FPV Immersive Video Prompting
Turns a scene photo plus a target character/route count into a structured FPV image-to-video prompt with matching asset pack.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 7d768c2
The assigned SKILL.md (repo root) links four `references/*.md` deep-dive files that don't resolve at that path -- the real files live one directory down at `skill/references/`, and one named file (`cafe-cat-numbered-stops-case.md`) doesn't exist anywhere in the repo at all -- but the core prompt template is fully self-contained in the main body and produced a genuinely more structured, physically-constrained FPV prompt than an unaided attempt.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 2/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 3/5
What FPV Immersive Video Prompting does
Converts a static scene, character images, aerial map, or drawn route into a directed first-person FPV video prompt for Seedance/Kling/Runway/Veo, choosing between numbered stop-marker mode (close character interactions, interiors) and red-line path-control mode (world-scale drone/flythrough routes), and generating the matching multi-image asset pack. Triggers on image-to-video, one-shot FPV, camera-route, or non-human POV (drone, cat, robot vacuum) prompt requests; not for generic video scripts or editing.
How to install FPV Immersive Video Prompting
git clone https://github.com/zhouwei713/fpv-immersive-video-prompting
cd fpv-immersive-video-prompting
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/fpv-immersive-video-prompting
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger FPV Immersive Video Prompting
-
/fpv-immersive-video-promptingTurns a scene photo plus a target character/route count into a structured FPV image-to-video prompt with matching asset pack.
It also activates on plain-language prompts like these:
-
Turn this drone photo into a first-person flythrough video prompt -
I have a scene image and a route drawing, build me an FPV video prompt -
Generate a POV prompt where a cat explores this room, plus the asset pack
Frequently asked questions
- Is the FPV Immersive Video Prompting skill free?
- Yes. The skill itself is free from zhouwei713/fpv-immersive-video-prompting. SkillProof publishes the install command and an independent test verdict at no cost.
- Does FPV Immersive Video Prompting work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. The assigned SKILL.md (repo root) links four `references/*.md` deep-dive files that don't resolve at that path -- the real files live one directory down at `skill/references/`, and one named file (`cafe-cat-numbered-stops-case.md`) doesn't exist anywhere in the repo at all -- but the core prompt template is fully self-contained in the main body and produced a genuinely more structured, physically-constrained FPV prompt than an unaided attempt.
- What is the FPV Immersive Video Prompting SkillProof Score?
- 7.6/10 — installs cleanly 2/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
- How do I install FPV Immersive Video Prompting?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use FPV Immersive Video Prompting with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.