\r \r

Creativault Creator Data Collection\r

\r

Prerequisites\r

\r Set the following environment variables:\r \r

• CV_API_KEY — Creativault Open API Key (obtain from admin dashboard)\r
• CV_USER_IDENTITY — Operator email address\r
• CV_API_BASE_URL (optional) — API base URL, defaults to http://api.creativault.vip\r \r Linux / macOS:\r \r

export CV_API_KEY=cv_live_your_key_here\r
export [email protected]\r
```\r
\r
**Windows PowerShell**:\r
\r
```powershell\r
$env:CV_API_KEY = "cv_live_your_key_here"\r
$env:CV_USER_IDENTITY = "[email protected]"\r
```\r
\r
## Capabilities\r
\r
| Capability | Script | Mode |\r
|------------|--------|------|\r
| Search creators | `scripts/search_creators.mjs` | Sync, real-time |\r
| Submit collection task | `scripts/submit_collection_task.mjs` | Async, returns task_id |\r
| Submit keyword collection | `scripts/submit_keyword_task.mjs` | Async, returns task_id |\r
| Check task status | `scripts/get_task_status.mjs` | Sync, single query |\r
| Poll task status | `scripts/poll_task_status.mjs` | Auto-poll every 60s |\r
| Get collection data | `scripts/get_task_data.mjs` | Sync, paginated |\r
| Export task data (server) | `scripts/export_task_data.mjs` | Returns file download URL |\r
| Export to local CSV | `scripts/export_to_csv.mjs` | Pipe input, incremental append |\r
| Get file download URL | `scripts/get_download_url.mjs` | Sync |\r
| Find similar creators | `scripts/find_lookalike.mjs` | Sync, auto-resolves username/URL |\r
\r
All scripts accept a JSON string as command-line argument. Results are output as JSON to stdout.\r
\r
**Language**: Always respond to the user in the same language they use. If the user writes in Chinese, respond in Chinese. If in English, respond in English.\r
\r
## Choosing the Right Approach\r
\r
Before executing, determine the best approach based on user intent:\r
\r
| User Intent | Approach | Response Time |\r
|-------------|----------|---------------|\r
| "Search/find creators" with filters (keyword, country, followers) | `search_creators.mjs` | Instant (~1s) |\r
| "Find similar/lookalike creators" given a profile link or username | `find_lookalike.mjs` | Instant (~2s) |\r
| "Collect/scrape data" for specific creators (links or usernames) | `submit_collection_task.mjs` → poll → get data | 5~30 minutes |\r
| "Find creators by keyword" and collect detailed data | `submit_keyword_task.mjs` → poll → get data | 5~30 minutes |\r
\r
**Decision rules:**\r
- If the user gives filter conditions (keyword, country, follower count) → use **search** first. It returns results instantly.\r
- If the user gives a specific creator link/username and asks for "similar"/"lookalike"/"相似达人" → use **lookalike** directly (no resolve needed).\r
- If the user gives specific profile links or usernames → use **collection** (async).\r
- If search results satisfy the user's needs → no need to submit a collection task.\r
- Only use collection when the user explicitly needs detailed/enriched data for specific creators.\r
- **After any collection task completes, ALWAYS call `export_task_data.mjs` to generate a downloadable file (default xlsx) and present the download link to the user. Do NOT just call `get_task_data.mjs` and show raw JSON.**\r
\r
### Service Level Selection\r
\r
Users may not know what S1/S2/S3 means. The agent MUST ask the user to confirm the service level before executing a search. Never auto-select silently.\r
\r
**Service level reference (show to user when asking):**\r
\r
| 等级 | 名称 | 返回内容 | 积分/条 |\r
|------|------|----------|---------|\r
| S1 | 纯名单筛选 | 基础信息（用户名、昵称、头像、粉丝数、主页链接） | 1 |\r
| S2 | 精准触达 | S1 + 国家、性别、互动率、平均播放、带货类目、邮箱标识、语言 | 3 |\r
| S3 | 深度画像 | S2 + 受众女性比例、受众国家分布、受众语言分布 | 4 |\r
\r
