FLUX 3 Prompt Doctor — prompt skill for prompts by model
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
Diagnose a FLUX 3 video brief before spending: resolve missing, conflicting or schema-changing asks.
- Type: Prompt · Prompts by model
- Slug:
flux-3-prompt-doctor - Status: live
- Publisher: Black Forest Labs (vendor, verified)
- License: MIT
- Source: https://github.com/black-forest-labs/skills/tree/master/skills/flux-3-prompt-doctor
- Works in: Claude Code, Codex, Cursor, Gemini CLI
- Requires: BFL API key (BFL_API_KEY)
- Cost: Billed by Black Forest Labs (API credits)
- Adoption: 161 installs, 135 GitHub stars (skills.sh, 2026-10-26)
What it does
Checks a FLUX 3 brief before generation, routing by what must survive and testing feasibility. It resolves missing, conflicting or schema-changing requirements and returns a verdict before any money is spent.
Use when
- A vague or contradictory video brief
- Checking feasibility before generating
Install
- Claude Code:
/plugin marketplace add black-forest-labs/skills && /plugin install flux-3-video@black-forest-labs - Codex:
npx skills add black-forest-labs/skills --skill flux-3-prompt-doctor -a codex - Cursor:
npx skills add black-forest-labs/skills --skill flux-3-prompt-doctor -a cursor - Gemini CLI:
npx skills add black-forest-labs/skills --skill flux-3-prompt-doctor -a gemini-cli
Models it drives: flux_3
Example output
https://skills.varg.ai/previews/flux-3-prompt-doctor.mp4 — FLUX 3 text-to-video example from BFL's docs (a beekeeper opening a hive at golden hour) — the kind of video job the prompt doctor checks before spending; 0-8 s (credit: Black Forest Labs, https://docs.bfl.ai/flux_3/flux3_video)
More prompts by model skills
- fal Prompting: Prompt specific model families well: Kling, GPT Image 2 and Happy Horse guides, loaded only when needed.
- Replicate Prompt Images: Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
- Replicate Prompt Videos: Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
- Video Prompting Guide: Write prompts that video models follow: shot types, camera moves and per-model tips from Veo to Sora.
- FLUX Image Best Practices: Prompt FLUX image models well: structure, JSON prompts, hex colors, typography and multi-reference edits.
- AI Film Director (Visual Skills): AI film director for video prompts: dramaturgy first (Murch, blocking, montage), then exact syntax per model.