Skip to content
Agentmart
Submit a tool

flux-3-prompt-doctor

Use when diagnosing a FLUX 3 brief before generation.

Skill by Black Forest Labs

IndexedMIT★ 136
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/black-forest-labs-flux-3-prompt-doctor

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/flux-3-prompt-doctor

What's inside

Skill name
flux-3-prompt-doctor
Description
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.
License
MIT
Metadata
tags: flux, flux-3, bfl, prompt-doctor, validation, routing · author: Black Forest Labs · version: 1.0.0
Instructions
67 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • metadata.json
  • brief.md · templates/

SKILL.md (first lines)

# FLUX 3 Prompt Doctor

Resolve the decisions that change routing, payload, or production method before a brief
becomes a prompt. Ask only blocking questions; use documented defaults or label
assumptions for everything else. Preserve the user's product names, exact copy, source
roles, and hard constraints verbatim. This skill does not write the final prompt or
call the API.

## Route by what must survive

Every request names its `mode` and carries the matching media field:

| Requirement | Route |
| --- | --- |
| Generate the whole clip from words | `mode: "t2v"`, no media |
| An image must appear on screen exactly as shot | `mode: "i2v"`, `keyframes` |
| Bridge an exact opening and closing frame | `mode: "i2v"`, two keyframes |
| Pass through visual waypoints | `mode: "i2v"`, keyframes as a storyboard |
| Continue from an existing ending | `mode: "v2v"`, `start_video` |
| Render an approved draft without replanning | `mode: "draft_enhance"`, `draft_cache` |

Two questions separate the image routes: must these exact pixels be on screen
(`keyframes`)? Can the source simply be described (then attach nothing)? There is no
field that carries a subject's identity without putting the source on screen; a brief
that needs one either opens each shot from a keyframe containing the subject, or is a
`REVISE`.

## Feasibility

- **Action budget:** one subject action and one camera move per short clip. Revise
  briefs demanding many sequential actions, several locations, exact mechanisms, or
  multiple full dialogue lines.
- **Shot structure:** state one continuous unbroken take, or an explicit sequence:

  ```text
  SHOT ONE: wide aerial of a desert highway at dawn, a single red car speeding through.
  HARD CUT. SHOT TWO: interior close-up, the driver's hands drumming the wheel to the radio.
  HARD CUT. SHOT THREE: from the roadside, the car shrinking into the heat haze.
  Warm engine hum under one continuous music bed across all three shots.
  ```

  Consecutive shots must contrast hard (scale, location, color) or the cut blends into
  a continuous take; each shot needs its own beat; one music bed can run across cuts.
- **Contradictions to catch:** locked-off camera plus tracking; extreme close-up plus
  establishing view; exact frame preservation plus major geometric change; one
  continuous shot plus hard cuts; production-critical generated typography with no
  post fallback; guaranteed speaker identity across separate generations.
- **Reserve for deterministic post** when exactness is a success condition:
  typography, subtitles, logos; frame-accurate sync; final mixing; precise mechanisms;
  cross-generation speaker identity. Generation creates footage and causal intent, not
  a compositor or final mix.

## Verdict

Return exactly one state, with a reason, next action, and a compact handoff
([templates/brief.md](templates/brief.md) when it should be reusable):

- **READY**: route, assumptions, handoff. Recommend a draft first when the concept is
  unproven.
- **NEEDS INFO**: only the blocking questions.
- **REVISE**: name the conflict and the minimum repair.

Non-blocking warnings go under **Production risks**, not a fourth state. Field names
and limits belong to the [API reference](https://docs.bfl.ai); flag intent conflicts
and leave schema validation to `flux-3-generate`.

From black-forest-labs/skills, MIT.

More from black-forest-labs/skills

Signals

Stars
136
Forks
11
Open issues
2
Last commit (this folder)
Aug 7, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Black Forest Labs

Cite this page

flux-3-prompt-doctor skill. Agent Mart. https://agentmart.dev/skills/black-forest-labs-flux-3-prompt-doctor (last updated 2026-10-24)