Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zpoint/vibe-sellernpx agentmods add skills/zpoint/vibe-seller/qianniu-listingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-listing)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-listing"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-listing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-listing"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-listing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00137 | $0.01261 |
| Opus 5 | $0.00068 | $0.00630 |
| Sonnet 5 | $0.00027 | $0.00252 |
| Haiku 4.5 | $0.00014 | $0.00126 |
Grade A, and why
qianniu-listing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qianniu (Taobao/Tmall) — Listing CRUD (Excel bulk round trip)
PREREQUISITE:
../qianniu-shared/SKILL.md(chrome login is a HUMAN step; the popup-close rule; page map; per-store download dir; GB18030 CSV; the 0.13 heredoc CLI +cdp()-not-in-js()gotcha).
千牛 商品管理 has a first-class Excel bulk surface — the batch
equivalent of the per-item 发布/编辑 wizard, and the default for touching
more than one 商品. Entry point (verified live 2026-07-03): 商品管理
(https://myseller.taobao.com/home.htm/SellManage/on_sale) → 更多批量操作 →
| Menu item | Purpose |
|---|---|
| excel商品批量导出 | download the selected/all 商品 as an .xlsx workbook |
| excel商品批量编辑 | download the editable workbook (edit → re-upload) |
| 批量导入 | upload the edited workbook to apply changes |
| 批量编辑商品属性 / 批量设置运费 | scoped batch edits (attributes / shipping) |
Work it like a human: export → inspect → edit → import → verify
The workbook's exact columns are category-specific and change over time —
do NOT hardcode them. Run the loop a human runs (same philosophy as
amazon-listing):
- Export a fresh workbook (
excel商品批量导出) for the target 商品. It lands in~/.vibe-seller/downloads/<slug>/. inspectit —listing_bulk.py inspect WORKBOOK.xlsxdumps the header row + the columns actually present (商品ID, 商品标题, 价格, 库存, the SKU sub-table, etc.). The header names are the ground truth, not this doc.fill— set values by header name for the rows you're changing (listing_bulk.py fill … --spec spec.json --out out.xlsx). Touch only the columns you mean to change; leave the rest as exported.- Import the edited workbook (
批量导入) — a WRITE; only after the user has reviewed the diff. Then read the import result. - Verify on the source of truth, not the submit toast: re-open 商品管理 (or the 商品 detail) and confirm the change landed. Import results also surface a per-row success/failure list — read it and fix exactly the rows/ fields it flags, then re-import (self-correct loop).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 93 lines · 137 tokens per session scan A 895626db261f
qianniu-listing is a skill published in the GitHub repository zpoint/vibe-seller (67 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 1,261 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.