Skip to main content
skill CX Codex

flux-3-cinematic-inserts — Claude Code skill: how to install

flux-3-cinematic-inserts structures FLUX 3 text-to-video prompts for standalone insert shots and B-roll. It locks camera movement, physics, and scene continuity around a single visual event.

MIT 185 installs ★ 138 updated 2026-09-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add black-forest-labs/skills --skill flux-3-cinematic-inserts -a claude-code
Open on GitHub

What flux-3-cinematic-inserts does

The skill formats prompt specifications for isolated video shots: material details, transitional bridges, macro captures, or capability tests. It builds prompts across six stages: the opening frame, a visible cause, the physical response, the final payoff, a strict continuity contract, and audio textures. The camera remains locked by default and moves only when the physical action demands it.

Pure text generation fails when a scene requires exact typography, multi-step machinery, nuanced human acting, or frame-accurate sync. Those cases require supplied media via flux-3-keyframes-continuation or editorial post-production.

The workflow begins with a low-step run using draft: true to evaluate geometry, lighting, and camera stability before rendering full-step video. If two iterations miss the target, the skill instructs changing the core event rather than swapping adjectives. Finished prompts hand off directly to flux-3-generate.

What it helps with

  • write a standalone B-roll prompt for FLUX 3 text-to-video
  • enforce camera constraints and eliminate unwanted frame cuts
  • describe physical material reactions for video models
  • iterate through draft renders using the ladder review workflow

Example prompts for the agent

  • Write a FLUX 3 insert shot prompt of honey dripping onto a dry wooden board.
  • Create a cinematic B-roll prompt with locked-off camera showing neon light reflecting on wet asphalt.

How to install flux-3-cinematic-inserts

1Skills CLI (Vercel)

npx skills add black-forest-labs/skills --skill flux-3-cinematic-inserts -a claude-code

2Manually: put the files in place

~/.claude/skills/flux-3-cinematic-inserts/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/flux-3-cinematic-inserts/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about flux-3-cinematic-inserts

How to install flux-3-cinematic-inserts in Claude Code?

Run npx skills add black-forest-labs/skills --skill flux-3-cinematic-inserts -a claude-code in your terminal.

What does flux-3-cinematic-inserts do?

It structures text-to-video prompts for FLUX 3 to produce standalone cinematic insert shots with clear physical motion and consistent camera framing.

When should you switch from text-only prompts to conditioning?

Switch to flux-3-keyframes-continuation or post-production when the shot demands exact text rendering, multi-step physical mechanisms, or close human performances.

Source text

SKILL.md · MIT
---
name: flux-3-cinematic-inserts
description: Use when writing a FLUX 3 text-to-video prompt for a standalone shot. Covers shot craft, reliable concept patterns, camera, continuity, and review.
metadata:
  author: Black Forest Labs
  version: "1.0.0"
  tags: flux, flux-3, bfl, text-to-video, cinematic, b-roll, prompting
---

# FLUX 3 Cinematic Inserts

Build one standalone shot around **one motivated physical or atmospheric event**: B-roll,
a bridge, a material detail, a capability test. Reroute when success requires supplied
media (`flux-3-keyframes-continuation`), exact typography, frame-accurate sync, a
multi-step mechanism, close human performance, or finished ad copy; those need
conditioning or post, not a text-only generation.

Before writing, settle the contract in one sentence: the visible cause, the physical
response, and the payoff. Then pick a proven lane from
[references/field-guide.md](references/field-guide.md) (atmospheric light in a medium,
wet reflections, viscous macro, tactile contact and ignition, restrained noir); treat
anything it marks experimental or parked as a test, not a promise.

Write the shot in this order:

1. **Opening frame**: composition, subject, setting, light.
2. **Visible cause**: source and contact point in the same frame as the response.
3. **Physical response**: direction, material behavior, restraint.
4. **Payoff**: one final state that works as an edit point or a still.
5. **Continuity contract**: same set and geometry; no cuts, transitions, frozen or
   repeated frames, or resets.
6. **Audio intent**: name material textures; route critical sync and mixing to post.

Camera is one physical contract: framing, angle, movement, focus. A locked-off camera
cannot track; an extreme close-up cannot establish. Locked and deliberate by default;
move only when it serves the event.

Style must be visible: "tense" becomes rigid posture, shallow breathing, and a slow
push-in; "vintage" becomes a named capture format, grain structure, and practical
light. No unmotivated sparks, bells, or effects.

Draft first (`draft: true`) while the concept is unproven, and judge the draft on event
legibility, composition, camera, and continuity; softness is the low-step trade and
resolves at full quality. Iterate as a ladder, one consequential change per variant:
event geometry, then material or light, then composition, then duration. After two
structurally similar misses, change the concept or the production method, not the
adjectives. Review the result with
[references/review-scorecard.md](references/review-scorecard.md): a technically valid
clip still has to be useful, physically legible, deliberate, and interesting.

Hand the finished prompt to `flux-3-generate` as a text-only request, with the risks and
anything post must own.

© Black Forest Labs · MIT · black-forest-labs/skills

Similar skills

All skills for AI and ML →

From the same set8

Project sponsors

Companies that keep this analytics open