All Skills

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

Provides core patterns and best practices for AWS SDK for Java 2.x. Use when configuring AWS service clients, setting up authentication, managing credentials, configuring timeouts, HTTP clients, or following AWS SDK best practices.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Use this when the user asks for a security review, vulnerability check, or wants to know if code is safe. Focus on common issues like injection, broken auth, insecure defaults, and sensitive data exposure.

Use when managing git worktrees. Provides patterns for creation, cleanup, and branch naming.

Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.

# Architecture Design Design comprehensive system architecture with technology selection and ADRs. ## Agent Winston (Architect) - `bmad-architect-winston` ## Workflow 1. Define high-level system architecture with components 2. Select technology stack with justification 3. Design data model and da

Draws 4 Tarot cards using os.urandom() to inject entropy into planning when prompts are vague or underspecified. Interprets the spread to guide next steps. Use when the user is nonchalant, feeling lucky, says 'let fate decide', makes Yu-Gi-Oh references ('heart of the cards'), demonstrates indifference about approach, or says 'try again' on a system with no changes. Also triggers on sufficiently ambiguous prompts where multiple approaches are equally valid.

Create git commits following repository style. Use when user asks to "create a commit", "commit changes", "/commit", or requests committing code to git.

Commit convention linting and changelog automation following the Kano commit format.

--- name: profiling description: 性能分析 version: 1.0.0 author: terminal-skills tags: [performance, profiling, perf, flamegraph, strace, cpu] --- # 性能分析 ## 概述 CPU/内存分析、火焰图、追踪技能。 ## perf 工具 ### 基础命令 ```bash # 安装 apt install linux-tools-common linux-tools-$(uname -r) # CPU 采样 perf record -g -p PID p

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or analyzing environment variable handling.

--- name: audit description: 安全审计 version: 1.0.0 author: terminal-skills tags: [security, audit, auditd, logging, compliance, vulnerability] --- # 安全审计 ## 概述 安全审计、漏洞扫描、合规检查技能。 ## auditd 审计系统 ### 安装与管理 ```bash # 安装 apt install auditd audispd-plugins # Debian/Ubuntu yum install audit

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Dask parallel computing library. Use for scaling pandas.

--- name: hardening description: 系统加固 version: 1.0.0 author: terminal-skills tags: [security, hardening, cis, baseline, sysctl] --- # 系统加固 ## 概述 系统加固、基线配置、CIS 标准技能。 ## SSH 加固 ### 配置优化 ```bash # /etc/ssh/sshd_config # 禁用 root 登录 PermitRootLogin no # 禁用密码认证 PasswordAuthentication no PubkeyAuthent

Automate GitHub workflows with AI-powered assistance for PR reviews, issue triage, CI/CD pipelines, and Git operations. Use when setting up automated code reviews, implementing issue labeling, creating smart CI/CD workflows, building deployment validation, automating Git operations, or configuring on-demand AI assistance bots.

Write a single haiku with an emotional bias (default: nostalgia or longing). Use when the user asks for haiku, poetry, or short evocative verse.

Build empowered product teams using discovery and delivery dual-track. Use when the user mentions "product discovery", "empowered teams", "feature factory", "product roadmap", "opportunity assessment", or "product vision". Covers product discovery techniques, team structure, and continuous value delivery. For customer interviews, see mom-test. For ongoing discovery systems, see continuous-discovery.

Generic 5-phase structured adversarial analysis protocol. Model-agnostic and domain-agnostic. Works for review, audit, research synthesis, planning, creative critique, or any task requiring multi-perspective examination. Can be used standalone or embedded by any orchestrating skill. Produces verdict with confirmed/withdrawn/disputed/merged/discovered findings.

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isn''t working", "team incentives", "autonomy", "mastery", or "purpose-driven". Covers why carrot-and-stick fails and how to build progress systems. For habit-forming product loops, see hooked-ux. For retention behavior design, see improve-retention.

Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret-dependent branches, or constant-time programming questions in C, C++, Go, Rust, Swift, Java, Kotlin, C#, PHP, JavaScript, TypeScript, Python, or Ruby.