kevinbadi/social-agents/brand-interview
Claude Code and agent skill by kevinbadi/social-agents
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install kevinbadi/social-agents/brand-interviewSKILL.md
brand-interview
The brand pack is the one file every caption, description, and CTA flows from. Onboarding does not collect it — you do, in chat, where you can follow up. Run this the moment social-agents/BRAND.md is missing, before anything else.
How to run it
One question at a time. Wait for the answer, reflect it back in a line, then move on. Never batch the questions into a form, never fill in guesses. If an answer is thin, ask one follow-up, then move on. Eight questions, about five minutes:
- About — "What is this brand actually about? What are you marketing?"
- Offers — "What do you sell, and where does each thing live?" One offer per line: link + what it is. No link yet is fine; note it as such. Every CTA you ever write points at one of these.
- Voice, three adjectives — "Your voice in three adjectives."
- Voice, one never — "One thing my copy should never sound like." (corporate, thirsty, salesy…)
- Emoji policy — none / sparingly (max one per caption) / free, part of the voice.
- Hashtag policy — none / a few relevant ones (2-4) / aggressive.
- Audience — "Target audience in one sentence."
- Competitors — up to five handles or URLs to watch. Empty is fine.
This workspace is ONE CreatorOS API key, one brand. If the human runs several brands (e.g. an agency), each has its own workspace: interview for THIS one only, in its own terms.
Write the file
Write social-agents/BRAND.md in exactly this shape, then read it back and ask for sign-off. Edit on request; the latest file always wins.
After sign-off
- If competitors were named, research them (content mix, cadence, hooks, gaps) and write
social-agents/knowledge/COMPETITORS.md. - Then the infrastructure question: where should automations live — local (this machine, awake at scheduled times) or a Railway worker you provision (
provision-railwayskill, from a Railway API token)? SaveautomationTargetandtimezonetosocial-agents/social-agents.json. Local is a fine answer; never lecture on cost. - Then the automation menu, one item at a time, only what they approve (
automationsskill).
Judgment rules
- No captions, no posts, no funnels before BRAND.md exists and is signed off.
- Never invent an offer or a link. No link means no CTA to it.
- Keep it a conversation: short questions, plain text, no forms.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtemplates/skills/brand-interview/SKILL.md
Popularity
- Repository stars
- 55
- Repository forks
- 19
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kevinbadi/social-agents/brand-interview)