vibe-seller

Amazon listing CRUD via the category flat-file (Add Products via Upload). Create a variation family (parent + colour/size children), update attributes, change parent-child relationships, and delete SKUs — all in one template round trip. Also covers the end-to-end sourcing flow: a supplier link (e.g. 1688) → extract product data → local GPU-free OCR of detail images → generate title / bullet points / description → bilingual review with the user → propose the parent-child structure → fill the template → upload → read the processing report. Load this BEFORE any browser-use action on sellercentral.amazon.<tld>/listing/upload or when the task is to create / edit / delete a listing from a product link.

Common Amazon Seller Central / advertising-console mechanics — marketplace TLD map; version-aware navigation (New Seller Central 'NGS' vs classic, navigate by direct URL); sign-in as a challenge LOOP with Ziniao auto-fill of password / OTP (紫鸟验证码服务) / hosted passkey (已托管账号Passkey, native overlay → coordinate-click), Ziniao-stored-else-human rule; ad-console vs seller-central account caveat; capture rule. Prerequisite: every other amazon-* skill (amazon-ads, amazon-reports, amazon-invoice, amazon-listing / amazon-fbn / etc.) expects this loaded for cross-cutting auth and navigation patterns.

Save the workflow you just carried out as a reusable skill — OR update an existing skill — whenever the user asks to remember, reuse, or amend it. Triggers include "把这个任务的流程保存为技能", "save this workflow as a skill", "save to skill", "remember how to do this", "turn this into a skill", "next time do it the same way", AND update/extend phrasings like "update that skill", "extend the skill", "add this step to the skill", "make the skill also remember to…", "更新这个技能", "把这一步加到技能里", "让技能也记住…". Search the existing skills first, then EXTEND the one that already covers this workflow or CREATE a new one — never duplicate. Skills are saved/extended ONLY through the vibe_seller_save_skill MCP tool (the built-in Write/Edit tools do not persist skill files); they then auto-load for future tasks.

Common noon Seller Center mechanics — login (OTP auto-fetch), page-structure URL map, My Catalog read access, common modals, button-click patterns, project-ID discovery. Prerequisite: every other noon-* skill (noon-listing, noon-fbn, noon-exports, noon-ads) expects this loaded for auth and shared UI patterns.

Amazon Sponsored Products / Sponsored Brands / Sponsored Display ads + Coupons on Seller Central / advertising console. ONE catalog covering BOTH mechanics (URLs, click paths, modal patterns, kat-* component gotchas, field input ranges) AND workflows (tuning existing campaigns, weekly review, search-term harvest, ACOS improvement). Load this skill BEFORE any browser-use action that creates, edits, captures, archives, or downloads campaigns / ad-groups / keywords / product targets / coupons on amazon.<tld> or advertising.amazon.<tld>. The catalog below points to topical references — load whichever ones the task needs. Defaults to last 30 days for tuning analysis but accepts any user-specified window.

MUST load BEFORE running any browser-use command. This is the only bridge between the agent and the browser — browser-use 0.13 has NO subcommands (open/click/state are gone); you drive the browser by piping Python helper code via a heredoc. Contains the helper API, wrapper rules, session management, and store-task restrictions. Without this skill, browser commands will fail.

Noon listing operations — create SKU (3-step wizard) and edit listings (Offer / Content / Sizes / Groups tabs). Load when creating, editing, pricing, restocking, or updating content on a noon SKU.

Generate tax invoices from Amazon Seller Central order data using browser extraction and PDF generation

Amazon platform only. MUST load BEFORE taking any action when the task involves Amazon Seller Central report pages (Tax Document Library, Business Reports, Fulfillment, Payments CSV, Advertising Reports, etc.). Contains URLs, hover navigation, CSV structures, and wait times.

Noon data exports — Sales report (per country), Transaction View (multi-contract CSV with status enum gotchas), Catalog Exports (Content / Pricing / Stock / Reports). Load when downloading sales, finance, transaction, or catalog data from noon.

