Agent skill · Audited from source
1688-shopkeeper
skill · next-1688/1688-shopkeeperLicence not declaredAudited 20 Oct 2026 · source 3a033c0bf54c
Is it safe? With care — CAUTION, grade B (82/100). We read this skill's source at commit 3a033c0bf54c and observed network and shell access and no hard-coded secrets. The audit raised 6 findings, 0 critical or high. What it does: 1688选品铺货 + 商机趋势专家。用于:(1) 在1688搜索商品/选品找货源 (2) 查询已绑定的下游店铺 (3) 将商品铺货到抖音/拼多多/小红书/淘宝等平台 (4) 配置1688 AK密钥 (5) 查看即时商机热榜 (6) 查看类目/行业趋势与价格分布 (7) 生成店铺经营日报并输出主营商品选品建议。…
Cite
Cite this page
ModelsAtlas. “1688-shopkeeper (next-1688/1688-shopkeeper)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/next-1688/1688-shopkeeper
Trust audit
Audit 0.4.1 · source read 20 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkDeclared2 observations
- ShellDeclared3 observations
- DependenciesNot pinnedSome versions float
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | WARN | 5 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass, no license.
Findings (6)
MEDIUMCode injectioncode.dynamic_import · cli.py:50
mod = importlib.import_module(module_path)
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · cli.py:63
mod = importlib.import_module(commands[name])
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · cli.py:89
module = importlib.import_module(module_path)
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWInventory / provenanceinv.no_license
- Why
- no LICENSE file and no repo licence
- Fix
- add a licence
LOWInsecure cryptocrypto.weak_hash · scripts/_auth.py:74
md5_obj = hashlib.md5(body.encode('utf-8'))- Why
- No further detail recorded for this rule.
- Fix
- —
LOWSupply chainsupply.unpinned · requirements.txt
requests
- Why
- 1 requirement(s) not pinned with ==
- Fix
- pin exact versions
Audit 0.4.1 · source sha 3a033c0bf54c · 20 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishernext-1688 GitHub organizationOwner of the repository this skill is read from
- Source foldernext-1688/1688-shopkeeperThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdict3a033c0bf54cA new audit runs when the source changes
- Repository statusNot archivedLast push 211 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: 1688选品铺货 + 商机趋势专家。用于:(1) 在1688搜索商品/选品找货源 (2) 查询已绑定的下游店铺 (3) 将商品铺货到抖音/拼多多/小红书/淘宝等平台 (4) 配置1688 AK密钥 (5) 查看即时商机热榜 (6) 查看类目/行业趋势与价格分布 (7) 生成店铺经营日报并输出主营商品选品建议。…
---
name: 1688-shopkeeper
description: |
1688选品铺货 + 商机趋势专家。用于:(1) 在1688搜索商品/选品找货源 (2) 查询已绑定的下游店铺
(3) 将商品铺货到抖音/拼多多/小红书/淘宝等平台 (4) 配置1688 AK密钥 (5) 查看即时商机热榜
(6) 查看类目/行业趋势与价格分布 (7) 生成店铺经营日报并输出主营商品选品建议。
触发词:帮我找商品、在1688搜、选品、铺货、上架、查店铺、配置AK、商机、热榜、排行榜、趋势、价格分布、经营日报、店铺日报、动销分析、经营分析、选品建议、1688找货。
metadata: {"openclaw": {"emoji": "🛒", "requires": {"bins": ["python3"]}, "primaryEnv": "ALI_1688_AK"}}
---
# 1688-shopkeeper
统一入口:`python3 {baseDir}/cli.py <command> [options]`
## 命令速查
| 命令 | 说明 | 示例 |
|------|------|------|
| `search` | 找商品 | `cli.py search --query "帮我找1688上支持一件代发包邮的露营椅,100元以内" --channel douyin` |
| `prod_detail` | 商品详情 | `cli.py prod_detail --item-ids "991122553819,894138137003"` |
| `shops` | 查绑定店铺 | `cli.py shops` |
| `publish` | 铺货 | `cli.py publish --shop-code CODE --data-id ID` |
| `opportunities` | 商机热榜 | `cli.py opportunities` |
| `trend` | 趋势洞察 | `cli.py trend --query "大码女装"` |
| `shop_daily` | 店铺经营日报 | `cli.py shop_daily` |
| `configure` | 配置 AK | `cli.py configure YOUR_AK` |
| `check` | 检查配置状态 | `cli.py check` |
所有命令输出 JSON:`{"success": bool, "markdown": str, "data": {...}}`
**展示时直接输出 `markdown` 字段,Agent 分析追加在后面,不得混入其中。**
## 使用流程
Agent 根据用户意图**直接执行对应命令**,无需每次先执行 `check`。
各命令在 AK 缺失、店铺异常等情况下会自行返回明确错误,Agent 按下方「异常处理」应对即可。
**选品铺货典型路径**:`search` → 用户筛选 → `shops`(确认目标店铺) → `publish`
**商品详情使用指引**:
- `prod_detail`:用户想看商品标题、价格、类目、SKU、CPV 属性、商家信息时使用。
**商机/趋势使用指引**:
- `opportunities`:用户想看“此刻/近1小时/热榜/趋势商机”。
- `trend`:用户询问某宽泛类目/行业的周期趋势、价格分布、热品概况;关键词过长或过细时先按用户原词尝试,若空结果再提示用户换更宽泛/拆分词后重试。
