, TPSA, synthetic accessibility),…
Score 70/100
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM…
Score 70/100
Perform SQL joins and multi-table analysis on DST data in DuckDB. Use when research requires combining multiple tables on common dimensions (time, region).
Score 70/100
Generate HTML research reports with embedded data, charts, and analysis. Use when creating final research deliverables.
Score 70/100
Use two independent agents for reviews or research, then collate findings to identify common findings, unique insights, and divergences
Score 70/100
Research UI E2E test targets and generate test scenario documentation. Use to analyze a frontend app and create comprehensive E2E test plans.
Score 70/100
Detect and alert on emerging anomalies and risk flags from pilot metrics and data streams. Use when monitoring live data, threshold breaches, or statistical outliers to trigger…
Score 70/100
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.
Score 70/100
Earth and life systems as contexts for scientific inquiry. Covers ecosystems, biodiversity, biogeochemical cycles, climate systems, geological processes, and human impacts -- not…
Score 70/100
User research reconnaissance — survey existing personas, research docs, interview notes, and feedback artifacts to establish what is already known about users.
Score 70/100
Cross-platform keyword research for e-commerce. Discover high-converting keywords across Amazon, Shopify, Etsy, Google Shopping, TikTok Shop, and Walmart.
Score 70/100
Produce an approved ecosystem briefing from bounded research and a governed content pass.
Score 70/100
Education Data Architecture (EDA) data model deep dive: Contact-centric, Affiliations, Relationships, Account record types (Academic Program, Educational Institution, Sports…
Score 70/100
Component research and procurement. Search JLC for components, analyze datasheets, compare options, and document selections with rationale.
Score 70/100
Perform differential expression analysis using edgeR in R/Bioconductor. Use for analyzing RNA-seq count data with the quasi-likelihood F-test framework, creating DGEList objects,…
Score 70/100
Education Cloud (EDA — Education Data Architecture) setup: student success hub, advisor workflows, enrollment management, academic data model.
Score 70/100
Effect-TS specialized research via deepwiki and submodules. Query Effect-TS/effect, tim-smart/effect-atom for verified patterns.
Score 70/100
Calculate and interpret effect sizes for statistical analyses. Use when: (1) Reporting research results to show practical significance, (2) Meta-analysis to combine study results,…
Score 70/100
Blockchain analytics and DeFi intelligence via Einstein's x402 micropayment services. Use when user wants on-chain market analysis, token research, whale tracking, smart money…
Score 70/100
Use when orchestrating multi-agent Electrobun feature development. Explains the electrobun-feature-team architecture — UI agent (views, RPC contract) followed by backend agent…
Score 70/100
Emerging and transformative technologies -- artificial intelligence, biotechnology, quantum computing, blockchain, robotics, IoT, augmented/virtual reality, and nanotechnology.
Score 70/100
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math +…
Score 70/100
A real-time monitoring system for identifying "incubation period" research hotspots in biological and medical sciences before they are defined by mainstream journals.
Score 70/100
Research user needs, existing patterns, and accessibility requirements before designing a component
Score 70/100
Create structured visualizations of stakeholder perspectives (says, thinks, does, feels) to build deep understanding. Use when conducting user research or validating assumptions.
Score 70/100
Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines.
Score 70/100
Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines.
Score 70/100
ENCODE Portal REST API for regulatory genomics: TF ChIP-seq, ATAC-seq/DNase-seq peaks, histone marks, and RNA-seq across 1000+ cell types.
Score 70/100
Oxford Nanopore read end reason QC analysis. Use when analyzing nanopore sequencing quality, checking for adaptive sampling efficiency, investigating read termination patterns,…
Score 70/100
Complete development workflow orchestrator coordinating all multi-ai skills (research → planning → implementation → testing → verification) with quality gates, failure recovery,…
Score 70/100
Adapt recommendations to your current energy level — low energy gets easy tasks (recycle, micro, curate), high energy gets ambitious tasks (research, series, course).
Score 70/100
Build an Energy Management Operating System Pack (energy drivers/drains map, calendar energy audit, zone-of-genius expansion plan, energy-aligned weekly schedule, recovery…
Score 70/100
Research and extract an engineer's coding style, patterns, and best practices from their GitHub contributions. Creates structured knowledge base for replicating their expertise.
Score 70/100
面向实现闭环的工程 workflow。用于把“需求/思路/方案”转成可交付改动，强调验收标准、最小改动、立即验证、明确回滚点。冲突优先级最低：若请求同时包含“接入审计”或“修 bug/继续查”等排障闭环意图，应让位于 skill-safety-audit 或 research-execution-protocol。
Score 70/100