Tiktok Editing With Ai

Skip the learning curve of professional editing software. Describe what you want — cut to the beat, add trending captions, and trim dead air for a 30-second...

Security Scan

The skill's declared behavior (cloud TikTok editing) matches the network calls and token use in SKILL.md, but the publisher is unknown, metadata references a local config path not used in the instructions, and you must trust the external nemo video service before giving it an auth token or uploading private video files.

Purpose & Capability

The name/description (AI TikTok editing) matches the runtime instructions: an external cloud backend at mega-api-prod.nemovideo.ai, upload endpoints, render/export endpoints, and a single service credential (NEMO_TOKEN). Required artifacts (video upload, render, download) are proportional to the stated purpose.

Instruction Scope

SKILL.md directs network operations to a single third‑party API, session creation, file uploads, SSE streaming, polling, and anonymous-token creation when NEMO_TOKEN is absent. These actions are consistent with cloud rendering, but the doc also requires automated platform detection (X-Skill-Platform) and mentions a config path in frontmatter (~/.config/nemovideo/) even though the instructions do not describe reading that path — a minor inconsistency worth noting. The instructions do not ask to read arbitrary local files beyond the declared env var.

Install Mechanism

This is an instruction-only skill with no install spec and no code files. That minimizes disk-write/executable install risk: the skill will only perform runtime HTTP calls as described.

Credentials

The only required credential is NEMO_TOKEN (declared primaryEnv) which is appropriate for a service that uploads and renders video. However: 1) providing a NEMO_TOKEN grants the skill bearer whatever API permissions that token represents (uploads, renders, credits, account access) — review what that token controls; 2) SKILL.md also describes the ability to mint an anonymous token via the service if no token is present (100 free credits, 7-day expiry), so the skill can operate without a user token but will route media to the external provider; and 3) metadata lists a config path (~/.config/nemovideo/) that is not referenced in the instructions — unclear whether the skill will attempt to read or write that path.

Persistence & Privilege

The skill is not always-enabled and does not request system-wide persistence. It can be invoked autonomously per platform defaults, which is normal. There is no install-time modification of other skills or system settings described.

What to consider before installing

Key things to consider before installing: 1) Source reputation: there is no homepage or identifiable publisher — that increases risk; verify the nemovideo.ai service independently before handing over tokens or private videos. 2) Token scope: a provided NEMO_TOKEN likely grants upload/render/credit access to your account — only supply it if you trust the service. Prefer using the anonymous-token path for testing (it expires) and try non-sensitive sample videos first. 3) Data privacy: video/audio you upload will be sent to mega-api-prod.nemovideo.ai; review their privacy/retention policy and whether uploads may be used for model training. 4) Metadata mismatch: the frontmatter references a local config path (~/.config/nemovideo/) not described in the runtime steps — ask the author whether the skill reads/writes that path. 5) If you require confidentiality, do not install or upload sensitive footage until you confirm the service's policies and the skill's origin. If you proceed, monitor what token you provide and limit its permissions where possible.

Getting Started

Share your raw video clips and I'll get started on AI TikTok editing. Or just tell me what you're thinking.

Try saying:

• "edit my raw video clips"
• "export 1080p MP4"
• "cut to the beat, add trending"

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.

TikTok Editing with AI — Edit and Export TikTok Videos

Send me your raw video clips and describe the result you want. The AI TikTok editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute vertical phone recording, type "cut to the beat, add trending captions, and trim dead air for a 30-second TikTok", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: vertical 9:16 footage processes best and skips any cropping step.

Matching Input to Actions

User prompts referencing tiktok editing with ai, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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	tiktok-editing-with-ai
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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)

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

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.

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=<id> (get <id> 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

Common Workflows

Quick edit: Upload → "cut to the beat, add trending captions, and trim dead air for a 30-second TikTok" → 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 "cut to the beat, add trending captions, and trim dead air for a 30-second TikTok" — 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 Shorts.