Noon Fulfilled-by-noon (FBN) — ASN creation flow, ASN status enum, inventory export, barcode print. Load when scheduling a shipment, managing FBN inventory, creating an ASN, or exporting warehouse stock.

Noon Ad Manager — campaigns (Auto / Manual / Brand), tuning audits, keyword research, negatives, Vantage analytics. Covers Targets / Customer Queries / Export Data flows. Load for any noon ads work — review, audit, tune, create. References under references/ for the tuning playbook (ads-tuning.md), creation guide (ads-creation.md), and keyword research (ads-keyword-research.md).

Collect product ratings + full customer-review history from Amazon (Seller Central / storefront) and noon, for every product in a store's catalog, and dump them as generic versioned JSON under store-data/<slug>/reviews/. Read-only: NEVER posts, replies to, edits, or deletes anything on Amazon or noon — it only reads review pages. Load this skill for any task that says collect/gather/refresh product reviews or ratings, build a review dataset, or audit customer ratings across a store. Produces one JSON per product (reviews/v1 contract) + a _MANIFEST.json index the server completeness reviewer checks. Defaults to FULL review history every run (idempotent, dedup by review id); accepts a per-(platform,country) scope from the store's metadata.json.

Taobao/Tmall 万相台无界 (one.alimama.com) ad analysis + campaign (计划) CRUD for a 千牛 store. Load before any browser-use action that reviews, audits, tunes, or reports on 万相台 计划 — 广告优化 / 每日(每周)广告优化 / 'review the ads' / adjust 计划. Analysis is bulk-first: download 报表 exports and parse them, rather than scraping the UI. Plan create/edit/delete is surfaced for HUMAN review, never auto-executed. Decision thresholds live in the store's ads-rules.md, never in this skill. Requires qianniu-shared for login + navigation.

Taobao/Tmall 千牛 listing (商品) CRUD via the Excel bulk round trip — 商品管理 → 更多批量操作 → excel商品批量导出 (export) → edit the workbook → excel商品批量编辑 / 批量导入 (import). One round trip creates/edits many 商品 at once (price, stock, title, attributes). Load before any browser-use action that lists, edits, prices, restocks, or bulk-updates 商品 on a 千牛 store. Prefer this bulk flow over per-item clicking; the single-item 发布商品 wizard is the fallback. Requires qianniu-shared for login + navigation.

Common Taobao/Tmall 千牛 (Qianniu) seller mechanics — chrome-backend login (QR scan or slider-captcha + SMS is a HUMAN step; NO auto-captcha), wrong-account guard (verify the logged-in 店铺名 matches the bound store, else ask), promo/公告/安全提示 popup detect-and-close on every page load, the 千牛 / 生意参谋 (sycm) / 万相台无界 (one.alimama.com) page map + SSO, per-store download dir, and GB18030 CSV caveat. Prerequisite: every other qianniu-* skill (qianniu-listing, qianniu-ads) expects this loaded for auth + navigation. Load before any browser-use action on a Taobao/Tmall (千牛) store.

Amazon listing CRUD via the category flat-file (Add Products via Upload). Create a variation family (parent + colour/size children), update attributes, change parent-child relationships, and delete SKUs — all in one template round trip. Also covers the end-to-end sourcing flow: a supplier link (e.g. 1688) → extract product data → local GPU-free OCR of detail images → generate title / bullet points / description → bilingual review with the user → propose the parent-child structure → fill the template → upload → read the processing report. Load this BEFORE any browser-use action on sellercentral.amazon.<tld>/listing/upload or when the task is to create / edit / delete a listing from a product link.

Amazon Sponsored Products / Sponsored Brands / Sponsored Display ads + Coupons on Seller Central / advertising console. ONE catalog covering BOTH mechanics (URLs, click paths, modal patterns, kat-* component gotchas, field input ranges) AND workflows (tuning existing campaigns, weekly review, search-term harvest, ACOS improvement). Load this skill BEFORE any browser-use action that creates, edits, captures, archives, or downloads campaigns / ad-groups / keywords / product targets / coupons on amazon.<tld> or advertising.amazon.<tld>. The catalog below points to topical references — load whichever ones the task needs. Defaults to last 30 days for tuning analysis but accepts any user-specified window.