**Rules:**\r
- If user does NOT specify a service level → show the table above and ask: "请选择服务等级：S1（基础名单，1积分/条）、S2（精准触达，3积分/条）、S3（深度画像，4积分/条）？"\r
- If user explicitly says "S1"/"S2"/"S3" or "深度画像"/"精准触达"/"名单" → use as specified, no need to ask again\r
- If user has already chosen a level in the current conversation → reuse that level for subsequent searches unless they say otherwise\r
- **ALWAYS show the service level and credits consumed in the stats section after search results**\r
- After showing results, display: "本次使用 S2（精准触达）等级，消耗 60 积分，剩余配额 xxx"\r
\r
## Output Formatting\r
\r
展示搜索或采集结果时，使用以下分区格式。字段要展示齐全，表格要对齐整齐。\r
\r
### TikTok 输出模板\r
\r
```\r
✅ 搜索成功！找到 N 个 [国家] [平台] [关键词]达人\r
\r
📊 采集结果\r
\r
| #   | 用户名      | 昵称        | 粉丝数  | 获赞数   | 平均播放 | 互动率  | 国家 | 主页链接          |\r
| --- | ----------- | ----------- | ------- | -------- | -------- | ------- | ---- | ----------------- |\r
| 1   | username1   | Nickname1   | 33.1K   | 95.5万   | 1.2万    | 6.50%   | US   | [查看][link1]     |\r
| 2   | username2   | Nickname2   | 59.2K   | 146.0万  | 3.8万    | 3.75%   | US   | [查看][link2]     |\r
\r
[link1]: https://www.tiktok.com/@username1\r
[link2]: https://www.tiktok.com/@username2\r
\r
📈 统计信息\r
• 总匹配数：12,652 个达人\r
• 服务等级：S2（精准触达）\r
• 本次消耗：60 积分\r
• 剩余配额：992 次\r
• 请求ID：xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\r
```\r
\r
### YouTube 输出模板\r
\r
```\r
| #   | 用户名      | 频道名      | 订阅数  | 总观看    | 平均播放 | 互动率  | 国家 | 频道链接          |\r
| --- | ----------- | ----------- | ------- | --------- | -------- | ------- | ---- | ----------------- |\r
| 1   | username1   | Channel1    | 120K    | 5,200万   | 8.5万    | 4.20%   | US   | [查看][link1]     |\r
```\r
\r
### Instagram 输出模板\r
\r
```\r
| #   | 用户名      | 昵称        | 粉丝数  | 帖子数   | 平均播放 | 互动率  | 国家 | 主页链接          |\r
| --- | ----------- | ----------- | ------- | -------- | -------- | ------- | ---- | ----------------- |\r
| 1   | username1   | Nickname1   | 85.3K   | 342      | 2.1万    | 5.30%   | US   | [查看][link1]     |\r
```\r
\r
### 相似达人输出模板\r
\r
```\r
🔍 找到 N 个与 @seed_username 相似的达人\r
\r
📊 相似达人列表\r
\r
| #   | 用户名      | 昵称        | 粉丝数  | 平均播放 | 互动率  | 相似度  | 国家 | 主页链接          |\r
| --- | ----------- | ----------- | ------- | -------- | ------- | ------ | ---- | ----------------- |\r
| 1   | username1   | Nickname1   | 120K    | 3.8万    | 7.20%   | 85.0%  | US   | [查看][link1]     |\r
| 2   | username2   | Nickname2   | 95.5K   | 2.1万    | 5.50%   | 78.3%  | US   | [查看][link2]     |\r
\r
[link1]: https://www.tiktok.com/@username1\r
[link2]: https://www.tiktok.com/@username2\r
\r
📈 统计信息\r
• 种子达人：@seed_username（平台ID：7123456789）\r
• 结果总数：N 个相似达人\r
• 本次消耗：10 积分\r
• 剩余配额：xxx 次\r
• 请求ID：xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\r
```\r
\r
### 格式规则\r
\r
- **分区结构**：用 emoji 标题分隔不同区域（✅ 搜索结果、📊 采集结果、📈 统计信息）\r
- **字段齐全**：展示 API 返回的所有核心字段，不省略\r
- **表格对齐**：每列用固定宽度对齐，分隔线用 `---` 填充，确保列宽一致\r
- **链接处理**：表格内用 `[查看][linkN]` 引用式链接，在表格下方定义完整 URL，避免撑坏表格\r
- **数字格式**：\r
  - 粉丝/播放等数值：≥1万 用 K（如 33.1K）、≥100万 用 M（如 1.2M）；\x3C1万 用逗号分隔（如 3,911）\r
  - 获赞/总观看等大数值：用万/亿简写（如 95.5万、5.2亿）\r
  - 互动率：转为百分比，保留两位小数（如 0.065 → 6.50%）\r
- **统计信息**：单独列出总匹配数、服务等级、本次消耗积分、剩余配额、请求 ID，用无序列表展示\r
- **总匹配数展示规则**：API 的 `meta.total` 仅在筛选条件 > 2 个时返回数值，≤ 2 个筛选条件时返回 null。当 total 为 null 时，统计信息中不展示"总匹配数"这一行，避免显示"总匹配数：null"\r
- **默认展示 5~10 条**，超过时询问用户是否需要更多\r
- 展示结果后主动询问："需要导出完整数据到 CSV/Excel 吗？"\r
\r
## Quota Awareness\r
\r
Every API response includes `meta.quota_remaining` and search responses include `meta.credits_consumed`. Monitor these values:\r
- `credits_consumed` shows how many credits were deducted for the current request (varies by `service_level`: S1=1/record, S2=3/record, S3=4/record)\r
- If `quota_remaining` \x3C 50: warn the user that quota is running low\r
- If `quota_remaining` \x3C 10: strongly recommend the user to conserve quota\r
