# Social Media Influencer

> Prepares a live stream broadcast title, updates style details, announces the live stream, and engages the audience using owncast-agent tools.

- Skill: `knuckles-team/social-media-influencer` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add knuckles-team/social-media-influencer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/knuckles-team/social-media-influencer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Knuckles-Team (https://skillmd.com/u/knuckles-team)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/knuckles-team/social-media-influencer

---


# Social Media Influencer Workflow

**CONCEPT:SOCIAL-001**

Prepares a live stream broadcast title, updates style details, announces the live stream, and engages the audience using owncast-agent tools.

## Steps

### Step 0: Social Media Influencer
**Agent**: `content-creator`
**Tools**: `graph_query, document_tools`

Update the live stream broadcast title, welcome message text, and style customization details using the owncast_objects and owncast_internal tools.
Expected: `stream_status, metadata`

### Step 1: Owncast Agent
**Agent**: `media-processor`
**Tools**: `graph_analyze`

Announce stream live status to connected social networks. Trigger an initial welcome notification message in the live stream chat using owncast_external and owncast_chat tools.
Expected: `system_chat_post, notification`

### Step 2: KG Persistence [depends_on: owncast-agent]
**Agent**: `media-processor`
**Tools**: `graph_write`

Persist workflow results as nodes and edges in the Knowledge Graph.
Create appropriate typed nodes with metadata and link to existing domain entities.

## Output
- Social Media Influencer results persisted in KG
- Structured report (MD/PDF)
- Audit trail with timestamps and agent attributions

## Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.

- **Run first (in parallel):** Step 0 — Social Media Influencer; Step 1 — Owncast Agent
- **After level 0:** Step 2 — KG Persistence

**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.