DataNavoAPI / SKILLS

Content performance sampling workflow

Content performance sampling workflow. Follow concrete contracts, examples and reviewable steps using Douyin, Xiaohongshu (RedNote), Bilibili.

LOCAL SIMULATIONAll displayed records are fictional fixtures. Live APIs, payments and external email are disabled.中文版 ↗
01

Inputs, goal and deliverable

Define the candidate set and ranking criteria, and retain a lower-performing comparison sample.

Inputs consist of explicit platforms, keywords or object identifiers. Preserve the samples, request IDs, classifications and unresolved questions in the deliverable. The task does not schedule itself or paginate indefinitely.

02

Step-by-step plan

StepCapabilityInputOutput
1douyin.videos.trendingboardpost / items
2xiaohongshu.pgy.notes.trendingboard, windowpost / items
3bilibili.videos.trendingContract defaultspost / items
03

Reusable task prompt

Ask the client to present a plan before you confirm each execution. This prompt bounds the sample; it does not call an external service for you.

text
Goal: Content performance sampling workflow
Use only DataNavoAPI local demo/simulated mode.
Planned capabilities: douyin.videos.trending → xiaohongshu.pgy.notes.trending → bilibili.videos.trending
Describe inputs and output fields and propose a bounded request count first.
Execute explicitly, retaining request IDs. Stop on failures or unknown outcomes.
Return a table, missing fields and sampling limits; never present fictional samples as market facts.
04

Plan, run and export

This bounded example has 3 steps. Successful customer simulation costs 6 TEST; anonymous demo costs zero. Provide each required identifier before generating a fixed plan; search results do not expand the request list automatically.

Use data.items[].id for the matching platform and object detail, account IDs for account content and comment IDs for replies. Check object types before reusing an ID. Fixture IDs do not establish a real relationship. The workbench exports per-step JSON and source-labelled CSV.

Workbench fieldMeaningExample
step1_board步骤 1 · boardlow_fan
step2_board步骤 2 · boardhot
step2_window步骤 2 · window7d
json
{
  "schemaVersion": 1,
  "templateId": "viral",
  "runId": "00000000-0000-4000-8000-000000000001",
  "inputs": {
    "step1_board": "low_fan",
    "step2_board": "hot",
    "step2_window": "7d"
  },
  "maxTotalCredits": 6,
  "estimatedCredits": 6,
  "priceVersion": "test-credit-v1",
  "steps": [
    {
      "id": "step-1",
      "title": "抖音视频榜",
      "capability": "douyin.videos.trending",
      "params": {
        "board": "low_fan"
      },
      "maxCredits": 2,
      "idempotencyKey": "wf:00000000-0000-4000-8000-000000000001:step-1"
    },
    {
      "id": "step-2",
      "title": "小红书蒲公英内容广场热门笔记",
      "capability": "xiaohongshu.pgy.notes.trending",
      "params": {
        "board": "hot",
        "window": "7d"
      },
      "maxCredits": 2,
      "idempotencyKey": "wf:00000000-0000-4000-8000-000000000001:step-2"
    },
    {
      "id": "step-3",
      "title": "B站综合热门",
      "capability": "bilibili.videos.trending",
      "params": {},
      "maxCredits": 2,
      "idempotencyKey": "wf:00000000-0000-4000-8000-000000000001:step-3"
    }
  ]
}
05

Review and stop conditions

  • Each conclusion links back to a sample and request ID.
  • Pagination stops at the agreed bound.
  • Missing fields remain missing rather than being invented by the model.
  • External writes, scheduled monitoring and automatic top-ups are not enabled by this workflow.
TRY THE CONTRACT

Clear inputs. Inspectable output.

Each click runs a local fixture. Advanced JSON inputs are checked against the selected method. Editing does not execute a request.

Copying does not execute. CLI quote is read-only and needs a local customer TEST key. Configure MCP in demo mode first. GET and POST batches both return only fictional local fixtures.

Download contract example (no execution) ↗

For TEST budgets, Key scopes or failure scenarios, open the account console. Customer sandbox ↗