Influencer Commerce Intel
Analyze creator commerce performance and monetization potential with direct mapping to commerce endpoints.
Capability Matrix
YouTube
| Capability | operationId | Interface | Minimum input |
|---|---|---|---|
none |
none |
none |
none |
TikTok
| Capability | operationId | Interface | Minimum input |
|---|---|---|---|
| 实时采集-商品详情 | tiktok_realtime_product_detail |
GET /api/v1/tiktok/realtime/product/detail |
query.product_id, query.region |
| 用户带货商品列表 | tiktok_user_shop_goods_list |
GET /api/v1/tiktok/user/shop/goods/list |
query.unique_id |
| 用户带货直播列表 | tiktok_user_shop_live_list |
GET /api/v1/tiktok/user/shop/live/list |
query.unique_id |
| 用户带货数据 | tiktok_user_shop_sale |
GET /api/v1/tiktok/user/shop/sale |
query.unique_id |
| 用户带货视频广告列表 | tiktok_user_shop_video_ad_list |
GET /api/v1/tiktok/user/shop/video/ad/list |
query.unique_id |
| Capability | operationId | Interface | Minimum input |
|---|---|---|---|
none |
none |
none |
none |
Cross-platform
| Capability | operationId | Interface | Minimum input |
|---|---|---|---|
none |
none |
none |
none |
Quick Start
- Confirm commerce objective (GMV growth, product seeding, ad ROI).
- Use the Capability Matrix to pick commerce operationIds.
- Validate required query/body fields in
references/request-response.md. - Run calls and summarize opportunity + risk + pilot plan.
Workflow
- Build a commerce snapshot first (
tiktok_user_shop_sale, goods/live/ad lists). - Deep dive top products with
tiktok_realtime_product_detailwhen needed. - Evaluate conversion consistency, category fit, and monetization durability.
- Return recommendation with expected KPI and test scope.
Tooling
Execution commands:
- List operations:
python3 scripts/execute_operation.py --env-file .env list - Sale snapshot:
python3 scripts/execute_operation.py --env-file .env call --operation tiktok_user_shop_sale --query '{"unique_id":"nike"}' - Goods list:
python3 scripts/execute_operation.py --env-file .env call --operation tiktok_user_shop_goods_list --query '{"unique_id":"nike","page":1,"page_size":20}'
Required environment variables:
SCRUMBALL_BASE_URL: API gateway base URLSCRUMBALL_API_KEY: unified API key- Optional:
SCRUMBALL_AUTH_PREFIX,SCRUMBALL_TIMEOUT_SECONDS
Env loading:
- Use
--env-file .envfor explicit loading. - Without
--env-file, script auto-tries./.envthen<skill-root>/.env.
Output Contract
Always return:
Commerce summary: top performance signalsOpportunity: product/category/content opportunityRisk: instability, low signal confidence, or limited sampleNext step: pilot recommendation and expected KPI
Failure Handling
- If identifiers are incomplete, request
unique_idfirst. - If one commerce dimension is missing, continue with available dimensions and reduce confidence.
- If user asks broad creator discovery, hand off to lead-discovery skill.
References
references/api-index.md: full operation index + platform grouped indexreferences/request-response.md: request parameters + response top-level/data fields + minimal examplesreferences/operations.json: operation manifest used byscripts/execute_operation.py
Quota & Unlock (important: act on 429)
-
Free tier: a limited number of calls per day, zero-config (no key required — the skill defaults to a hosted gateway that injects the key server-side).
-
When any operation returns HTTP 429, or the response body has
code=429/ containsquota_exceeded, you (the assistant) MUST immediately and clearly tell the user (do not silently retry, do not treat it as a generic error):Free quota exhausted. Register and get your own API key at https://data.scdata.cc/pricing, then set the environment variable
SCRUMBALL_API_KEYto your key (in your host/agent environment or a local.env). You can then continue with your own quota. -
The 429 response body usually includes
apply_urlandenv_varfields you can quote directly.
