Total 51,191 skills
Showing 12 of 51191 skills
通过 EHunt Shopify 商品查询（网关路由 `ehunt/shopify/productQuery`）按多维度筛选独立站 Shopify 商品（关键词/URL、价格、周销量、上架时间、Facebook 广告、竞争度、是否有货源、发货国家等）。当用户提到 EHunt Shopify 商品、Shopify 选品、独立站选品、Shopify 爆款、Shopify dropshipping、独立站铺货、Facebook 广告商品、Shopify product query、shopify items 时触发。即使用户未写 EHunt，只要在 Shopify 独立站上搜商品、看周销量/销售额/竞争度或筛品，也应触发此技能。
Temu 全球站（非 US/EU）订单管理 API，经 LinkFox 网关转发 9 个 bg.order.* / temu.order.* / temu.local.order.* 接口，默认 site=global、tokenPurpose=order-shipping。当用户提到 Temu Global 订单、全球站订单列表、parentOrderSn、订单金额 V2、temu.order.amount.v2.query、合并发货、SN鉴真、verification upload 时触发。美国站用 linkfox-temu-order-us；欧洲站用 linkfox-temu-order-eu；商品用 linkfox-temu-manage-product-global；价格用 linkfox-temu-price-global。
通过 EHunt Temu 品类检索（网关路由 `ehunt/temu/temuCategorySearch`）在已同步到本地库的 EHunt Temu 类目数据中按关键词检索类目中文名、英文名与类目 id，用于商品/店铺筛选的类目 id。当用户提到 EHunt Temu 类目、Temu category id、Temu 类目树、Temu 后台类目、temu 品类、syncTemuCategory（Temu 品类同步）后查类目、Temu category search 时触发。即使用户未写 EHunt，只要在本地已同步的 Temu 类目库里按关键词找类目 id，也应触发此技能。
Call the Recoup API and external connectors directly — fetch any platform resource (artists, socials, organizations, research, documents) and run connector actions (Google Docs/Sheets/Drive edits, Gmail, TikTok, Instagram). Use whenever you need raw Recoup data, a platform resource, to write curl against api.recoupable.dev, or to read/write something outside Recoup like a Google Doc URL or a spreadsheet. The plumbing every other skill rides on. To onboard or operate on an artist use the recoup-roster-* skills; for first-run connection use recoup-platform-connect-account.
Make sure your code is ready to commit, then stage changes into clean, atomic commit. Use before committing.
Check whether the Meticulous CLI (@alwaysmeticulous/cli) is installed and up to date, and install/update it if not. Invoked at the start of every other Meticulous skill, since the CLI is under active development with frequent changes and improvements.
Clarify or discuss a proposed task, plan, design update, or ADR by resolving the highest-value unresolved decisions, decision criteria, trade-offs, and option boundaries until the inputs are ready for task creation, task planning, task/design updates, ADR writing, or safe implementation continuation. Use this as the default path when the user asks to clarify, discuss criteria, compare options, stress-test a design, or otherwise resolve material unresolved questions before proceeding. When clarification ends, resume the invoking workflow. It may also be used for general grilling when explicitly selected or when no other default grilling skill is available.
README construction — initialize template structure, generate per-package READMEs from doc comments, plan writing tasks, assemble root README from docs/ and package READMEs via doc.json config, and verify edits with `plan drift`.
Book Teardown. Calm, concise, sharp, and straightforward. Explain five key points clearly: What question is the author answering? What unproven assumptions does the author base their argument on? What framework do they use to analyze the topic? What conclusions do they reach? Finally, a few sentences of God's-eye view compression of the entire book. Use this when the user says '拆书', '拆这本', '分析这本书', '这本书在讲什么', '上帝之眼看这本书', '压缩一本书', 'book', or shares a book name requesting structural analysis. DO NOT use for chapter summaries (use Fabric extract_wisdom), papers (use ljg-paper), deep dives into a single viewpoint (use ljg-think), or ranking within a field (use ljg-rank).
High-agency frontend skill that gives AI good taste with tunable design variance, motion intensity, and visual density to stop generic UI slop.
Publication-ready matplotlib figures for Nature/high-impact journals and academic papers. Covers bar charts, grouped bars, heatmaps, line/trend plots, forest plots, microscopy-style image panels, schematic + quantitative composites, radar plots, and multi-panel layouts with Nature-style typography (Arial/sans-serif), restrained color systems, and SVG/PDF export conventions. Use when creating scientific figures that must match Nature publication standards. Do NOT use for interactive dashboards (Plotly, Bokeh) or Illustrator/Figma-first infographic workflows.
Long-form Web Novel Rankings Scan. Analyze ranking data from platforms such as Qidian, Tomato Novel, Jinjiang Literature City, etc., to extract market trends and popular genres. Trigger methods: /story-long-scan, /long-form-ranking-scan, "What's hot in long-form novels", "Qidian rankings"