Social Post — Musician
SkillMediaWrite a platform-native social media post for a music release, show announcement, or general artist content. Load artist-context.md and promotion-strategy.md before running. Use when asked to "write a caption," "write a post for [platform]," or "help me announce [thing]."
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Social Post — Musician skill
What this skill tells your AI
The instructions your AI receives, as published by conorbronsdon/agent-context-os in projects/example-musician/workflow-examples/social-post/SKILL.md and read by ahel’s review.
Write a social media post for the artist. Load their artist context and promotion strategy before writing.
Before writing
- Read
projects/example-musician/artist-context.md— understand the sound, audience, and voice - Read
projects/example-musician/promotion-strategy.md— understand what's being promoted and what's worked before - Read
writing/skills/avoid-ai-writing/SKILL.md— apply its writing audit - Note the platform — Instagram, TikTok, Twitter/X, and LinkedIn all require different approaches
Platform guidelines
- Caption can be longer but front-load the most interesting line — it's what shows before "more"
- 1-3 hashtags max, at the end or in a comment — not sprinkled throughout
- No "link in bio" as the opener unless that's genuinely their voice
- Can be a story, an observation, a behind-the-scenes detail, or a direct announcement
- Avoid the "excited to share" opener — just share it
TikTok
- The caption is secondary to the video, but it should add context or a hook that drives saves/shares
- Shorter is better — 1-3 sentences
- Trending sounds, challenges, or formats can be referenced but don't force them
Twitter/X
- 280 characters or a thread if the story warrants it
- Punchy, direct — cut everything soft
- Can be more casual and real-time than Instagram
Writing rules
- Write in the artist's voice based on their context file — specific to them, not generic musician content
- No AI-isms (see
writing/skills/avoid-ai-writing/SKILL.md) - Avoid: "excited to share," "thrilled to announce," "I've been working so hard on this," "dream come true"
- Lead with something specific — a lyric, a detail, a moment, a question — not a label ("NEW MUSIC OUT NOW")
- Match energy to the release: a quiet introspective track gets a different tone than a high-energy single
Output
Provide 2-3 versions at different tones or lengths. Label each by platform or approach (e.g., "Instagram — story-driven," "Instagram — direct announcement," "Twitter/X"). Let the artist choose.
Apply the avoid-ai-writing audit to your own output before returning it. If any version has AI-isms, fix them before presenting.
Signals
- GitHub stars
- 24
- Forks
- 8
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
social-post- Source
- github.com/conorbronsdon/agent-context-os