Not in the top 1,000 by GitHub stars
LunarXuan/video-prompt-reverse
High-fidelity AI video prompt reverse-engineering skill for Codex
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
a36d41e10921 → a36d41e10921
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → a36d41e10921
No earlier version was observed for comparison.
68GitHub stars
2stars in 7 days
1skill in this repository
0commits in 30 days
Heat
2.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
video-prompt-reverse
When your agent uses it
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.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
1,437 tokensWhen the skill is activated
Reference documents
3,509 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation cues
- Choose the mode
- Analyze the source
- Compile the deliverables
- Optimize against a target model
Scripts executed separately
scripts/closed_loop.pyscripts/compile_prompt.pyscripts/probe_video.pyscripts/validate_spec.py
Files
README.mddoc2,343 bytesSKILL.mdcore7,349 bytesSKILL.mdcore7,349 bytesSKILL.mdcore7,349 bytesSKILL.mdcore7,349 bytesSKILL.mdcore7,349 bytesSKILL.mdcore7,349 bytesagents/openai.yamlasset335 bytesreferences/analysis-contract.mddoc6,298 bytesreferences/closed_loop_config.example.jsonasset1,173 bytesreferences/model-adapters.mddoc4,785 bytesreferences/model_profiles.jsonasset1,243 bytesreferences/optimization-loop.mddoc3,021 bytesscripts/closed_loop.pyruns15,050 bytesscripts/compile_prompt.pyruns12,649 bytesscripts/probe_video.pyruns6,965 bytesscripts/validate_spec.pyruns6,768 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- video-prompt-reverse
Repository facts
- License
- No license detected
- Created
- Sep 4, 2026
- Last pushed
- Sep 4, 2026
- Forks
- 9
- Open issues
- 0
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 5 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 12 network referencesin 2 files: references/model-adapters.md:17 README.md:32
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 4 files: scripts/closed_loop.py:1 scripts/compile_prompt.py:1 scripts/probe_video.py:1 and 1 more
- 1 reference to secretsin 1 file: scripts/closed_loop.py:30
- No requests to vote in Hot
Show all 17 signals by file
README.md
references/model-adapters.md
- Network accessline 17
- Prefer one coherent 8-second unit per generation. For longer references, split on shot or narrative boundaries and plan extensions or editorial assembly. - When visual continuity matters, recommend first/last-frame or reference-image cond - Network accessline 19
- Current capability reference: https://ai.google.dev/gemini-api/docs/veo - Network accessline 25
- If generating through the legacy API, record model, duration, size, reference asset, and returned job ID. Do not pretend the API exposes a deterministic seed when it does not. - As checked on 2026-09-04, the official Sora video API was ma - Network accessline 27
- Current API reference: https://developers.openai.com/api/reference/typescript/resources/videos/methods/create - Network accessline 33
- Keep dialogue order, language, delivery, and audio cues explicit for audio-capable variants. - Do not emit camera-control JSON or duration limits until the exact Kling endpoint and model version are verified; capabilities differ across ve - Network accessline 35
- Current official overview for Kling 3.0: https://ir.kuaishou.com/node/11216/pdf - Network accessline 42
- Alongside the required Chinese copy prompt, emit a compact model-native English prompt of at most 100 words when following the official Wan2.2 prompt-extension style. - Record task (`t2v`, `i2v`, or `ti2v`), model/checkpoint, resolution, - Network accessline 43
- Record task (`t2v`, `i2v`, or `ti2v`), model/checkpoint, resolution, frame count, sampler, sampling steps, guidance scale, base seed, and whether prompt extension was used. - Official prompt-extension guidance: https://github.com/Wan-Vide - Network accessline 44
- Official prompt-extension guidance: https://github.com/Wan-Video/Wan2.2/blob/main/wan/utils/system_prompt.py - Network accessline 45
- Official inference parameters: https://github.com/Wan-Video/Wan2.2/blob/main/generate.py
scripts/closed_loop.py
scripts/compile_prompt.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/probe_video.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/validate_spec.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 17 facts
- Network access in prose of documentationREADME.md:32Low confidence
- Network access in prose of documentationREADME.md:61Low confidence
- Network access in prose of documentationreferences/model-adapters.md:17Low confidence
- Network access in prose of documentationreferences/model-adapters.md:19Low confidence
- Network access in prose of documentationreferences/model-adapters.md:25Low confidence
- Network access in prose of documentationreferences/model-adapters.md:27Low confidence
- Network access in prose of documentationreferences/model-adapters.md:33Low confidence
- Network access in prose of documentationreferences/model-adapters.md:35Low confidence
- Network access in prose of documentationreferences/model-adapters.md:42Low confidence
- Network access in prose of documentationreferences/model-adapters.md:43Low confidence
- Network access in prose of documentationreferences/model-adapters.md:44Low confidence
- Network access in prose of documentationreferences/model-adapters.md:45Low confidence
- Executable script in code of a file that runsscripts/closed_loop.py:1High confidence
- Access to secrets in code of a file that runsscripts/closed_loop.py:30High confidence
- Executable script in code of a file that runsscripts/compile_prompt.py:1High confidence
- Executable script in code of a file that runsscripts/probe_video.py:1High confidence
- Executable script in code of a file that runsscripts/validate_spec.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
