L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Données et recherche · SKILL.md

kol-discovery

kol-discovery

Discover and evaluate KOLs (Key Opinion Leaders) and creators across TikTok, Instagram, YouTube, and Xiaohongshu through SandBase. Use when asked for influencer research, creator outreach lists, KOL evaluation, or partnership prospecting.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: kol-discovery description: Discover and evaluate KOLs (Key Opinion Leaders) and creators across TikTok, Instagram, YouTube, and Xiaohongshu through SandBase. Use when asked for influencer research, creator outreach lists, KOL evaluation, or partnership prospecting.

KOL Discovery

Cross-platform influencer and creator discovery through SandBase. Find, evaluate, and compare creators across TikTok, Instagram, YouTube, and Xiaohongshu. Read the API map before selecting a capability.

Call SandBase capabilities

Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with sandbase_discover(q: "<provider and capability>"); use its returned name in sandbase_inspect(name: "<returned name>"). Read inputSchema, pricing, and execute_as, then call sandbase_run using execute_as.arguments.name and schema-defined arguments. If a run_id is returned, poll sandbase_run_get(run_id: "<returned run_id>") within the task budget until completed or failed; report pending or failed runs without resubmitting them automatically.

Operating principles

  • Evaluate creators by engagement rate, not just follower count.
  • Cross-platform presence indicates established creators.
  • Engagement rate = (likes + comments) / followers for each platform.
  • Focus on content relevance and audience fit, not vanity metrics.
  • Respect creator privacy — only report on public information.

Workflow

1. Discover on TikTok

Use tiktok_app_v3_general_search_result to search by niche keyword. Use tiktok_app_v3_creator_info for creator profile and stats. Use tiktok_app_v3_creator_search_insights for performance data.

2. Discover on Instagram

Use instagram_v3_general_search to find creators by keyword. Use instagram_v3_user_profile for profile details and metrics. Use instagram_v3_user_posts to evaluate content quality and engagement. Use instagram_v3_similar_users to find more creators in the same niche.

3. Discover on YouTube

Use youtube_web_v2_search_channels to find channels by niche. Use youtube_web_v2_channel_videos to evaluate content and consistency. Use youtube_web_v2_channel_description for channel positioning.

4. Discover on 小红书

Use xiaohongshu_app_v2_search_users to find creators. Use xiaohongshu_app_v2_user_info for profile and fan count. Use xiaohongshu_app_v2_user_posted_notes for content analysis.

Output

Return: ranked creator list with metrics (followers, engagement rate, content fit), cross-platform presence, content style assessment, and outreach recommendation.

Example tasks

  • "Find 10 TikTok creators in the [niche] space with 50K-500K followers."
  • "Evaluate @[creator] across all platforms — followers, engagement, content fit for [brand]."
  • "Build an influencer outreach list for a [product category] launch in [market]."
  • "Find 小红书 KOLs who post about [category] with high engagement."
  • "Compare creator engagement rates between TikTok and Instagram for [niche]."
Skills enregistrées