Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Compare and merge two design docs for the same feature into a single source of truth. Use when you have competing or complementary design/implementation docs (e.g. from separate design runs) that need reconciling into one unified document.
Extract structured resources (icons, metadata, text, forms, videos, social links) from any webpage using playwright-cli. Supports individual collectors via subcommands (icons, metadata, text, forms, videos, socials) or all at once. The icon collector classifies SVGs as icon/logo/image based on size and DOM context, optimizes them for EDS, and outputs to /icons/ for use with decorateIcons(). Use when migrating pages, auditing sites, or extracting assets.
Use this when the page-import pipeline needs to analyze the content sequences within a single section and describe them neutrally for AEM Edge Delivery Services. Covers identifying breaking points between default content and blocks, one section at a time. Do not invoke directly — called by page-import per section.
Reduce a webpage to a structural skeleton with semantic tokens. Two-phase pipeline: Phase 1 injects a browser script that tokenizes content ({TEXT}, {HEADING:n}, {IMAGE:WxH}, {CTA:label}, {LINK:label}, {INPUT:type}, {VIDEO}, {ICON}). Phase 2 applies LLM structural reasoning to collapse repeated patterns ({REPEAT:N}), remove decorative wrappers, strip utility classes, and produce skeleton.html + manifest.json. Use when migrating pages to EDS, analyzing page structure, extracting page blueprints, or preparing input for GenAI block generation. Triggers on: reduce page, page skeleton, page blueprint, extract structure, tokenize page, page reduction, structural skeleton, reduce URL.
Capture a spatial hierarchy of rendered DOM elements from any webpage. Injects a pre-built script via playwright-cli that walks the DOM, detects layout grids, extracts backgrounds, prunes invisible nodes, promotes elements rendered outside their DOM parent (overlays, fixed navs, modals), and tags overlay nodes with occlusion metadata. Returns three outputs: LLM-friendly indented text, structured JSON tree, and a nodeMap mapping positional IDs to CSS selectors with background and overlay data. Use before page decomposition, overlay detection, brand extraction, or any workflow that needs structured page analysis. Triggers on: visual tree, capture tree, page structure, page hierarchy, DOM tree, capture visual, page analysis, extract tree.
基于项目代码 + README + CLAUDE.md 生成中英文 2 张项目概览图。当前 DashScope 文生图模型在多文字 + 信息图场景下文字易错位（详见 README.md），已回退 docs/project-overview-{en,zh}.png 到 mermaid 版本作为 baseline；skill 框架已搭好（generate.py + check.py + 异步 + 重试 + 文本检查），等更好模型可一键启用。
Refresh the awesome-ev-charging project listing's metadata (stars, forks, pushed_at, dormant/archived signals) and re-render it into README.md — the periodic maintenance pass, with no new repo to add and no issue to close. Use this whenever the user wants to "refresh the metadata", "update the stars", "re-run the pipeline", "mets à jour la liste / les métadonnées", "rafraîchis le README", or otherwise bring the generated listing up to date with GitHub. Handles the cache-vs-TTL decision (whether to clear cache_github/ before re-fetching) that a plain re-run gets wrong. For ADDING or REMOVING a specific repo, use add-project instead. Never hand-edit README.md between the generated markers.
Use this when the page-import pipeline needs to fetch a source webpage and prepare it for import/migration to AEM Edge Delivery Services. Covers scraping content, extracting metadata, downloading images, and returning analysis JSON with paths, metadata, cleaned HTML, and local images. Do not invoke directly — called by page-import as a pipeline step.
Use when updating TulingResearch Plus architecture docs, MCP namespaces, or YAML contracts.
Use when maintaining the markdown vault, BM25-like index, graph edges, lint, or artifact ingestion.