功能描述

convert still images into animated photo videos with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. TikTok creators use it for turning static...

使用说明 (SKILL.md)

Getting Started

Got still images to work with? Send it over and tell me what you need — I'll take care of the AI video creation.

Try saying:

"convert five vacation photos in JPG format into a 1080p MP4"
"turn my photos into a slideshow video with transitions and music"
"turning static photos into shareable videos for TikTok creators"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer \x3Ctoken>, Content-Type: application/json, and body {"task_name":"project","language":"\x3Cdetected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Image to Video CapCut — Convert Photos Into Shareable Videos

Name: Image To Video Capcut
Author: francemichaell-15

Send me your still images and describe the result you want. The AI video creation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload five vacation photos in JPG format, type "turn my photos into a slideshow video with transitions and music", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: using fewer than 10 images keeps the output tight and processes faster.

Matching Input to Actions

User prompts referencing image to video capcut, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...	Action	Skip SSE?
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"	→ §3.3 Credits	✅
"status" / "状态" / "show tracks"	→ §3.4 State	✅
"upload" / "上传" / user sends file	→ §3.2 Upload	✅
Everything else (generate, edit, add BGM…)	→ §3.1 SSE	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
`/api/tasks/me/with-session/nemo_agent`	POST	Start a new editing session. Body: `{"task_name":"project","language":"\x3Clang>"}`. Returns `session_id`.
`/run_sse`	POST	Send a user message. Body includes `app_name`, `session_id`, `new_message`. Stream response with `Accept: text/event-stream`. Timeout: 15 min.
`/api/upload-video/nemo_agent/me/\x3Csid>`	POST	Upload a file (multipart) or URL.
`/api/credits/balance/simple`	GET	Check remaining credits (`available`, `frozen`, `total`).
`/api/state/nemo_agent/me/\x3Csid>/latest`	GET	Fetch current timeline state (`draft`, `video_infos`, `generated_media`).
`/api/render/proxy/lambda`	POST	Start export. Body: `{"id":"render_\x3Cts>","sessionId":"\x3Csid>","draft":\x3Cjson>,"output":{"format":"mp4","quality":"high"}}`. Poll status every 30s.

Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is image-to-video-capcut, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

Include Authorization: Bearer \x3CNEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with `?bind=\x3Cid>` (get `\x3Cid>` from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
`heartbeat` / empty `data:`	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

"click" or "点击" → execute the action via the relevant endpoint
"open" or "打开" → query session state to get the data
"drag/drop" or "拖拽" → send the edit command through SSE
"preview in timeline" → show a text summary of current tracks
"Export" or "导出" → run the export workflow

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Common Workflows

Quick edit: Upload → "turn my photos into a slideshow video with transitions and music" → Download MP4. Takes 30-60 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn my photos into a slideshow video with transitions and music" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, HEIC for the smoothest experience.

Export as MP4 for widest compatibility across TikTok, Instagram, and YouTube.

安全使用建议

This skill appears to call a third‑party rendering API to turn images into videos, which matches its description — but there are a few red flags to resolve before you install or use it with sensitive content: - Confirm where tokens and session IDs are stored: ask the author whether the anonymous token or session_id will be written to disk (and if so, what path and file permissions). If you prefer, supply your own NEMO_TOKEN rather than letting the skill create one. - Verify the backend domain (mega-api-prod.nemovideo.ai): check its reputation, privacy policy, and data retention rules before uploading personal photos or private audio. - Ask why the registry declares NEMO_TOKEN as required when the SKILL.md documents automatic anonymous-token creation — this mismatch should be fixed. - Clarify whether the skill will probe local install paths (e.g., ~/.clawhub/, ~/.cursor/) to derive X-Skill-Platform; if you want to avoid local filesystem checks, request an option to force a platform header or suppress that behavior. If you cannot get these clarifications or you must handle sensitive images, avoid using the skill or only use it with non-sensitive sample images and provide an explicit, short-lived token you can revoke afterwards.

功能分析

Type: OpenClaw Skill Name: image-to-video-capcut Version: 1.0.0 The skill is classified as suspicious because SKILL.md instructs the agent to use risky capabilities, including network access to an external API (mega-api-prod.nemovideo.ai) and local environment discovery (detecting install paths and reading the NEMO_TOKEN environment variable). While these actions are aligned with the stated purpose of converting images to video via a cloud service, the provided criteria mandate a suspicious classification for such behaviors even when plausibly necessary. No evidence of malicious intent, such as unauthorized data exfiltration or persistence, was found in SKILL.md or _meta.json.

能力评估

ℹ Purpose & Capability

Name/description match the instructions (calls a remote rendering API to convert images to videos). Requesting a NEMO_TOKEN is expected for a third‑party API. However, registry metadata (required env/config) and the SKILL.md disagree: SKILL.md explains how to obtain an anonymous token automatically if NEMO_TOKEN is not present, yet the registry lists NEMO_TOKEN as required. The SKILL.md also includes a configPaths entry (~/.config/nemovideo/) while the registry reported no required config paths — an internal inconsistency.

⚠ Instruction Scope

Runtime instructions only perform network calls to the named API and handle user file uploads, SSE, and polling — which is coherent for a cloud render skill. Concerns: (1) headers include a platform value derived from install paths (e.g., checking ~/.clawhub/ or ~/.cursor/skills/) which implies probing local filesystem state; (2) SKILL.md tells the agent to 'store the returned session_id' but does not specify where (memory vs disk), and metadata references a config path. These are ambiguous and could lead to unexpected local file writes or filesystem probing not explained in the description.

✓ Install Mechanism

No install spec and no code files — instruction-only. This is the lowest-risk install mechanism; nothing is downloaded or written by an installer per the package metadata.

ℹ Credentials

Only one credential is declared (NEMO_TOKEN) which is proportionate for a third‑party rendering API. But SKILL.md will POST to an anonymous-token endpoint to generate a token if NEMO_TOKEN is not set, so requiring NEMO_TOKEN in the registry is inconsistent with the documented behavior. No other unrelated secrets are requested.

⚠ Persistence & Privilege

The skill is not always-enabled and uses normal autonomous invocation. However, it instructs creating/storing an anonymous token and a session_id and references ~/.config/nemovideo/ in frontmatter. It's unclear whether tokens or session state will be persisted to disk (and to what path) or only kept in-memory. That ambiguity increases the risk of unintended persistent credentials or files.

版本历史

v1.0.0

Initial release of Image to Video CapCut. - Convert JPG, PNG, WEBP, and HEIC images (up to 200MB) into 1080p MP4 videos. - Cloud GPU processing delivers quick video creation (30–60 seconds for typical jobs). - Simple authentication flow with 100 free credits for new users. - Automatically matches user requests to editing, upload, export, and credits actions. - Exports optimized, shareable videos for TikTok and other platforms. - Clear error handling and guidance for supported files, credits, and account setup.

元数据

Slug image-to-video-capcut

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Image To Video Capcut 是什么？

convert still images into animated photo videos with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. TikTok creators use it for turning static... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 65 次。

如何安装 Image To Video Capcut？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-to-video-capcut」即可一键安装，无需额外配置。

Image To Video Capcut 是免费的吗？

是的，Image To Video Capcut 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Image To Video Capcut 支持哪些平台？

Image To Video Capcut 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Image To Video Capcut？

由 francemichaell-15（@francemichaell-15）开发并维护，当前版本 v1.0.0。

Image To Video Capcut