An advertising-analysis and campaign-management workflow for Taobao and Tmall stores using the 万相台无界 advertising platform. A campaign is one set of ads managed toward a business goal.

Use it to download and analyze advertising reports, inspect current campaign settings, find campaigns worth scaling or products losing money, and recommend changes for a person to apply.

It helps separate reliable exported performance data from the platform's live display and identifies campaigns or products that may need attention without automatically applying changes.

qianniu-ads — Skill for Claude Code by zpoint

Install

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.

Clone the repo

git clone --depth 1 https://github.com/zpoint/vibe-seller

agentmods

npx agentmods add skills/zpoint/vibe-seller/qianniu-ads

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-ads/github.svg)](https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-ads)

Your own site

<a href="https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-ads"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-ads/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-ads"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 963 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 3
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 17
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 51
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00145	$0.00963
Opus 5	$0.00072	$0.00481
Sonnet 5	$0.00029	$0.00193
Haiku 4.5	$0.00015	$0.00096

Measured 13d ago against content hash 13481c252aac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qianniu-ads 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ads_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

app/skills_v2/qianniu-ads/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qianniu (Taobao/Tmall) Ads — 万相台无界 catalog

PREREQUISITE: ../qianniu-shared/SKILL.md — 万相台 is reached by SSO from the 千牛 session (no second login); the popup-close rule and the 0.13 heredoc CLI apply.

This is a catalog: procedure + report shape live in the references. The loop is — pull the performance data, find the 计划 worth scaling and the products bleeding money, and recommend the change; the human applies it. Analysis is read-only; this skill never auto-executes a 计划 change.

Bulk-first: analyze from 报表 exports, not the UI

万相台's 报表 exports are the performance source of truth (the plan list itself warns 「页面数据仅供参考，历史推广数据以报表数据为准」). Default flow:

Download the 报表 for the audit window (报表 on one.alimama.com; export lands in ~/.vibe-seller/downloads/<slug>/, GB18030 CSV or .xlsx).
Parse it — scripts/ads_report.py FILE normalises the rows (计划/宝贝 × 花费/成交/ROI/点击…) into TSV for the analysis.
Read the live plan list (references/mechanics.md) only for current state (状态 / 每日预算 / 出价 / target) that the report doesn't carry.

The plan-list DOM scrape in mechanics.md is the fallback for state the report lacks — not the primary data path.

References — load what the task needs

File	When
`references/mechanics.md`	any 万相台 read: routes (`#!/manage/onesite` etc.), date-window selector, plan-list extraction per 场景, the 报表 export flow, and the APPLY-phase (write) actions kept for review.

Decision thresholds are per-store, not here

What counts as "scale" (加投) or "cut" (删除) — ROI floors, spend caps, lookback — is store-specific and lives in stores/<slug>/ads-rules.md (same pattern as amazon-ads). This skill carries mechanics only; read the store's rules for the numbers. Do not bake thresholds into the skill.

Safety rails ⚠️

Analysis/audit phases are read-only. Toggling a 计划, editing 每日预算, changing 出价, deleting a product — all writes. Surface them as a recommendation for the user to review; never auto-execute.
Never click a promo CTA (开通/升级/领取/报名…) — see qianniu-shared § 4.
Save exports/captures to /tmp/<task>/; never knowledge/ or stores/.

Read the full file on GitHub · 67 lines

Files

What ships with it

3 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.

Changes

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.

13d ago First seen · 67 lines · 145 tokens per session scan A 13481c252aac

Subscribe to this mod's changes

qianniu-ads is a skill published in the GitHub repository zpoint/vibe-seller (67 stars, last pushed yesterday), licensed Apache-2.0. It adds 145 tokens to every session and 963 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.

E-commerce Marketing and SEO

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…

browser-act/skills · 124 tokens

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.

browser-act/skills · 48 tokens

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.

rorkai/app-store-connect-cli-skills · 60 tokens

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.

Bitterbot-AI/bitterbot-desktop · 53 tokens

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…

nexscope-ai/eCommerce-Skills · 126 tokens

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.

nexscope-ai/Amazon-Skills · 51 tokens