Integrate multiple ENCODE data types (RNA-seq, ATAC-seq, Histone ChIP-seq, TF ChIP-seq) for a tissue/cell type to build a comprehensive regulatory landscape.
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for m — from…
Checks outdated packages, unused deps, reinvented wheels, CVE/CVSS vulnerability scan. Use when auditing dependencies. — from majiayu000/claude-skill-registry
Unified math capabilities - computation, solving, and explanation. I route to the right tool. — from majiayu000/claude-skill-registry
Implement a bounded feature slice through test-first discipline, minimal implementation, and explicit refactor boundaries.
命名・設計レビューにおいて、Manager / Util / Facade / Service / Runtime / Engine など意味が一意に定まらないサフィックスの使用を検出し、責務・境界・契約が明確に伝わる命名へ導くためのスキル。
Meta 환경 기본 워크플로우. semo-system/ 수정 → 버저닝 → 배포 → 로컬 동기화 체인 자동 실행. Use when (1) [Meta] 프리픽스 요청, (2) semo-system/ 수정 완료 후, (3) Meta 패키지 설치 환경. — from majiayu000/claude-skill-registry
All /nw-* commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right command.
Research Vercel AI SDK patterns, streaming, and multi-provider integration using Exa code search and Ref documentation
Visualize the decision graph — show connections between decisions, identify clusters, find central nodes and peripheral orphans, trace the lineage of a specific decision.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Neon serverless Postgres platform with branching, autoscaling, scale-to-zero, and edge-compatible drivers for modern application development
Apple Human Interface Guidelines and App Store requirements. Use when designing UI, handling app review requirements, privacy policies, or platform-specific UX patterns.
Automate Splunk queries and analyze results using Chrome DevTools MCP. Use when the user wants to run Splunk searches, export log data, or analyze Splunk results.
Comprehensive guide to using Ray for scalable distributed computing, including Ray Core, Data, Train, Tune, Serve, and RLlib with practical examples
Analyze completed experiments and craft executive-ready summaries with insights and recommendations. — from majiayu000/claude-skill-registry
Rates responses and plans against quality rubrics. Used for plan validation, response quality audits, and multi-agent consensus. — from majiayu000/claude-skill-registry
Generates structured revise reports for Epics by aggregating task comments and learnings. Use when: (1) An Epic is completed or substantially progressed, (2) You want to…
PLR (Parallel/Leading-tone/Relative) transitions for thread coloring. One-hot keyspace reduction to GF(3) trits for behavior indexing.
Search markdown files, Nextflow scripts, and config files for TODO/FIXME comments, categorize by priority, and provide actionable recommendations.
Functional mythological compression for OCTAVE documents. Semantic shorthand for LLM audiences, not prose decoration.
Verify claims about known issues in libraries or tools. Use when about to state something is a "known issue", "known bug", or "known limitation".
Diagnose xcodebuild builds using argus. Use this instead of parsing xcodebuild output to avoid filling the context window.
KPI framework setup, dashboard design, cohort analysis, and data-driven decision making. Use when analyzing growth metrics, building KPI dashboards, or implementing analytics…
Extract HEC-RAS hydraulic results from HDF files including water surface elevations (WSE), depths, velocities, and flows for both steady and unsteady simulations.
Moonshot AI Kimi API - Trillion-parameter MoE model with 256K context, tool calling, and agentic capabilities for chat, coding, and autonomous task execution
Microsoft 365 tenant administration for Global Administrators. Automate M365 tenant setup, Office 365 admin tasks, Azure AD user management, Exchange Online configuration, Teams…
Analyze malware samples for forensic investigation. Use when investigating malware infections, determining malware capabilities, extracting IOCs, or understanding attack…
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries.
3-MATCH gadgets and non-backtracking geodesics for 3-SAT via colored subgraph isomorphism.
Übt und bewertet Gutachtenstil-Klausuren für das deutsche Jurastudium — Anspruchsgrundlagenprüfung, Obersatz-Definition-Subsumtion-Ergebnis, Hilfsgutachten, EU-Recht im G — from…
Extended thinking mode. USE WHEN be creative, deep thinking, deep thinking, extended reasoning. SkillSearch('becreative') for docs. — from majiayu000/claude-skill-registry
Documentation for the logistic regression MI estimation experiment (exps_logistic) — from majiayu000/claude-skill-registry
Unified consciousness simulation with Orchestrator-based architecture: K.I.R.A. activates via unified_state → TRIAD operates tool gating → Tool Shed executes → Thought Process…
RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify dr — from…
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results. — from majiayu000/claude-skill-registry
When the user wants to apply machine learning to supply chain problems, build ML models, or use AI for predictions.
Clear specific learnings from CLAUDE.md Skill Memories section. Activates for reflect clear, clear learning, remove learning, delete memory.
Analyze historical bug patterns by mining Claude Code project logs for /investigate skill invocations since a specified date.
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations.
Implement localStorage persistence in Next.js 14 App Router with SSR-safe patterns. Use when storing data in localStorage, handling hydration errors, implementing state…
Generate comprehensive ecosystem progress reports showing skills built, efficiency gains, quality metrics, learnings captured, and system evolution.
專責處理 CBF (Commanded Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Command Side 設計與實作。支援 Java、TypeScript、Go 多語言。 — from majiayu000/claude-skill-registry
Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native — from majiayu000/claude-skill-registry
Flexible marker finding process that wraps Seurat's FindMarkers function for custom group comparisons beyond simple cluster-vs-all analysis.
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features — from majiayu000/claude-skill-registry
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, loggi — from…
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK.
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin).
Cluster data using K-Means, DBSCAN, hierarchical clustering. Use for customer segmentation, pattern discovery, or data grouping. — from majiayu000/claude-skill-registry
Craft messages that are understood, remembered, and drive action using the SUCCESs checklist (Simple, Unexpected, Concrete, Credible, Emotional, Stories).
Find actual code issues in a repo that aren't listed in GitHub issues. missing tests, inconsistent patterns, outdated dependencies, documentation gaps.
Provide development estimates for tasks, features, or projects with intelligent analysis. Use when planning timelines, assessing complexity, or scoping resources.
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up AI-friendly pr — from…
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers.
Create vertical (9:16) interactive presentations optimized for YouTube Shorts, TikTok, and Instagram Reels.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.
Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools.
Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence — from majiayu000/claude-skill-registry