nexscope-ai/nexscope-ecommerce-skills / ecommerce-geekbi-temu-market-research
ecommerce.geekbi-temu-market-research
VerifiedAnalyze public Temu category opportunities and keyword demand through Nexscope.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.1 KB |
| manifest.json | config | 514 B |
| references/api.md | markdown | 17.9 KB |
| references/testing.md | markdown | 1.2 KB |
| scripts/geekbi_temu_category_list.py | script | 18.0 KB |
| scripts/geekbi_temu_category_search.py | script | 20.6 KB |
| scripts/geekbi_temu_keyword_search.py | script | 21.2 KB |
| scripts/geekbi_temu_site_list.py | script | 17.9 KB |
SKILL.md
View on GitHub---
name: ecommerce.geekbi-temu-market-research
description: Analyze public Temu category opportunities and keyword demand through Nexscope.
---
# Nexscope Temu Market Research
## Scope
Category opportunity discovery, keyword-demand research, site lookup, category trees, filters, and daily, weekly, or monthly trends.
Public-market research only. It does not access a Temu seller account or perform product, order, advertising, or fulfillment mutations.
Read [references/api.md](references/api.md) for the authoritative source-derived request and response contract.
## Operations
| Script | Nexscope route |
|---|---|
| `geekbi_temu_category_list.py` | `POST /api/v1/tools/research/geekbi/temu/categoryList` |
| `geekbi_temu_category_search.py` | `POST /api/v1/tools/research/geekbi/temu/categorySearch` |
| `geekbi_temu_keyword_search.py` | `POST /api/v1/tools/research/geekbi/temu/keywordSearch` |
| `geekbi_temu_site_list.py` | `POST /api/v1/tools/research/geekbi/temu/siteList` |
## Response handling
For the research HTTP response, require a numeric outer `code` equal to `0` before using `data`. Nonzero codes are platform failures; display outer `msg` without interpreting its wording as a retry instruction. Nexscope preserves upstream messages and translates Chinese to English; successful responses may have `msg: null`. HTTP 200 alone and nested business `code` / `status` do not replace the platform check. See `references/api.md` for response paths and task-specific states.
Package scripts that unwrap the response keep the platform `code` and `msg` under `_nexscope`; their remaining fields are the business payload. `_nexscope.cost` is elapsed time, not credits.
## Authentication and safety
- Set `NEXSCOPE_PROXY_BASE` and `NEXSCOPE_API_KEY`. Send the Nexscope key as `Authorization: Bearer <key>`.
- No marketplace account authorization is required; these operations read public-market data.
- Provider credentials and upstream tokens remain backend-owned. Never accept, print, or persist them.
- Treat HTTP 401 as Nexscope authentication failure and HTTP 402 as insufficient Nexscope credits.
- Do not substitute another account, market, region, creator, product, or operation after an authorization or ambiguous network failure.
- This operation consumes credits. Preserve `X-Cost-Token` and `X-Cost-Credit` from response headers as server-reported billing metadata.
## Workflow
1. Identify the exact operation, market/account context, filters, dates, pagination, and requested output.
2. Validate required fields, types, enums, ranges, and operation-specific limits against `references/api.md` before any request.
3. Explain that additional pages, markets, or operations may consume more credits and obtain approval before a paid call.
4. Run only the selected entry script, for example: `python scripts/geekbi_temu_category_list.py '<JSON parameters>' --no-cache` when the script supports that flag.
5. Preserve the full response under `nexscope/<date>/<session>/data`; return a concise summary and the saved path.
6. On an ambiguous timeout or upstream failure, do not retry automatically. Report the trace ID and reconcile state first.
## Output rules
- Distinguish the Nexscope transport envelope from the nested business response.
- Report only returned facts. Preserve absent values as unknown and keep provider-specific metric definitions intact.
- Never expose API keys, provider tokens, presigned URL query strings, internal account records, or raw secrets.
- Do not submit feedback or make any unrelated external mutation unless the user explicitly requests it.
## Authentication
Set the `NEXSCOPE_API_KEY` environment variable. If credentials are missing or expire, visit [https://www.nexscope.ai/help/skills-external-access?co-from=skillNS](https://www.nexscope.ai/help/skills-external-access?co-from=skillNS) to top up credits.
Legacy local cache: a still-valid cache created before this response contract remains usable without a new paid request. The scripts mark its copied metadata as `_nexscope.responseContract = "legacy-cache"`, with `_nexscope.code` and `_nexscope.msg` set to `null` because the original platform status/message is unavailable. Do not infer platform success from business `errcode`, `code`, or `status`. Existing business data, billing metadata, cache contents and expiration are preserved; the marker is added only to the in-memory output.
## API Key request rate
All Nexscope API Keys belonging to the same user share one request-rate allowance for public API execution. The allowance is measured over any rolling 1-second window. Your RPS depends on your account entitlements; do not assume every user has a fixed 1 RPS. A single Skill operation may make multiple public API requests, and each request uses this allowance.
If an execution request returns HTTP 429 with outer code `13012`, the request-rate allowance was exceeded. Honor the returned `Retry-After` before considering another request. Outer code `13013` means the concurrent-request limit was exceeded, not the rate limit; honor its `Retry-After` when supplied. Inspect the response and reconcile state before retrying. Never automatically replay a write operation or a request whose outcome is unclear.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |