UnoCSS projects often fail when generated utilities ignore the active presets and configuration. This skill grounds recommendations in project settings and focused UnoCSS references.

Library builds often need multiple formats, declarations, and package validation. This skill guides tsdown configuration, migration, framework integration, and troubleshooting.

Vue state patterns can become inconsistent and difficult to test. This skill provides proven Pinia guidance for stores, plugins, SSR, Nuxt, HMR, and testing.

JavaScript and TypeScript projects often accumulate inconsistent tooling and structure. This skill applies Anthony Fu's conventions for linting, testing, applications, libraries, and monorepos.

Running the correct SummitUI Playwright tests requires specific TUnit commands and filter syntax. This skill selects documented commands for focused runs, controlled parallelism, and reports.

Plugin repositories need consistent structure, validation, and release steps. This skill gives Claude, Codex, and Claude Code a focused guide for ANcpLua plugin work.

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.

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.

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.

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.

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.

AMap integrations require coordinated setup, security configuration, overlays, events, and service APIs. This skill provides focused guidance and examples for JSAPI v2.0 web projects.

Incomplete code and unclear instructions make construction software changes difficult to implement safely. This skill requests complete solutions with error handling and exact steps.

Invalid or inconsistent JSON can break APIs, configurations, and data workflows. This skill identifies errors, explains corrections, and produces clean structured output.