Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.

Create, update, or review Picoclaw skills. Use when writing a new skill, modifying an existing SKILL.md, turning a repeated workflow into a reusable skill, or organizing scripts, references, and assets for a skill.

Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.

Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.

Interactive quiz that maps your AI/ML knowledge to a starting point in the 523-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead"

Use this skill to finalize a release. It stamps the [Unreleased] changelog section with a version and date, runs bumpversion to update all version files, and creates the release commit and tag. Only run this when you're ready to ship.

Use this skill to add a new TTS engine to Voicebox. It walks through dependency research, backend implementation, frontend wiring, PyInstaller bundling, and frozen-build testing. Always start with Phase 0 (dependency audit) before writing any code.

Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad

Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'

Use when reviewing string concatenation involving counts, translation key lookups, or i18n library configurations to check whether plural forms are handled correctly for all target locales.

Use when reviewing image assets, markup, and CDN or build transforms related to Use <picture> with an <img> fallback. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Use when reviewing an HTTPS page for resources (scripts, images, stylesheets, iframes) that are loaded over plain HTTP.

Use when reviewing dashboards, admin tables, search results, or feeds with many repeated items. Confirm the bottleneck is DOM or rendering cost before introducing virtualization because small lists usually do not need the added complexity.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Ensure logical focus order. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when reviewing custom element class definitions or Web Component source code to check for missing ARIA reflection, keyboard handling, and form association.

Use when reviewing templates, rendered HTML, or shared components related to Implement accessible breadcrumb navigation. Validate the final browser-facing markup, not just the source framework abstraction.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Remove focusable elements from aria-hidden containers. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。

长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」。