Use Sorftime to find Walmart US products by a natural-language name or inspect one product's detail, historical trend, or daily sales-volume series.
Core Concepts
- Send exactly one
operationper request. Never call all four operations as a default workflow. - Use
searchByNameto discover related products,detailfor the current product summary,trendfor historical product changes, andsalesVolumefor dated sales rows. - Every request uses a flat JSON body.
searchByNamerequiresname; the other operations require stringproductId.operationvalues are case-sensitive. - A follow-up operation or a different date range is another paid call. Reuse the 24-hour cache for identical JSON.
Operation Routing
| Intent | operation | Parameters | Sorftime Request |
|---|---|---|---|
| Find related products by name | searchByName |
name, optional pageIndex |
2 |
| Current product details | detail |
productId |
1 |
| Historical product trend | trend |
productId |
2 |
| Daily/variant sales rows | salesVolume |
productId, optional dates/page |
1 |
Read references/api.md before calling for exact date and pagination rules.
Parameter Guide
- Always treat
productIdas a string, even when it contains digits only. searchByNameaccepts a natural-language product name and returns up to 100 related products per page;pageIndexdefaults to 1.salesVolumeaccepts optionalqueryDateandqueryEndDateinyyyy-MM-dd. With neither, it returns the recent 30-day range; with onlyqueryDate, the end defaults to the current day.pageIndexapplies tosearchByNameandsalesVolume, starts at 1, and defaults to 1.- The current available historical range is controlled by Sorftime; do not promise a fixed earliest date.
How to Call
- API Endpoint:
POST /sorftime/walmart/productAnalysis(for full parameters/responses/error codes, seereferences/api.md) - Python Script:
python scripts/sorftime_walmart_product_analysis.py '<JSON 参数>' [--inline] - Cost Constraints: This tool consumes compute; by default, the same parameter combination is called only once per session, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, paginate, or change the zip code to probe repeatedly; if further retrieval is needed, first explain to the user that additional consumption will be incurred.
Output Strategy (Script Default Behavior):
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-sorftime-walmart-product-analysis-<timestamp>.json(<cwd>is the working directory when the script is executed, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user's task;writing to /tmp is prohibited, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after writing to disk, print the full JSON to stdout
- Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, length of the largest list field + first 3 samples) - Add
--inlineto force full printing to stdout (also written to disk)
Data Reading Suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.
Resolving Authentication and Compute Issues
When the following abnormal situations occur, use references/onboarding.md to guide resolution:
- API Key not configured: the environment variable is not configured
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY - Response 401 or 402 status code
- Response indicates insufficient compute or balance: the message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge" or similar meaning
Usage Examples
python scripts/sorftime_walmart_product_analysis.py '{"operation":"searchByName","name":"wireless earbuds","pageIndex":1}'
python scripts/sorftime_walmart_product_analysis.py '{"operation":"detail","productId":"5169493923"}'
python scripts/sorftime_walmart_product_analysis.py '{"operation":"trend","productId":"5169493923"}'
python scripts/sorftime_walmart_product_analysis.py '{"operation":"salesVolume","productId":"5169493923","queryDate":"2026-07-01","queryEndDate":"2026-07-31","pageIndex":1}'
Display Rules
- State the operation and supplied product name or product ID, and show returned
requestConsumed,costCredit, andcostToken. If_cache.hit=true, make clear that the cached values describe the original live request and no new production charge occurred. - For
searchByName, label results as related products rather than exact matches and report the requested page. - For
detail, present only fields returned by the ProductSummeryObject; do not infer missing attributes. - For
trend, identify time fields and units from the response before summarizing changes. - For
salesVolume, interpret rows as[date, sales, type];type=2marks yesterday's sales record. - Label estimates or observed values accurately; do not present them as guaranteed Walmart transactions.
Important Limitations
- This integration targets Walmart US only.
- The API accepts one product name or one product ID and one operation per call.
- Sorftime controls historical coverage and data availability.
- Pagination or a second operation creates another paid call and requires user authorization.
searchByNameis natural-language related-product discovery, not a multi-filter product database or category-market query.
User Expression & Scenario Quick Reference
Applicable: finding Walmart products from a natural-language product name, or queries centered on a known ProductId and its details, trend, or sales history.
Not applicable: category market research, keyword metrics/reverse lookup, or multi-condition product filtering.
Boundary judgment: Use searchByName only when the user needs related products from a name; use detail for a current snapshot, trend for historical attributes, and salesVolume only for dated sales rows.
Compute Consumption Rules
Billed according to dynamic rules: a single Sorftime Request is currently shown as 6 compute; multi-Request operations are calculated by the gateway for the entire order and rounded, and the final amount is subject to the costCredit returned by the entry script; do not simply use requestConsumed × 6 in place of the actual bill.
Users pay fees due to compute consumption. Do not call another operation or the next page without confirmation.
Feedback:
Auto-detect and report feedback via the Feedback API when behavior or results mismatch intent, the user expresses praise or dissatisfaction, or an improvement is apparent. Follow references/api.md without interrupting the user's flow.
For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.