В каталоге 183 730 навыков в 14 категориях.
Use this skill when setting up, validating, or repairing the local environment for the cross-modal appraisal transfer pr...
Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation uni...
Use when the user has a research question and needs a complete experiment package — design document, runnable code, resu...
Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track exp...
Integrate Trackio for experiment tracking in Kaggle competitions. Use PROACTIVELY when user trains models, logs metrics,...
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted...
Run thesis experiments from ideation through publication. Use when brainstorming research questions, writing specs, exec...
Prerequisites: npm install @jaypie/tildeskill
Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treat...
Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out trea...
Plan experiments and choose designs. Use when selecting factors, controls, randomization, or run allocation.
A/B testing, randomization, sample size calculation, confounding control, and causal inference for data science. Covers...
Experimental design principles for scientific inquiry. Covers variable identification and control, control groups (posit...
Experimental methods for physics including measurement, uncertainty analysis, and experimental design. Covers the scient...
Use when theoretical calculations need experimental validation, protocols must be designed with clear hypotheses and suc...
Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + toolin...
Directs bold, memorable, highly art-directed website concepts while preserving usability, accessibility, brand coherence...
Designs, runs, and reads A/B tests and growth experiments — hypothesis, sample size, duration, and honest interpretation...
Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous, well-instrument...
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential te...
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitu...
A/B tests, feature flags, gradual rollout experiments cho PikaRobot. TRIGGERS: "experiment", "A/B test", "feature flag",...
Use when adding, changing, or reviewing a VS Code A/B experiment, either an experiment-controlled setting or a treatment...
Critiques one proposal or plan from several expert angles and reports strengths, weaknesses and risks. Use when the user...
Expert Nuxt developer specializing in Nuxt 3, Nitro, server routes, data fetching strategies, and performance optimizati...
Expert Vue.js frontend engineer specializing in Vue 3 Composition API, reactivity, state management, testing, and perfor...
Draws an explicit boundary around decisions AI may never make autonomously (high-stakes agency), and protects the junior...
Search for candidate books, download owner-named titles immediately, present candidates for selection questions, save ap...
Arquitecto de Software Senior autónomo. Se activa automáticamente para: decisiones técnicas, validación de código, corre...
Create an architecture document from a spec — the bridge between specification and implementation, answering every desig...
站在使用者视角审查 expert-team 产出的专家资产:零上下文用户能否看懂照用、格式是否合规(R1–R7 / CR1–CR9 / INDEX),格式问题自动修复、可读性问题给修复路径。触发:"核对专家团"、"审查专家资产"、"expe...
Part of the Expert Standard Dev Tools package. Use when an existing artifact — a spec, an architecture, or a plan — must...
Alias for $council --mode=debate (adversarial named-persona debate).
Runs an autonomous debug cycle: reads linter/TS/test diagnostics, applies fixes in priority order, re-checks, and repeat...
Systematic debugging workflow to reproduce, isolate, and fix hard software bugs, resolve related lint issues, and add te...
设计原型专家团入口。用于 Codex CLI 的 $expert-design 调用。 覆盖需求发现、设计系统选择、原型生成、质量审查和导出交付。 触发词:设计原型、UI、UX、设计系统、高保真、HTML 原型、品牌设计、页面设计
EXPERTS/ persona kartları üret/güncelle — uzman kurulu devreye alma.
Faithfully execute an approved implementation plan end-to-end, as the main agent with no subagent, under the Expert Stan...
Meta-orchestration system that connects all Agent Experts for seamless workflow execution.
Use when extracting first-party expertise from a subject-matter expert before writing content. Produces a knowledge docu...
Get the most from an hour with an expert — the do-your-homework floor (never ask what's googleable), the question arc fr...
Plan decision-focused expert interviews or synthesize supplied interview transcripts and notes into traceable findings,...
查找并复用已沉淀的"业务专家"资产包(.module-experts/):按使用意图分层加载(使用 → 契约层,深入 → 实现层 + 源码),支持子专家与专题查找。触发:"有没有这个模块的专家"、"查专家"、"expert lookup",...
Audit, repair, or rebuild an MCP server until it is a verified, production-grade system — functional, secure, reliable,...
Senior Next.js 15 expert with 15+ years experience. Generate production-ready code with strict TypeScript typing, profes...
基础设施运维专家入口。用于 Codex CLI 的 $expert-ops 调用。 适用于监控告警、可观测性、云基础设施与 IaC、安全加固、成本优化、备份恢复、容量规划和完整基础设施健康评估。 触发词:运维、SRE、Prometheus、...
Multi-expert evaluation pattern for structured analysis and decision-making. PROACTIVELY activate for: (1) Analyze with...
Create implementation plans concrete enough that another engineer — or an autonomous agent — can execute them step by st...
Extract a founder's or expert's point of view — core beliefs, contrarian takes, origin stories, taste — and synthesize a...
产品战略团队专家团入口。用于 Codex CLI 的 $expert-product 调用。 覆盖 PRD、竞品分析、用户研究、指标分析、路线图、Sprint 和干系人更新。 触发词:产品战略、PRD、竞品分析、用户研究、路线图、指标分析、...
将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI(DeepSeek、豆包、Kimi、Claude、Ollama 等)的实用工具。内置「清理平台语法 / 单专家单任务 / 补背景信息」三大原则、五段式提示词结构、迁移自检清单,以及...
Structured deep review of engineering work — code, implementations, architectures, specs, plans — producing standards-gr...
ESP-IDF v5.x RMT5 API expert for LED protocols, encoders, and multi-channel control. Use when working with RMT periphera...
Build a mass movement around your expertise using Russell Brunson's proven framework—position yourself as the charismati...
安全专家入口。用于 Codex CLI 的 $expert-security 调用。 适用于威胁建模、漏洞评估、安全代码审查、安全架构设计、DevSecOps、安全运营、事件响应、合规审计和完整安全健康评估。 触发词:安全专家、威胁建模、S...
Expert-level guidance for creating high-quality Claude Code skills. Use alongside Anthropic's skill-creator when creatin...
软件开发团队专家团入口。用于 Codex CLI 的 $expert-software 调用。 支持快速模式、BugFix、标准 SOP、PRD、架构设计、代码实现、测试验证。 触发词:软件开发、写代码、修 bug、PRD、架构设计、测试、...
资产复用工作流:区分"业务专家团"(领域地图,走 expert-lookup)与"解决方案"(场景菜谱,走 solution-lookup),并把解决后的可复用成果路由到 solution-capture / expert-team。触发:...
Part of the Expert Standard Dev Tools package. Use when a specification must be written to a high bar — a contract that...
The foundational evaluation frame for all engineering work. Activates whenever Claude is making an engineering judgment...
Comprehensive guidance for understanding, designing, and implementing expert systems using rule-based inference, knowled...
专家团总路由器。用于 Codex CLI 的 $expert-team 调用。 自动在软件开发团队、设计原型专家团、产品战略团队、基础设施运维专家、安全专家和数据库优化专家之间路由,也支持显式指定 software/design/produ...
派多专家子 agent 并行深挖单个业务模块,产出"契约层(黑盒使用)+ 实现层(白盒技术)"两层资产的专家包(落 .module-experts/),大模块可拆子专家或专题。触发:"掌握这个模块"、"深度分析 xxx 模块"、"梳理这个模...
This skill should be used when the owner asks to "use the expert plugin", "use expert-dev-tools", "run the expert workfl...
Team expertise billboard via `adept exchange`: ask teammates for expertise and stack responses. Apply when the user want...
Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, def...
/============================================================================/
Run expertise to procedure.
Herramienta que genera SQL correcto y eficiente en los principales dialectos de almacenes de datos Snowflake, BigQuery,...
Guía a los desarrolladores a seleccionar y configurar herramientas y formatos de nodo del Protocolo de Contexto de Model...
Use when a project needs multi-perspective review — pre-launch audit, post-refactor check, inherited codebase assessment...
Test skill with expired license for unit testing.
Deep explanation of complex code, files, or concepts. Dispatches skill-preloaded agents, uses structural search, generat...
Step-by-step explanation of a file, function, or module with mini-diagram if appropriate Arguments: <file-path|module-pa...
Explain what code does line by line so you can understand and learn from it.
Explain a Java, Spring Boot, JPA, or React Native concept to an experienced Go/TypeScript developer, grounded in this re...
Use when explaining code, concepts, patterns, or architecture: engineer-grade technical explanations with 3-tier depth c...
Explain all bluera-base plugin functionality in human-readable format
Explain a file, function, or system — architectural walkthrough using query tools
코드를 비유 기반으로 설명하고 Mermaid 다이어그램을 생성합니다. 파일/기능/줌아웃 3가지 모드 지원. /explain @file.ts (상세 설명), /explain "로그인 기능" (기능 단위), /expla...
Explain code, concepts, or system behavior with adjustable depth levels
Explains how existing code works in a diagram-rich report on design and weak spots, read-only. Use when the user says "w...
Explain how code, a feature, or system works
Explain code with educational depth. Generates Mermaid diagrams for architecture and data flow, traces data through the...
Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also...
Document the reasoning behind implementation decisions as markdown files. Creates decision records that future developer...
Explain Semantica reasoning, decision logic, and graph results with traceability, causal context, and human-readable rat...
Use when the user needs a catch-up, concept explanation, goal closeout, current-state refresh, Lev context mapping, or a...
Longer human recap this reply only.
Use when explaining concepts, code, plans, decisions, investigation findings, or work outcomes in terms the reader can u...
Explain anything the user does not understand in the simplest true way, so it is easy to understand and easy to remember...
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they...
Teach one gnarly topic (a bug family, a design constraint, a system) until you genuinely understand it: author a verifie...
อธิบาย concept, code, skill, term หรือกลไกการทำงานที่ user สงสัยอย่างชัดเจน