- If `quota_remaining` = 0 or error 42902: inform the user that daily quota is exhausted (resets at UTC 00:00)\r
- When using S2/S3 service levels, remind the user that credits are consumed faster\r
\r
## Workflows\r
\r
### Workflow 1: Search Creators (instant)\r
\r
```bash\r
node {baseDir}/scripts/search_creators.mjs '{"platform":"tiktok","keyword":"beauty","country_code":"US","followers_cnt_gte":10000,"size":20,"service_level":"S2"}'\r
```\r
\r
### Workflow 2: Search + Export (instant)\r
\r
```bash\r
# Search and export to local CSV in one pipeline\r
node {baseDir}/scripts/search_creators.mjs '{"platform":"tiktok","keyword":"beauty","country_code":"US","size":50,"service_level":"S2"}' | node {baseDir}/scripts/export_to_csv.mjs '{"output":"creators.csv"}'\r
\r
# Append page 2 to the same file\r
node {baseDir}/scripts/search_creators.mjs '{"platform":"tiktok","keyword":"beauty","country_code":"US","size":50,"page":2,"service_level":"S2"}' | node {baseDir}/scripts/export_to_csv.mjs '{"output":"creators.csv"}'\r
```\r
\r
### Workflow 3: Batch Collection (async, 5~30 min)\r
\r
> **Important**: Collection tasks are async and take 5~30 minutes. You MUST poll for completion before fetching data.\r
\r
**Step 1** — Submit task:\r
\r
```bash\r
node {baseDir}/scripts/submit_collection_task.mjs '{"task_type":"LINK_BATCH","platform":"tiktok","values":["https://www.tiktok.com/@creator1","https://www.tiktok.com/@creator2"],"task_name":"Q1 collection"}'\r
```\r
\r
**Step 2** — Poll until completed (auto-polls every 60s):\r
\r
```bash\r
node {baseDir}/scripts/poll_task_status.mjs '{"task_id":"task_xxx"}'\r
```\r
\r
After submitting, inform the user: "Collection task submitted. This typically takes 5~30 minutes. I'll monitor the progress for you."\r
\r
**Step 3** — After task is completed, **ALWAYS export the data as a file first**, then show the download link to the user. Only use `get_task_data.mjs` if the user explicitly asks for raw JSON data.\r
\r
```bash\r
# PREFERRED: Export as file and give user the download link\r
node {baseDir}/scripts/export_task_data.mjs '{"task_id":"task_xxx","format":"xlsx"}'\r
\r
# Only if user explicitly requests raw JSON:\r
node {baseDir}/scripts/get_task_data.mjs '{"task_id":"task_xxx","page":1,"size":50}'\r
```\r
\r
> **Rule**: When a collection task completes, the default action is to call `export_task_data.mjs` with `format:"xlsx"` and present the `file_url` download link to the user. Do NOT just call `get_task_data.mjs` and dump raw JSON — users want a downloadable file.\r
\r
### Workflow 4: Keyword Collection (async)\r
\r
```bash\r
# Step 1: Submit\r
node {baseDir}/scripts/submit_keyword_task.mjs '{"platform":"tiktok","keywords":["beauty tips","skincare routine"]}'\r
\r
# Step 2: Poll\r
node {baseDir}/scripts/poll_task_status.mjs '{"task_id":"task_xxx"}'\r
\r
# Step 3: ALWAYS export as file after completion\r
node {baseDir}/scripts/export_task_data.mjs '{"task_id":"task_xxx","format":"xlsx"}'\r
```\r
\r
### Workflow 5: Find Similar/Lookalike Creators (instant)\r
\r
When the user provides a creator profile link or username and asks for similar creators, call `find_lookalike.mjs` directly — the API internally resolves username/URL to platform ID, no separate resolve step needed.\r
\r
**By username + platform:**\r
\r
```bash\r
node {baseDir}/scripts/find_lookalike.mjs '{"username":"creator_demo","platform":"tiktok","limit":10}'\r
```\r
\r
**By profile URL (auto-detects platform):**\r
\r
```bash\r
node {baseDir}/scripts/find_lookalike.mjs '{"profile_url":"https://www.tiktok.com/@creator_demo","limit":10}'\r
```\r
\r
**By username only (auto-searches all platforms):**\r
\r
```bash\r
node {baseDir}/scripts/find_lookalike.mjs '{"username":"creator_demo","limit":10}'\r
```\r
\r
**Cross-platform search**: Set `target_platform` different from the seed creator's platform to find similar creators on another platform (e.g., find YouTube creators similar to a TikTok creator).\r
\r
Optional filters: `target_region`, `target_language`, `follower_min`, `follower_max`, `avg_views_min`, `avg_views_max`, `female_rate_min`, `lang`, `service_level`.\r
\r
**Decision rules for lookalike:**\r
- If user gives a profile URL → pass it as `profile_url`, the API auto-parses platform and username\r
- If user gives a username + platform → pass both\r
- If user gives only a username → pass just `username`, the API searches all three platforms\r
- If API returns error 40401 → inform user the creator is not in the database\r
\r
## Script Parameters\r
\r
### search_creators.mjs\r
\r
`platform` is required. All other parameters are optional filters.\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `platform` | string | **Required**. `tiktok` / `youtube` / `instagram` |\r
| `keyword` | string | Search keyword |\r
| `country_code` | string | Country code, comma-separated (e.g., `US,CA`) |\r
| `gender` | string | Gender filter |\r
| `has_email` | boolean | Has email contact |\r
| `followers_cnt_gte` | integer | Followers ≥ |\r
| `followers_cnt_lte` | integer | Followers ≤ |\r
| `page` | integer | Page number, default 1 |\r
| `size` | integer | Page size, default 50, max 100 |\r
| `sort_field` | string | Sort field (e.g., `followers_cnt`) |\r
| `sort_order` | string | `asc` / `desc` (default `desc`) |\r
| `service_level` | string | Service level: `S1` (list only) / `S2` (precise reach) / `S3` (deep profile). Default `S2`. Different levels return different fields and consume different credits per record |\r
| `lang` | string | Response language: `cn` (Chinese) / `en` (English). Translates code values like country_code, gender, etc. |\r
\r
**Platform-specific category parameters:**\r
\r
All platforms use the same format: **level-3 category IDs** (8-digit codes). The skill automatically converts user input to the correct format.\r
\r
- **TikTok**: `industry_category_levels_list` parameter\r
- **YouTube/Instagram**: `industry` parameter\r
\r
**Supported input formats** (all platforms):\r
- **Level-3 category IDs** (8-digit codes): `25009001,24001001` (Skincare + Mobile Phones)\r
- **Level-1 category IDs** (2-digit codes): `25` (expands to all Beauty & Personal Care subcategories)\r
- **Chinese category names**: `美妆,科技数码` (auto-converts to IDs)\r
- **English category names**: `Skincare,Mobile Phones` (auto-converts to IDs)\r
\r
See [Industry Categories Reference](references/industry-categories.md) for complete mapping.\r
\r
**Category Input Examples:**\r
\r
```bash\r
# TikTok: All formats work, auto-converted to level-3 IDs\r
node scripts/search_creators.mjs '{"platform":"tiktok","industry_category_levels_list":"美妆"}'\r
node scripts/search_creators.mjs '{"platform":"tiktok","industry_category_levels_list":"Skincare"}'\r
node scripts/search_creators.mjs '{"platform":"tiktok","industry_category_levels_list":"25"}'\r
node scripts/search_creators.mjs '{"platform":"tiktok","industry_category_levels_list":"25009001"}'\r
\r
# YouTube/Instagram: All formats work, auto-converted to level-3 IDs (same as TikTok)\r
node scripts/search_creators.mjs '{"platform":"youtube","industry":"美妆"}'\r
node scripts/search_creators.mjs '{"platform":"youtube","industry":"Skincare"}'\r
node scripts/search_creators.mjs '{"platform":"instagram","industry":"25"}'\r
node scripts/search_creators.mjs '{"platform":"instagram","industry":"25009001"}'\r
```\r
\r
#### Service Level Details\r
\r
| Level | Name | Included Fields | Credits/Record |\r
|-------|------|----------------|----------------|\r
