nexscope-ai/nexscope-ecommerce-skills / ecommerce-amazon-product-research-api
ecommerce.amazon-product-research-api
VerifiedRoute Amazon product-selection work across market, keyword, competitor, trend, review, and profitability capabilities. Use this skill when the user asks for this exact ecommerce workflow, analysis, data lookup, or deliverable.
references/testing.md
View on GitHub# Testing evidence for `ecommerce.amazon-product-research-api`
## Required user information
- Marketplace, region, or account context when applicable.
- Entity identifiers and filters required by the selected operation.
- Explicit confirmation for every mutation.
## Prompt coverage
1. Basic: request the core capability with one valid entity or input.
2. Filtered: add marketplace, time range, pagination, or business filters.
3. Advanced: request a structured deliverable or a multi-step analysis using returned evidence.
4. Error: omit a required identifier or provide malformed JSON.
## Image upload checks
1. Verify the presign request contains `fileName`, `contentType`, and `fileSize`.
2. Verify the presigned HTTPS `PUT` request contains the image bytes and content type, but no `NEXSCOPE_API_KEY`.
3. Verify the confirm request contains `ossKey`, `expectedSize`, and the SHA-256 value in `expectedSha256`.
4. Verify the script returns the confirm response's `publicUrl` and `assetId`, rather than a URL derived from the presigned upload address.
## Evidence levels
- [ ] Static package validation recorded.
- [ ] Offline mock request recorded.
- [ ] Sandbox or test-environment request recorded.
- [ ] Real-account request recorded.
- [ ] ZIP import and installation recorded.
- [ ] English trigger and output review recorded.
Unchecked items are not evidence of failure; they have not been demonstrated yet. Never mark them complete without durable command output or an external test record.
- Assert every research-tool request path begins with `/api/v1/tools/research/`; reject legacy short paths in mocks and fixtures.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |