Development & Agent Automation Skills

Use when the user asks to improve AI-assisted development reliability, AGENTS.md, skills, tests, CI, hooks, review loops, agent workflow governance, loop engineering, agent automations, worktree isolation, maker/checker separation, or external state design for long-running agents. It designs feedforward guides, feedback sensors, verification gates, human decision points, and loop architectures from repository evidence.

Use when an AI agent is executing software development, code generation, refactoring, debugging, or system architecture tasks to enforce strict harness principles, self-verification gates, non-destructive editing, context collapse defense, and human-in-the-loop boundaries.

Use when designing, evaluating, or implementing Agent workflows, prompt chains, routing, planning, reflection, multi-agent collaboration, memory management, or other framework-agnostic LLM orchestration patterns.

Use when the user asks to create, review, debug, or modernize Azure Pipelines YAML for CI/CD, especially .NET builds, Azure App Service deploys, or IIS/on-premises deploys. Prefer bundled templates and verify task syntax against Microsoft docs when version-specific accuracy matters.

Use when the user gives vague, emotional, fragmented, screenshot-based, or complaint-style requirements and wants them converted into structured specs, acceptance criteria, or clarifying questions.

Use when the user wants to design, implement, review, or refactor software systems conforming to Clean Architecture principles. It structures code into Domain, Application, Infrastructure, and Presentation/API layers, enforcing inward-only dependencies. It advocates rich domain models, CQRS, and the Result pattern, operating on technology-neutral concepts without database or framework bindings.

Use when the user asks for a code review, audit, PR/diff review, bug risk scan, security/performance/style feedback, or validation of recent changes. Prioritize actionable findings with file and line evidence.

Use when writing, reviewing, debugging, or modernizing C code in .NET projects. Trigger for .cs/.csproj files, C language-version questions, nullable reference types, records, pattern matching, async/cancellation, or version-appropriate syntax from C 10+.

Use when the user asks to generate, update, or place a C interface from an existing class. Trigger for extracting public members, filtering virtual or non-public members, enforcing getter-only properties, and safely creating, appending, or replacing interface blocks.

Use when the user asks broad .NET questions or the project contains .sln/.csproj files and the exact ASP.NET/EF/C subdomain is not yet clear. Detect the SDK/project shape, run or recommend .NET CLI commands, and route to Minimal APIs, Web API, MVC, Tag Helper, EF Core, or C skills when appropriate.

Use when the task involves Entity Framework Core models, DbContext, migrations, LINQ queries, change tracking, database providers, performance tuning, or data access review in .NET projects.

Use when building, debugging, refactoring, or reviewing ASP.NET Core Minimal APIs, lightweight endpoints, route groups, endpoint filters, typed results,…

Use when building, debugging, refactoring, or reviewing ASP.NET Core MVC apps with Razor views, controllers, ViewModels, validation, Tag Helpers, View…

Use when the user asks to design, implement, refactor, or review custom ASP.NET Core Tag Helpers in C, including TagBuilder usage, strongly typed attributes, dependency injection, ProcessAsync, and reusable Razor UI behavior.

Use when building, debugging, refactoring, or reviewing controller-based ASP.NET Core Web APIs, including ControllerBase, ActionResult , Problem Details, API versioning, global exception handling, DTOs, and OpenAPI behavior.

Use when you need to inspect a target project codebase and generate or improve a tailored, comprehensive AGENTS.md file (Harness Workflow Specification) that enforces strict AI agent harness rules, feedback sensors, execution SOP, orchestration topologies, and safety redlines. Supports non-interactive script execution via scripts/generate-agents-md.py. The generated AGENTS.md MUST NOT exceed 32 KiB in size.

Use when writing, reviewing, debugging, or modernizing JavaScript across browser, Node.js, and pure JS projects. Trigger for ES module/CommonJS issues, async patterns, functional array/set/iterator code, DOM/runtime behavior, or version-aware ECMAScript syntax.

Use when explaining OpenTelemetry concepts, choosing telemetry signals, planning or reviewing Collector architectures and declarative configuration, operating or troubleshooting telemetry pipelines, securing telemetry data, evaluating zero-code instrumentation, or planning Prometheus, OpenCensus, or OpenTracing interoperability and migration. Do not use it to write language SDK/API instrumentation code or custom Collector components.

Use when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.

Use when writing, reviewing, debugging, or architecting Python 3.10+ code, including type hints, structural pattern matching, dataclasses, async/task groups, packaging-aware project structure, testability, and maintainability.

Use when the user asks how to install, add, remove, update, or run Python dependencies; choose between uv, Poetry, venv, or pip; create/sync a virtual environment; or diagnose Python package manager setup from pyproject.toml, lock files, or requirements.txt.

Use when writing, refactoring, debugging, or auditing Rust code. Trigger for .rs files, Cargo projects, ownership/borrowing/lifetime issues, Result/Option error handling, unnecessary clone/performance work, unsafe code review, or modern Rust architecture.

Use when the user wants to polish, rewrite, shorten, or review prose so it sounds natural rather than AI-generated. Trigger for Traditional Chinese or English drafts, technical docs, code comments, commit messages, PR descriptions, sales copy, and requests to remove AI tells, slop, fluff, or formulaic phrasing.

Use when the user asks to design, create, review, or convert sub-agents, custom agents, worker/reviewer/planner agents, background agents, or multi-agent workflows for Antigravity CLI, Codex, Claude Code, GitHub Copilot CLI, or neutral agent blueprints.