| S1 | List only | uid, username, nickname, avatar_url, profile_url, followers_count, likes_count, video_count, has_showcase, has_email, has_mcn, has_line, has_zalo, last_video_publish_date | 1 |\r
| S2 | Precise reach | S1 + country_code, gender, engagement_rate, avg_views, views_per_follower, product_categories, industry_categories, bio, hashtags, email, contact fields, mcn, language | 3 |\r
| S3 | Deep profile | S2 + audience_female_rate (percentage), audience_country_code_list, audience_language_code_list, audience_age_id_list | 4 |\r
\r
Platform-specific parameters: see [Platform Parameters Reference](references/platform-params.md).\r
\r
### submit_collection_task.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `task_type` | string | **Required**. `LINK_BATCH` (links) / `FILE_UPLOAD` (usernames) |\r
| `platform` | string | **Required**. `tiktok` / `youtube` / `instagram` |\r
| `values` | string[] | **Required**. Links or usernames, max 500 |\r
| `task_name` | string | Task name |\r
| `webhook_url` | string | Completion callback URL (HTTPS) |\r
\r
### submit_keyword_task.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `platform` | string | **Required**. `tiktok` / `youtube` / `instagram` |\r
| `keywords` | string[] | **Required**. Keyword list, max 10 |\r
| `task_name` | string | Task name |\r
| `webhook_url` | string | Completion callback URL (HTTPS) |\r
\r
### poll_task_status.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `task_id` | string | **Required**. Task ID |\r
| `interval` | integer | Poll interval in seconds, default 60 |\r
| `max_attempts` | integer | Max poll attempts, default 45 (~45 min) |\r
\r
### get_task_status.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `task_id` | string | **Required**. Task ID |\r
\r
### get_task_data.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `task_id` | string | **Required**. Task ID |\r
| `page` | integer | Page number, default 1 |\r
| `size` | integer | Page size, default 20, max 100 |\r
\r
### export_task_data.mjs\r
\r
Exports task data to file (server-side), uploads to OSS, returns download URL. Repeated calls with same task_id + format return cached file.\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `task_id` | string | **Required**. Task ID (must be completed) |\r
| `format` | string | **Required**. `xlsx` / `csv` / `html` |\r
\r
### export_to_csv.mjs\r
\r
Pipe JSON from search or collection results to export as local CSV file. Supports incremental append.\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `output` | string | Output file path, default `output.csv` |\r
| `mode` | string | `append` (default) / `overwrite` |\r
\r
### get_download_url.mjs\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `file_id` | string | File ID (either file_id or file_name required) |\r
| `file_name` | string | File name (either file_id or file_name required) |\r
\r
### find_lookalike.mjs\r
\r
Find similar/lookalike creators. Supports username, profile URL, or cross-platform search. The API internally resolves username/URL to platform ID.\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| `username` | string | Creator username (without `@`), either this or `profile_url` required |\r
| `platform` | string | Creator platform: `tiktok` / `youtube` / `instagram`. Optional — if omitted, searches all platforms |\r
| `profile_url` | string | Creator profile URL (auto-detects platform), either this or `username` required |\r
| `target_platform` | string | Target search platform. If omitted, same as seed creator's platform |\r
| `target_region` | string | Target country code, `all` for no filter |\r
| `target_language` | string | Target language code, `all` for no filter |\r
| `limit` | integer | Number of results, default 20, max 50 |\r
