DevOps

Protect repositories from accidental secret commits. Essential when working with AI agents.Use when: setting up new project, adding pre-commit hooks, scanning for secrets, fixing leaked credentials.Triggers: "настрой защиту секретов", "setup secrets", "check secrets", "scan secrets", "проверь секреты", "pre-commit", "gitleaks".PROACTIVELY suggest when creating new projects or when .pre-commit-config.yaml is missing.

Advanced intent interpretation system that analyzes user requests using cognitive science principles and extrapolates logical volition. Use when user requests are ambiguous, when deeper understanding would improve response quality, or when helping users clarify what they truly need. Applies probabilistic intent mapping, first principles decomposition, and Socratic clarification to transform vague requests into well-understood goals.

Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work. Use for Azure, .NET, Microsoft 365, Windows, Power Platform, and all Microsoft technologies. Get accurate, current information from learn.microsoft.com and other official Microsoft websites—architecture overviews, quickstarts, configuration guides, limits, and best practices.

Export Google Docs and Google Sheets (spreadsheets) to Markdown files or stdout. Use when asked to fetch, download, or ingest Google Docs/Sheets content for summarization, analysis, or context loading. Tries gcloud ADC first with browser OAuth fallback.

AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity.USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, generating continuation prompts, scoring feasibility risk, or adding editing metadata.PIPELINE POSITION: screenwriter → **production-validator** → imagine/arch-vINPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 promptsKEY FUNCTIONS: - Veo 3 feasibility validation with risk scoring (LOW/MEDIUM/HIGH/CRITICAL) - 8-second scene chunking with continuation prompts - Shot continuity tagging for editors - Technical optimization for AI-friendly alternatives

Analyzes completed projects to identify generalizable patterns, common workflows, and reusable knowledge worth extracting into skills. Use after completing a project to review LOG.md, skill updates, and project artifacts. Generates extraction recommendations but does not modify skills directly (user decides whether to apply via skill-updater).

Detect and fix memory leaks in Python and PyTorch code, especially matplotlib figures and unreleased tensors. This skill should be used during Phase 4 performance optimization when memory usage grows over time.

Use this skill after code changes are made, when reviewing implementations, checking code quality, or ensuring constitutional compliance. Apply when user mentions reviewing, analyzing, or checking code quality. Also use proactively after significant code implementations to verify they follow mini_agent framework principles.

[Extends solution-architect] GraphQL API specialist. Use for GraphQL schemas, Apollo Server/Federation, DataLoader, resolvers, subscriptions. Invoke alongside solution-architect for GraphQL API design.

Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.

Acts as an intellectual sparring partner to critique, challenge, and refine thinking through Socratic questioning and alternative perspectives. Activates automatically when detecting complex decision-making, strategic planning, or multi-consideration problems where critical evaluation adds value. Also activates when user explicitly asks to "challenge my thinking", "critique this idea", "what am I missing", "play devil's advocate", or similar requests for critical analysis. Includes synthesis mode to integrate feedback into refined positions.

Enterprise interactive survey orchestrator with AskUserQuestion tool integration, multi-select support, conditional branching, error recovery, and production-grade decision automation across all Alfred workflows; activates for requirement clarification, architectural decisions, risky operations, feature selection, and complex multi-step user interactions

APC Mini MK2 color palette reference with velocity values and custom RGB via SysEx. Use when user asks about "color", "velocity value", "RGB", "palette", "brightness", "LED color", or needs to set specific colors on the APC Mini MK2.

Comprehensive guide for building Computer Use Agents with the CUA framework. This skill should be used when automating desktop applications, building vision-based agents, controlling virtual machines (Linux/Windows/macOS), or integrating computer-use models from Anthropic, OpenAI, or other providers. Covers Computer SDK (click, type, scroll, screenshot), Agent SDK (model configuration, composition), supported models, provider setup, and MCP integration.

MCP (Model Context Protocol) server evaluation guide for creating comprehensive test suites with read-only, independent questions. Use when building MCP servers, creating evaluation frameworks, or testing LLM tool usage patterns.

Knative serverless platform for Kubernetes. Use when deploying serverless workloads, configuring autoscaling (scale-to-zero), event-driven architectures, traffic management (blue-green, canary), CloudEvents routing, Brokers/Triggers/Sources, or working with Knative Serving/Eventing/Functions. Covers installation, networking (Kourier/Istio/Contour), and troubleshooting.

Implement autonomous KB query functionality with SQL and ChromaDB tools for financial data analysis

Craft concise commit messages with technical precision

Manage deployment, Docker, CI/CD, server hardening, and infrastructure security. EXCLUSIVE to devops-engineer agent.

Write maintainable CSS using consistent methodologies and design systems. Use this skill when styling components with Tailwind, BEM, CSS modules, or styled-components. When working on files like styles/, *.css, *.scss, or component files with inline styles. When establishing design tokens for colors, spacing, and typography. When optimizing CSS for production with purging or tree-shaking.