Developer-only skill for poking at vibe-seller stores from outside the task system — inspect the SQLite DB, drive a store's browser-use wrapper directly via the CDP proxy, manage VIBE_TASK_ID for stable sessions, recover wedged daemons, find seller SKUs, and authenticate without the JWT cookie path. Load when the user says 'debug a store', 'why is store X broken', 'check the wrapper for store X', 'I need to drive Ziniao directly without creating a task', or anything that touches the runtime store layer outside the normal task → agent flow.

MUST load BEFORE running any browser-use command. This is the only bridge between the agent and the browser — contains all CLI syntax (open, click, hover, scroll, input, state, eval, etc.), wrapper rules, session management, and store-task restrictions. Without this skill, browser-use commands will fail or use wrong syntax.

Debug agent task execution infrastructure issues — wrong cwd, wrong files, wrong venv, browser startup failures, agent retry loops, skill loading failures

Generate tax invoices from Amazon Seller Central order data using browser extraction and PDF generation

Amazon platform only. MUST load BEFORE taking any action when the task involves Amazon Seller Central report pages (Tax Document Library, Business Reports, Fulfillment, Payments CSV, Advertising Reports, etc.). Contains URLs, hover navigation, CSV structures, and wait times.

Common Amazon Seller Central / advertising-console mechanics — marketplace TLD map, hamburger-menu hover navigation, sign-in / Ziniao auto-fill / OTP redirect handling, ad-console vs seller-central account caveat, capture rule. Prerequisite: every other amazon-* skill (amazon-ads, amazon-reports, amazon-invoice, future amazon-listing / amazon-fbn / etc.) expects this loaded for cross-cutting auth and navigation patterns.

Noon Ad Manager — campaigns (Auto / Manual / Brand), tuning audits, keyword research, negatives, Vantage analytics. Covers Targets / Customer Queries / Export Data flows. Load for any noon ads work — review, audit, tune, create. References under references/ for the tuning playbook (ads-tuning.md), creation guide (ads-creation.md), and keyword research (ads-keyword-research.md).

Noon data exports — Sales report (per country), Transaction View (multi-contract CSV with status enum gotchas), Catalog Exports (Content / Pricing / Stock / Reports). Load when downloading sales, finance, transaction, or catalog data from noon.

Noon Fulfilled-by-noon (FBN) — ASN creation flow, ASN status enum, inventory export, barcode print. Load when scheduling a shipment, managing FBN inventory, creating an ASN, or exporting warehouse stock.

Noon listing operations — create SKU (3-step wizard) and edit listings (Offer / Content / Sizes / Groups tabs). Load when creating, editing, pricing, restocking, or updating content on a noon SKU.

Common noon Seller Center mechanics — login (OTP auto-fetch), page-structure URL map, My Catalog read access, common modals, button-click patterns, project-ID discovery. Prerequisite: every other noon-* skill (noon-listing, noon-fbn, noon-exports, noon-ads) expects this loaded for auth and shared UI patterns.

Collect product ratings + full customer-review history from Amazon (Seller Central / storefront) and noon, for every product in a store's catalog, and dump them as generic versioned JSON under store-data/<slug>/reviews/. Read-only: NEVER posts, replies to, edits, or deletes anything on Amazon or noon — it only reads review pages. Load this skill for any task that says collect/gather/refresh product reviews or ratings, build a review dataset, or audit customer ratings across a store. Produces one JSON per product (reviews/v1 contract) + a _MANIFEST.json index the server completeness reviewer checks. Defaults to FULL review history every run (idempotent, dedup by review id); accepts a per-(platform,country) scope from the store's metadata.json.

Debug CI failures by downloading artifact logs, reading test code, and tracing agent LLM thinking to find root causes