Imported from topviewai/skill (
topview-youtube-kol-ops/SKILL.md). Install upstream withnpx skills add topviewai/skill --skill topview-youtube-kol-ops. Copyright stays with the author.
Topview YouTube KOL Ops
Merchant-facing YouTube creator research via the host's unified topview-mcp server (progressive disclosure; domain youtube_kol).
Step 0 — Bootstrap
- Confirm MCP server
topview-mcpis connected (look foruse_youtube_kol,get_tool_schema,call_tool). - If missing, point the user to
mcp.example.json→~/.cursor/mcp.json, reload MCP. - Do not run
scripts/mcp_call.py, open SSE yourself, or use curl/raw HTTP.
Execution
Server: topview-mcp (unified). Never open SSE yourself.
YouTube KOL tools are deferred. Invoke via progressive disclosure:
- Read the
use_youtube_koldescription ontools/list(embedded Tools catalog). Callinguse_youtube_kolonly to list tools is optional. - Pick a deferred
youtube_kol_*name from the catalog or references/tool_routing.md. get_tool_schemawith{ "name": "<youtube_kol_*>", "domain": "youtube_kol" }.call_toolwith{ "name": "<youtube_kol_*>", "domain": "youtube_kol", "arguments": { "req": { ... } } }(confirm shape with schema).
Typical host tool ids: mcp__topview-mcp__get_tool_schema / mcp__topview-mcp__call_tool.
Prefer youtube_kol_auto_quote_saved over write tool youtube_kol_auto_quote unless the user explicitly wants a new saved quote.
UX Rules
- Prefer analysis and shortlists over CRM execution.
- Never invent subscriber/metrics; report empty/failed tool results honestly.
- Creative production →
topview-generate. - Match the user's language.
Source
Adapted from Marketing Studio youtube-kol-ops-assistant (V049).