- `shop_daily`:用户想看“店铺经营日报/今日动销/渠道经营诊断/主营商品选品建议”。
## 安全声明
| 风险级别 | 命令 | Agent 行为 |
|---------|------|-----------|
| **只读** | search, shops, check, opportunities, trend, shop_daily | 直接执行 |
| **配置** | configure | 提示影响范围后执行 |
| **写入** | publish | **必须先 dry-run 预检查;仅当写入目标不唯一时追问,目标唯一则直接执行** |
**全局写入规则(适用于所有写操作)**:
1. 必须先执行 dry-run。
2. 仅当写入目标不唯一(商品或店铺存在多个候选)时,才向用户追问一次做歧义消解。
3. 目标唯一时,dry-run 成功后直接执行正式写入,不再二次确认。
## 异常处理
任何命令输出 `success: false` 时:
1. **先输出 `markdown` 字段**(已包含用户可读的错误描述)
2. **再根据关键词追加引导**:
| markdown 关键词 | Agent 额外动作 |
|----------------|--------------|
| "AK 未配置" 或 "签名无效"/"401" | 输出下方 **AK 引导话术** |
| "授权过期" | 提示用户在 1688 AI版 APP 中重新授权 |
| "店铺未绑定" 或 shops 返回 0 个店铺 | 输出下方 **开店引导话术** |
| "限流"/"429" | 建议用户等待 1-2 分钟后重试 |
| 其他 | 仅输出 markdown 即可 |
详细错误码说明见 `references/common/error-handling.md`。
## 执行前置(首次命中能力时必须)
- 首次执行 `search` 前:先完整阅读 `references/capabilities/search.md`
- 首次执行 `prod_detail` 前:先完整阅读 `references/capabilities/prod_detail.md`
- 首次执行 `shops` 前:先完整阅读 `references/capabilities/shops.md`
- 首次执行 `publish` 前:先完整阅读 `references/capabilities/publish.md`
- 首次执行 `configure` 前:先完整阅读 `references/capabilities/configure.md`
- 首次执行 `opportunities` 前:先完整阅读 `references/capabilities/opportunities.md`
- 首次执行 `trend` 前:先完整阅读 `references/capabilities/trend.md`
- 首次执行 `shop_daily` 前:先完整阅读 `references/capabilities/shop_daily.md`
- 同一会话内后续重复调用同一能力可复用已加载知识;仅在规则冲突或文档更新时重读。
## AK 引导话术
> "需要先配置 AK。打开 [**1688 AI版 APP**](https://air.1688.com/kapp/1688-ai-app/pages/home?from=1688-shopkeeper)(没装的话点链接下载),首页点击「一键部署开店Claw,全自动化赚钱🦞」,进入页面获取 AK,然后告诉我:'我的AK是 xxx'"
## 开店引导话术
> "还没有绑定店铺。打开 [1688 AI版APP](https://air.1688.com/kapp/1688-ai-app/pages/home?from=1688-shopkeeper) → 首页「一键开店」,开好后告诉我。"
## FAQ 知识库(按需加载)
用户问经营或技术问题时,**先加载对应文件再回答**,不凭经验泛泛而谈。
| 用户话题 | 加载文件 |
|---------|---------|
| AK 问题、铺货失败、支持平台、收费 | `references/faq/base.md` |
| 选哪个平台、抖店/拼多多/淘宝 | `references/faq/platform-selection.md` |
| 选品风险、品类、节日选品 | `references/faq/product-selection.md` |
| 运费模板、定价、加价倍率 | `references/faq/listing-template.md` |
| 发货超时、中转费、偏远地区 | `references/faq/fulfillment.md` |
| 退货、仅退款、运费险、售后 | `references/faq/after-sales.md` |
| 新店破零、服务分、推广 | `references/faq/new-store.md` |
| 素材审核、白底图、标题优化 | `references/faq/content-compliance.md` |Excerpt, first 3,759 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 3a033c0
git clone https://github.com/next-1688/1688-shopkeeper git -C 1688-shopkeeper checkout 3a033c0bf54c
The author documents no install command, so this uses the repository directly. Our verdict covers commit 3a033c0bf54c only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
Audit history
Every audit, every source change
- !CAUTION B 82 / 100
first audit · source
3a033c0bf54c
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/next-1688/1688-shopkeeper/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
FreedomIntelligence/OpenClaw-Medical-Skills
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial,…
FreedomIntelligence/OpenClaw-Medical-Skills
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
romainsimon/paperasse
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER.
Add this badge to your README
[](https://modelsatlas.com/skills/next-1688/1688-shopkeeper/)
<a href="https://modelsatlas.com/skills/next-1688/1688-shopkeeper/"><img src="https://modelsatlas.com/skills/next-1688/1688-shopkeeper/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about 1688-shopkeeper
What does the 1688-shopkeeper skill do?
Is 1688-shopkeeper safe to install?
What can 1688-shopkeeper access on my machine?
Which assistants does 1688-shopkeeper work with?
How current is this page?
Sources
- github.com/next-1688/1688-shopkeeper — the audited source at commit 3a033c0bf54c and every finding aboveObserved · 20 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the 1688-shopkeeper skill do?
- Is 1688-shopkeeper safe to install?
- What can 1688-shopkeeper access on my machine?