AI models often answer the wrong layer of complex user inputs, leading to drift, overreach, or fake certainty. Structure judgment analyzes inputs to identify the primary structural problem and routes to the correct handling layer before responding.

Prevents common reasoning failures where AI models present inference as observation or give costless recommendations. This skill enforces structural discipline through six systematic checks that ensure claims are properly grounded and uncertainty is honestly represented.

Developers spend hours on repetitive tasks like running builds, tests, and deployments. This skill provides ready-to-use templates for npm scripts, Makefiles, Git hooks, and CI/CD pipelines to automate these workflows.

Software projects lack consistent test coverage and face frequent bugs. This skill provides comprehensive testing strategies covering unit, integration, and E2E testing with practical examples and best practices.

Transform vague feature requests into actionable development tasks with clear acceptance criteria. Apply agile best practices like INVEST criteria and MoSCoW prioritization to deliver predictable sprint outcomes.

Stop guessing task durations and start planning with confidence. This skill applies proven agile estimation techniques to help your team reach consensus on story points, identify risks early, and create realistic sprint plans.

Running disorganized standups wastes team time and misses blockers. This skill provides structured templates and formats for efficient daily standups that keep agile teams synchronized.

Quickly configure consistent development and production environments using Docker Compose, environment variables, dev containers, and infrastructure templates.

Teams struggle to run effective retrospectives that produce actionable outcomes. This skill provides proven retrospective formats and facilitation guidance to help teams continuously improve their processes.

This skill helps developers improve application speed and efficiency through proven optimization techniques including React performance, lazy loading, caching, and database query optimization.

Vague requirements and incomplete tasks waste development time. Ralph provides specification-first methodology with autonomous iteration until verification passes, ensuring tasks complete properly.

Catch implementation mistakes before code is written by reviewing AI agent plans in a visual browser interface. Annotate plans with structured feedback, approve or request changes, and auto-save to Obsidian or Bear Notes.

AI assistants lose context across sessions, repos, and dates, forcing users to repeat background and re-explain decisions. OpenContext provides a lightweight context store that preserves project knowledge, decisions, and conclusions for consistent multi-session collaboration.

Complex tasks require coordinated effort across multiple AI agents. OMC provides teams-first orchestration with 32 specialized agents and smart model routing for efficient task completion.

Managing complex projects across multiple AI agents is fragmented and error-prone. This skill provides a unified orchestration layer with specialized agents, Serena Memory state sharing, and real-time observability dashboards.

This skill helps developers and DevOps engineers quickly identify errors, performance bottlenecks, and security threats in application logs using proven command-line techniques.

Managing external Git repositories as submodules can be complex. This skill provides step-by-step commands and examples for adding, updating, cloning, and removing Git submodules in your projects.

This skill helps AI assistants design optimized database schemas for SQL and NoSQL databases. It provides structured guidance for entity modeling, relationship design, indexing strategies, and migration scripts.

This skill automates GitHub Copilot Coding Agent to transform issues into Draft Pull Requests with a single label. Team members add the ai-copilot label, and Copilot handles implementation automatically.

This skill enables AI assistants to conduct professional code reviews by checking for bugs, security issues, code quality, and best practices. It provides structured feedback for pull requests.