DevOps

DevOps Captain - Infrastructure-as-code, Kubernetes, CI/CD, and automation specialist

Tracks complex, multi-session work with dependency graphs using bd (beads) issue tracker. Triggers on 'multi-session', 'complex dependencies', 'resume after weeks', 'project memory', 'persistent context', 'side quest tracking', 'portfolio', 'all my beads', 'cross-project beads', or when TodoWrite is insufficient for scope. For simple single-session linear tasks, TodoWrite remains appropriate. (user)

Align language learning content to CEFR framework (A1-C2), design can-do statements for each proficiency level, create language assessment rubrics, and map content progression. Use for language learning curriculum. Activates on "CEFR", "language proficiency", "A1", "B2", or "language curriculum".

PC application security analyzer for Windows/macOS/Linux executables. Static analysis (SAST) for desktop applications including PE/ELF/Mach-O analysis, dependency scanning, SBOM generation. Integrates with cve-checker and cra-code-reviewer for CRA compliance. Triggers on: PC app analysis, Windows exe, macOS app, Linux binary, PE analysis, ELF analysis, desktop security, SBOM generation, dependency scan.

Dynamic task distribution, work-stealing algorithms, queue management, and adaptive load balancing. Use for optimizing task execution across agents, preventing overload, and maximizing throughput.

Create technical design documents for ABP Framework features including API contracts, database schemas, and architecture decisions. Use when: (1) designing REST APIs, (2) planning database schemas, (3) creating technical specifications, (4) documenting architecture decisions (ADRs).

Master orchestration skill for ProSWARM Neural MCP - ALWAYS use this for complex tasks requiring decomposition, planning, or parallel execution. Leverages 70+ specialized neural models for instant task classification and orchestration with 84.8% SWE-Bench accuracy. Use when user asks to solve problems, fix bugs, implement features, or any multi-step task. PRIMARY workflow engine for ALL development work.

Apply targeted fixes to failing artifacts based on validation issues. Improves hook density, singability, rhyme tightness, section completeness, and profanity compliance with minimal changes. Use after VALIDATE fails (≤3 iterations) to address specific quality issues before re-composing.

Empirical validation workflow for blockchain data collection pipelines before production implementation. Use when validating data sources, testing DuckDB integration, building POC collectors, or verifying complete fetch-to-storage pipelines for blockchain data.

Master philosophy of science - scientific method, explanation, realism, theory change. Use for: scientific methodology, explanation, realism/anti-realism, paradigms. Triggers: 'scientific method', 'falsification', 'Popper', 'Kuhn', 'paradigm', 'scientific explanation', 'scientific realism', 'instrumentalism', 'theory change', 'confirmation', 'induction problem', 'underdetermination', 'demarcation', 'reduction', 'emergence'.

Use this skill when users want to scrape web content and convert it to clean Markdown or PDF. Handles workflows like "Save this webpage as PDF", "Fetch this article", "抓取网页内容", or "转换为PDF". Supports crawl4ai for general web scraping and Playwright-based WeChat (微信公众号) article fetching with anti-bot bypass. Automatically converts to PDF by default unless user specifies Markdown-only.

Builds full-stack applications with SolidStart, combining Solid's fine-grained reactivity with server functions and multiple rendering modes. Use when creating SolidJS applications with SSR/SSG, server functions, or when user mentions SolidStart or Solid meta-framework.

Comprehensive guide for the Cloudflare Agents SDK - build AI-powered autonomous agents on Workers + Durable Objects.Use when: building AI agents, creating stateful agents with WebSockets, implementing chat agents with streaming, scheduling tasks with cron/delays, running asynchronous workflows, building RAG (Retrieval Augmented Generation) systems with Vectorize, creating MCP (Model Context Protocol) servers, implementing human-in-the-loop workflows, browsing the web with Browser Rendering, managing agent state with SQL, syncing state between agents and clients, calling agents from Workers, building multi-agent systems, or encountering Agent configuration errors.Prevents 15+ documented issues: migrations not atomic, missing new_sqlite_classes, Agent class not exported, binding name mismatch, global uniqueness gotchas, WebSocket state handling, scheduled task callback errors, state size limits, workflow binding missing, browser binding required, vectorize index not found, MCP transport confusion, authentic

Master monetization models, pricing strategies, and growth tactics. Learn to build sustainable business models and optimize plugin revenue.

Project-specific linting and type-checking commands. Customize for your project.

Load when analyzing performance metrics, creating reports, setting up tracking,evaluating growth experiments, or any task involving data-driven decision makingfor content and audience growth. Contains KPIs, benchmarks, and reporting frameworks.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use this skill when creating UI components, writing copy, designing layouts, or making any visual/brand decisions for the Planted website. Ensures consistency with Planted's challenger brand voice (inspired by Oatly's approach) and the established design system.

Spécialiste du secteur vétérinaire au Québec. Benchmarks, valorisations, analyse concurrentielle.

DEPRECATED - Use deploy-phoenix-client for production or deploy-rails-client for legacy Rails backend. This skill redirects to the appropriate deployment skill.