| `follower_min` | integer | Minimum followers |\r
| `follower_max` | integer | Maximum followers |\r
| `avg_views_min` | integer | Minimum average views |\r
| `avg_views_max` | integer | Maximum average views |\r
| `female_rate_min` | number | Minimum female audience ratio (0~100) |\r
| `lang` | string | Response language: `cn` / `en` |\r
| `service_level` | string | Service level, default `S1` |\r
\r
Returns: `items` array with `uid`, `username`, `nickname`, `avatar_url`, `profile_url`, `country_code`, `followers_count`, `avg_views`, `engagement_rate`, `match_score`.\r
\r
## Error Handling\r
\r
| Code | HTTP | Description | Action |\r
|------|------|-------------|--------|\r
| 40001 | 400 | Invalid parameters | Check parameter format and values |\r
| 40101 | 401 | Invalid API Key | Check CV_API_KEY env variable |\r
| 40102 | 401 | API Key expired | Contact admin to renew |\r
| 40103 | 401 | API Key revoked | Contact admin |\r
| 40104 | 401 | Missing user identity | Check CV_USER_IDENTITY env variable |\r
| 40201 | 402 | Insufficient credits | Top up or upgrade plan |\r
| 40301 | 403 | No permission for this endpoint | Check API Key scopes |\r
| 42901 | 429 | Rate limit exceeded | Auto-retry after Retry-After seconds |\r
| 42902 | 402 | Daily quota exhausted | Wait until UTC 00:00 or upgrade plan |\r
| 50001 | 500 | Server error | Report request_id to support |\r
\r
## References\r
\r
- [API Reference](references/api-reference.md) — Full request/response field documentation\r
- [Platform Parameters](references/platform-params.md) — TikTok/YouTube/Instagram specific filters\r
- [Industry Categories](references/industry-categories.md) — Industry category tree with Chinese/English mapping (for `industry_category_levels_list` and `industry` params)\r
- [Country Codes](references/country-codes.md) — ISO country codes with Chinese/English names and region shortcuts\r
- [Language Codes](references/language-codes.md) — ISO language codes with Chinese/English names\r
- [Error Codes](references/error-codes.md) — Complete error code list and troubleshooting\r
\r
## Changelog\r
\r
### v1.3.0\r
- Updated all three platform search response fields per v1.4 API doc\r
- TikTok: added `video_count`(S1), `views_per_follower`(S2), `bio`(S2), `industry_categories`(S2), `hashtags`(S2), `audience_age_id_list`(S3), contact fields\r
- YouTube: added `bio`(S2), `industry_categories`(S2), `hashtags`(S2), `audience_female_rate`(S3)\r
- Instagram: added `gender`(S2), `bio`(S2), `industry_categories`(S2), `hashtags`(S2), `audience_age_id_list`(S3)\r
- Added `lang` parameter support for i18n (cn/en) on all search and lookalike endpoints\r
- `audience_female_rate` now returns percentage value (e.g., 78.65 = 78.65%)\r
- Removed `resolve_creator.mjs` — lookalike API now auto-resolves username/URL internally\r
- Simplified `find_lookalike.mjs` to accept `username`/`profile_url` directly (no more `seed_platform_id`)\r
- Simplified Workflow 5 to single-step lookalike call\r
\r
### v1.2.0\r
- Added similar/lookalike creator discovery via `find_lookalike.mjs`\r
- Search API now defaults to S2 (precise reach) service level\r
- `meta.total` only returned when filter conditions > 2; output formatting hides total when null\r
- Added cross-platform lookalike search support\r
- Added Workflow 5 for lookalike creator discovery\r
\r
### v1.1.0\r
- Added server-side export (xlsx/csv/html) via `export_task_data.mjs`\r
- Added auto-retry on 429 rate limit in API client\r
- Added quota awareness guidance\r
- Added output formatting guidance for agents\r
- Added smart workflow selection (search vs collection)\r
- Unified all script logs and SKILL.md to English\r
\r
### v1.0.0\r
- Initial release: search, collection, polling, local CSV export\r