nexscope-ai/nexscope-ecommerce-skills / ecommerce-product-description-generator-api
ecommerce.product-description-generator-api
VerifiedGenerate product descriptions and other text asynchronously, or query an existing text-generation task by taskId. Use this skill for ecommerce copywriting, text/image/video-assisted content generation, task creation, status polling, and result retrieval.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.3 KB |
| manifest.json | config | 535 B |
| references/api.json | config | 1.3 KB |
| references/api.md | markdown | 4.7 KB |
| references/credentials.md | markdown | 984 B |
| references/testing.md | markdown | 1.6 KB |
| references/workflow.md | markdown | 1.4 KB |
| scripts/aigc_textgen.py | script | 19.3 KB |
references/api.md
View on GitHub# API contract for `ecommerce.product-description-generator-api`
## Scope
Create asynchronous text-generation tasks and query their status and results by `taskId`. Both routes are exposed through the Nexscope research gateway.
## Operations
### `create_text_task`
- Method and path: `POST /api/v1/tools/research/aigc/textGenAsync`
- Script mode: `python scripts/aigc_textgen.py --create-only --inline '<JSON>'`
- Required inputs: `prompt`, `imageUrls`, `thinkingLevel`
- Optional inputs: `model`, `memberId`
- Result: returns a `taskId` immediately; it does not wait for generated content.
Supported models are `GEM_3_FLASH` and `GEM_3_1_PRO`. Use an empty `imageUrls` array for text-only generation. Image or video URLs may be supplied when multimodal analysis is required. `thinkingLevel` accepts `minimal`, `low`, `medium`, or `high`; `GEM_3_1_PRO` does not support `minimal`.
### `query_text_task`
- Method and path: `POST /api/v1/tools/research/aigc/textTaskQuery`
- Script mode: `python scripts/aigc_textgen.py --query-task --inline '<JSON>'`
- Required input: `taskId`
- Optional input: `memberId`
- Result: returns `PROCESSING`, `SUCCESS`, or `FAILED`; successful results include generated `content` and may include token-usage fields.
Do not create another task when a previous create request timed out ambiguously. Query the known `taskId` first.
## Combined workflow
The default script mode creates a task and polls the query route until completion:
```bash
python scripts/aigc_textgen.py --inline '{"prompt":"Write a concise product description for a wireless speaker","imageUrls":[],"model":"GEM_3_FLASH","thinkingLevel":"minimal"}'
```
Create and query separately:
```bash
python scripts/aigc_textgen.py --create-only --inline '{"prompt":"Write a concise product description for a wireless speaker","imageUrls":[],"model":"GEM_3_FLASH","thinkingLevel":"minimal"}'
python scripts/aigc_textgen.py --query-task --inline '{"taskId":"123456789"}'
```
## Nexscope response envelope
These research endpoints return a platform object with numeric `code`, nullable `msg`, and business `data`. Only outer `code: 0` means success; `200`, string codes, missing codes, and HTTP 200 alone do not. A nonzero code is a platform error: show `msg` and do not interpret the payload as a successful result.
`msg` preserves the upstream message when available; Chinese messages are translated to English by Nexscope. A successful response without a message has `msg: null`. Do not infer success or retry behavior from the message text. On both success and failure, the direct fields `code`, `errcode`, `errorCode`, `msg`, `errmsg`, `message`, and `errorMsg` are removed from public `data`. Read the message only from outer `msg`; deeper business fields are preserved, including nested `code` and `status`.
Business field tables and abbreviated business examples below describe `data`, unless explicitly labeled as a complete platform response. For example, a business `products` field is at HTTP `data.products`, and a business `data` array is at HTTP `data.data`. The research endpoints already had this outer envelope; no additional wrapper is added.
```json
{"code":0,"msg":null,"data":{}}
```
Metadata includes string `ts` (epoch milliseconds), string `cost` (elapsed milliseconds, not credits), `time`, and nullable `traceId`. Handle network/HTTP failures before the platform code; gateway failures may not be platform JSON. Keep the existing billing-header guidance separate from elapsed time.
## Runtime and errors
Set `NEXSCOPE_PROXY_BASE` to the gateway origin, without the research route suffix, and set `NEXSCOPE_API_KEY`. The script sends `Authorization: Bearer <key>` and JSON request bodies.
Treat HTTP failures, non-success response envelopes, `FAILED` task status, malformed responses, and polling timeouts as distinct errors. Never expose the API key.
The script accepts both the standard gateway envelope (`code`, `data`) and the legacy flat business response. It unwraps a successful gateway response before reading `taskId`, `status`, `content`, and `costToken`.
## API Key request rate and retries
All API Keys of one Nexscope user share the public API execution request-rate allowance, measured in any rolling 1-second window. The allowed RPS depends on that user's entitlements; it is not a universal 1 RPS. One Skill operation may issue multiple public API requests, each of which uses the allowance.
HTTP 429 with Nexscope outer code `13012` means request-rate exhaustion: honor the response's `Retry-After`. Outer code `13013` means concurrent-request exhaustion, not rate exhaustion; honor `Retry-After` when supplied. Check the HTTP status and outer JSON code separately. Do not automatically replay writes or requests with uncertain outcomes; first reconcile the operation's state.
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: 471k | 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 |