PCI DSS compliance assessment and reporting for cardholder data protection, SAQ automation, and ASV scan orchestration
Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling, LLM inference, and sustainability UX.
Performance test design skill for test planning, data collection, and acceptance criteria verification
Perses platform operations: dashboards, plugins, deployment, migration, and quality.
Verify codebase quality — architecture consistency, convention compliance, gap analysis. Triggers: code review, architecture check, quality, gap analysis, 코드 리뷰, 품질 검증.
Deploy to production — CI/CD pipelines, environment config, deployment strategies. Triggers: deployment, CI/CD, production, Vercel, 배포, 프로덕션.
Use when applying Phoenix Framework best practices including context design, controller patterns, and application architecture. Use when building Phoenix applications.
Rédige un message de commit Git pour un projet PHP/Symfony, en suivant la convention Emoji-Log. À utiliser dès que l'utilisateur demande un commit ou un message de commit.
Set up CI, GitHub Actions, automate builds, continuous integration. GitHub Actions CI/CD pipeline configuration for iOS apps — build/test/deploy workflows, caching strategies,…
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance.
Complete guide to building Claude Code plugins — manifest schema, command/skill/agent/hook authoring, MCP server development, marketplace publishing, and testing
Implement Hexagonal Architecture (Ports and Adapters) in Symfony; separate domain logic from infrastructure with clear boundaries
迁移或大规模重构前，按四层递进的静态+语义分析产出可机器消费的 JSON 与简短摘要（BLIR → 业务推理 → v1/v2 语义差分 → 模式/反模式）。适用于框架升级、模块拆分、遗留改造、分支对比、Breaking change 审计、以及需要论证业务等价而不仅是文本 diff 的场景。 Triggers：迁移前分析、重构预分析、语义…
30-point audit of a B2B pricing program across four dimensions — diagnostic data (8 points), reference frames + copy (8 points), tier architecture (8 points), and operating…
Process code review findings interactively - fix or skip issues from monty-code-review output. Presents issues in severity order, applies fixes, runs quality checks, and updates…
Discrete event simulation skill for process modeling, scenario testing, and optimization
Generate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentation, or needs help with OpenAPI/Swagger — from…
Generate project documentation from codebase analysis — ARCHITECTURE.md, API_ENDPOINTS.md, DATABASE_SCHEMA.md.
Prompt caching for Claude API to reduce latency by up to 85% and costs by up to 90%. Activate for cache_control, ephemeral caching, cache breakpoints, and performance optimization.
Prompt engineering specialist for system prompt optimization. Designs effective prompts, A/B testing, prompt injection detection, AI response quality.
Promptfoo evaluation framework for testing and comparing LLM outputs. Use when writing eval configs, creating test cases, debugging eval runs, or working with assertions.
Serial protocol analysis and debugging for common embedded interfaces (I2C, SPI, UART)
Pick up a GitHub issue and implement it. On the first story for an Epic, freezes the drafty spec from the Epic body into docs/specs/.md as part of the story's PR.
Full feature/refactor ceremony: brainstorm → spec → eng-review → decompose → file Epic + sub-issues. Drafty spec lives in the Epic issue body (web-UI editable); it's frozen to…
Develop, validate, and adapt measurement instruments including factor analysis, reliability testing, and cross-cultural validation
Publish a public website safely: DNS, web server, HTTPS, hardening, verify. Routes raw dev servers through nginx/Caddy/Apache/Cloudflare Pages.
Run ty (Astral's Python type checker) on Python code. Use when writing, editing, or reviewing Python code to catch type errors.
Manage Python projects with uv (Astral's package/project manager). Use when creating Python projects, adding dependencies, running scripts, or managing Python versions.
ML-specific testing skill using pytest with fixtures for data, models, and predictions.
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning.
Expert-level Python development with Python 3.12+ features, async/await, type hints, and modern best practices
Production validation specialist for post-deployment smoke tests, SEO audits, visual regression, and analytics verification.
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything — from…
Technical debt management and prioritization. Trigger when the user wants to identify, prioritize, or plan the repayment of technical debt.
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory…
Different techniques to optimize the performance of Qdrant, including indexing strategies, query optimization, and hardware considerations.
Batch embedding generation with caching, rate limiting, and multiple provider support
RAG systems analyst and architect skill. Collects and clarifies requirements through structured dialogue, then transforms unstructured business or developer descriptions into…
Use when React Hooks patterns including useState, useEffect, useContext, useMemo, useCallback, and custom hooks. Use for modern React development.
Use when handling platform-specific code in React Native for iOS and Android. Covers Platform API, platform-specific components, native modules, and cross-platform best practices.
Generates PDF documents using the React-PDF library (@react-pdf/renderer) with TypeScript and JSX.
Captures conversation sessions into structured summaries, pushes observations to ai-memory entities, creates Notion todos, and creates Notion notes.
Plans large-scale refactoring campaigns across codebases. Analyzes dependency graphs, calculates blast radius, designs migration strategies, and creates incremental plans that…
Perform a behavior-preserving structural refactor that deepens a module — turning a small amount of behaviour behind a large, leaky interface into a large amount of behaviour…
Architect interactive WebGL2 and WebGPU 3D scenes using Three.js or React Three Fiber with compressed GLTF streaming, PBR materials, and post-processing pipelines.
Resolve an in-progress git merge or rebase conflict end to end: read the conflict state, recover each side's original intent, resolve every hunk, run the project's checks, and…
Reverse engineers business logic from source code by extracting operational business truth. Use when user asks to understand what the system actually does, analyze business rules,…
Pre-landing review workflow for Codex. Analyze the diff against the default branch for structural bugs, trust-boundary issues, race conditions, missing tests, and other problems…
Svelte 5 and SvelteKit: runes reactivity, component composition, routing, data loading, form handling. — from JasonWarrenUK/goblin-mode
Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks.
Select and configure the appropriate command runner based on Docker Compose standard, Symfony Docker (FrankenPHP), or host environment
Enterprise integration solutions using SAP Integration Suite on BTP. Covers Cloud Integration (iFlows), API Management, Event Mesh, Edge Integration Cell, Integration Advisor,…
Right-sizes architecture to project scope. Prevents over-engineering by classifying projects into 6 tiers and constraining pattern choices accordingly.
Modernizes legacy scripts (bash, Node, Python) by replacing deprecated APIs, adding error handling, converting callbacks to async/await, and improving maintainability.
Execute the MAD-based single-cell RNA-seq QC workflow (scripts + Python API) to filter low-quality cells and emit reports plus filtered AnnData files. — from bg-szy/TOP-SKILLS
Seldon Core deployment skill for model serving, A/B testing, and canary deployments on Kubernetes.
Selenium WebDriver expertise for cross-browser automation and legacy system testing
Семантический воркфлоу для кода через Serena MCP - приоритет перед raw reads и grep. Используй для: изучи код, проиндексируй проект, найди символы, найди ссылки на символ,…
Exploration symbolique du code avec Serena MCP. Utiliser pour naviguer dans le code par symboles (fonctions, classes, hooks), trouver des définitions, et comprendre l'arc — from…