MSBuild and package version rules are easy to miss during .NET repository changes. This skill runs a focused architecture linter and explains the violations to fix.

Current software facts change faster than model training data. This skill prompts Claude, Codex, and Claude Code to verify versions, dates, and release status before answering.

Shortcut fixes can hide failures, delete tests, or suppress warnings. This skill adds completion integrity checks that flag risky commit patterns before review.

Complex code decisions need more than one perspective. This skill coordinates architecture and implementation reviewers, then merges findings for a stronger follow-up analysis.

Agents can report work as done before local tests and CI prove it. This skill defines a verification workflow that checks tests, GitHub Actions, failures, and final evidence.

ANcpLua users need quick answers across SDK, analyzer, and Roslyn utility docs. This skill maps topics to the right files and search patterns for precise documentation responses.

Modern Angular component APIs can be difficult to apply consistently across a project. This skill provides focused patterns for standalone, signal-based, accessible components.

Complex implementations often hide dependencies and block parallel work. This skill researches the codebase and produces validated, dependency-aware plans for coordinated agent execution.

Large development plans are slow and difficult to coordinate across concurrent tasks. This skill schedules Sparky subagents, validates results, integrates changes, and updates the source plan.

Custom Codex agents need precise TOML files and clear runtime settings. This skill guides role design, writes configs, and validates required fields.

Repository documentation and code can be difficult to inspect quickly across many projects. This skill retrieves and searches public repository content through GitMCP.

Complex technical requests can hide dependencies, risks, and unclear requirements. This skill produces phased plans with atomic tasks, acceptance criteria, and validation steps.

Complex engineering requests often lack clear sequencing, validation, and risk controls. This skill converts them into researched, phased plans with atomic tasks and review.

Large development plans are slow when independent tasks run sequentially. This skill schedules ready tasks in parallel, validates results, commits changes, and updates plan logs.

Large development plans are slow and difficult to coordinate across dependent tasks. This skill schedules subagents in dependency-aware waves, validates their work, commits changes, and updates plan logs.

OpenAI platform details change quickly, so memory can become outdated. This skill gives agents a repeatable way to search and fetch official OpenAI documentation.

Web pages can be difficult to extract and summarize. This skill routes suitable public pages through markdown.new for cleaner Markdown content.

Single-agent plans can miss risks and favor one model's perspective. This skill compares independent CLI plans, anonymizes them, and merges the strongest guidance.

Browser automation agents require a reliable screenshot and action loop. This skill provides a Playwright runner with Gemini Computer Use actions and safety prompts.

Plot contradictions and weak transitions can disrupt reader trust. This skill reviews story materials and proposes focused fixes in a clear table.