功能描述

Turn a 60-second raw video clip into 1080p edited video clips just by typing what you need. Whether it's generating CapCut-style videos with effects and text...

使用说明 (SKILL.md)

Getting Started

Ready when you are. Drop your video clips here or describe what you want to make.

Try saying:

"generate a 60-second raw video clip into a 1080p MP4"
"generate a CapCut-style edited video with transitions, text overlays, and background music"
"generating CapCut-style videos with effects and text automatically for TikTok creators"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

Generate a UUID as client identifier
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Generator CapCut — Generate CapCut-Style Videos Fast

Name: Generator Capcut
Author: francemichaell-15

This tool takes your video clips and runs AI video generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 60-second raw video clip and want to generate a CapCut-style edited video with transitions, text overlays, and background music — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 30 seconds process faster and get sharper results.

Matching Input to Actions

User prompts referencing generator 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
`X-Skill-Source`	`generator-capcut`
`X-Skill-Version`	frontmatter `version`
`X-Skill-Platform`	auto-detect: `clawhub` / `cursor` / `unknown` from install path

All requests must include: Authorization: Bearer \x3CNEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

Error Codes

0 — success, continue normally
1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
1002 — session not found; create a new one
2001 — out of credits; anonymous users get a registration link with ?bind=\x3Cid>, registered users top up
4001 — unsupported file type; show accepted formats
4002 — file too large; suggest compressing or trimming
400 — missing X-Client-Id; generate one and retry
402 — free plan export blocked; not a credit issue, subscription tier
429 — rate limited; wait 30s and retry 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.

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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 → "generate a CapCut-style edited video with transitions, text overlays, and background 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 "generate a CapCut-style edited video with transitions, text overlays, and background music" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

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

安全使用建议

This skill appears to do what it claims (upload your video to a cloud renderer), but there are a few reasons to be cautious: 1) There is no homepage or source repository to verify the service and its privacy/security practices. 2) The SKILL.md will upload your media to a third-party endpoint and can obtain and store an anonymous NEMO_TOKEN if none is provided — if your videos are sensitive, do not use this with private content. 3) Registry metadata and the SKILL.md disagree about config paths (SKILL.md references ~/.config/nemovideo/) — ask the author to explain and provide a privacy/retention policy and source code. Recommended steps before installing: test with non-sensitive sample videos, request the service's privacy policy and retention/deletion API, prefer supplying your own token if you have one, and ask the publisher for a homepage or repository to confirm legitimacy.

功能分析

Type: OpenClaw Skill Name: generator-capcut Version: 1.0.0 The generator-capcut skill is a legitimate integration for an AI-driven video editing service hosted at mega-api-prod.nemovideo.ai. The SKILL.md file provides clear instructions for the agent to manage authentication tokens, handle file uploads, and interact with a cloud rendering pipeline. There are no indicators of data exfiltration, malicious code execution, or unauthorized access to sensitive system files.

能力评估

ℹ Purpose & Capability

The skill claims to perform cloud video editing and its runtime instructions describe uploading clips, creating sessions, streaming SSE, and starting renders on a remote API (mega-api-prod.nemovideo.ai) — these actions are coherent with the stated purpose. However, registry metadata and the SKILL.md disagree: the top-level registry says no required config paths while the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). Also there is no homepage or source repository listed, making it hard to verify the backend/service.

✓ Instruction Scope

The SKILL.md focuses on network interactions with the named backend, token handling, uploads, SSE streaming, polling render status, and response translation. It does not (in the visible portion) instruct reading unrelated local files or environment variables beyond NEMO_TOKEN. These actions stay within editing/export scope, but they do involve sending user media and metadata to a third-party service.

✓ Install Mechanism

Instruction-only skill with no install spec or code files — lowest install risk. The runtime relies on the agent performing HTTP requests and uploads rather than installing binaries.

ℹ Credentials

Only NEMO_TOKEN is declared as required (primaryEnv), which is appropriate for a cloud API. However, the SKILL.md also documents a self-service anonymous-token flow (POST to /api/auth/anonymous-token) that will create and store a token if NEMO_TOKEN is missing — raising the question of why NEMO_TOKEN is mandatory in registry metadata. The SKILL.md frontmatter also references a config path (~/.config/nemovideo/) that the registry metadata omitted.

✓ Persistence & Privilege

Skill does not request always:true and is user-invocable; it instructs maintaining per-session session_id and tokens for the duration of operations, which is normal for a remote-rendering integration. No instructions (in the visible content) to modify other skills or global agent settings.

版本历史

v1.0.0

Generator CapCut 1.0.0 — Initial Release - Instantly generate CapCut-style edited videos (1080p, with effects, text, BGM) from raw clips in 30-60 seconds. - Seamless cloud workflow: upload clip, describe your desired edits, and download the result—no manual timeline editing or export config. - Automatic setup: creates a cloud session and acquires a free-use token if not detected. - Supports batch and iterative editing with session state for refining results. - Provides real-time status, credit checks, export, and troubleshooting for uploads (max 500MB, most standard formats). - All API requests include required attribution headers for correct operation.

元数据

Slug generator-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

Generator Capcut 是什么？

Turn a 60-second raw video clip into 1080p edited video clips just by typing what you need. Whether it's generating CapCut-style videos with effects and text... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 48 次。

如何安装 Generator Capcut？

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

Generator Capcut 是免费的吗？

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

Generator Capcut 支持哪些平台？

Generator 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 Generator Capcut？

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

Generator Capcut