video-prompt-reverse SKILL.md skillA
video-prompt-reverse from lunarxuan/video-prompt-reverse is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lunarxuan/video-prompt-reverse/video-prompt-reverse@git:20260904.a36d41ePins git:20260904.a36d41e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lunarxuan/video-prompt-reverse
- Path
SKILL.md- Versions recorded
- 2
- Latest version
- git:20260904.a36d41e, committed Sep 4, 2026
- First version recorded
- Sep 4, 2026
- Size
- 7,349 bytes
- Repository stars
- 69
- License
- none declared
Reverse-engineer a supplied video into a shot-by-shot generation specification, displayed evidence frames, and paired Chinese-English prompt packages. Use for requests such as 视频反推提示词, 视频转提示词, 从视频生成提示词, 视频逆向提示词, 逐镜头反推, 分镜拆解并生成提示词, 反推视频 prompt, or video-to-prompt; also use for Veo, Sora, Kling, Wan, generic prompt adaptation, and bounded generate-compare-optimize loops. Do not use for ordinary video summaries or basic transcription.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Video Prompt Reverse Turn a reference video into an executable, evidence-linked generation package. Distinguish semantic recreation from exact reconstruction: a text prompt can preserve scene logic, action, camera language, pacing, and style, but cannot guarantee frame-identical output. Escalate to reference frames or control signals when identity, geometry, or motion fidelity matters. ## Invocation cues Treat “视频反推提示词” and semantically similar requests as direct requests to use this skill. Common equivalents include “视频转提示词”, “从视频生成提示词”, “视频逆向提示词”, “逐镜头反推”, “分镜拆解并生成提示词”, “反推视频 prompt”, and “video-to-prompt”. The user may append a target model, such as Veo, Sora, Kling, or Wan, and may request iterative similarity optimization. ## Choose the mode - **Prompt**: analyze the video and produce two language-specific packages: one Chinese block containing its positive and negative prompts, followed by one English block containing its positive and negative prompts. - **Adapt**: also compile model-native prompts for one or more of `veo`, `sora`, `kling`, `wan`, or `generic`. …
Read the whole file at its exact version.
How to install
mdr add lunarxuan/video-prompt-reverse/video-prompt-reverse@sha256:4de82316c2717ff1The line at the top of this page pins the label git:20260904.a36d41e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sasyalpq66vhkhwc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 4, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260904.a36d41e latest | 2026-09-04 | a36d41e | 7,349 B | A | view · diff |
| git:20260904.53b1201 | 2026-09-04 | 53b1201 | 7,357 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7349 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lunarxuan/video-prompt-reverse · 69 stars · license none declared · pushed 2026-09-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sasyalpq66vhkhwc GET https://markdownregistry.com/api/v1/resolve?ref=lunarxuan/video-prompt-reverse/video-prompt-reverse GET https://markdownregistry.com/api/v1/blob/4de82316c2717ff1b529cff46472b48b6b70c9a9631017ee8f9389904c3fbd7a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.