Video Editor Freelance

Skip the learning curve of professional editing software. Describe what you want — cut the pauses, add lower-third titles, and export a clean final cut — and...

Security Scan

The skill's requested API token and cloud-render workflow match a video-editing service, but there are inconsistencies (a declared config path in the SKILL.md that isn't listed in the registry) and privacy/credential risks you should understand before installing.

Purpose & Capability

The name/description (AI cloud video editing) aligns with the runtime instructions (upload video, create session, render via nemovideo API) and the single required credential (NEMO_TOKEN) is plausible for that purpose. However the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that was not declared in the registry metadata — this mismatch is unexpected and should be clarified.

Instruction Scope

The SKILL.md contains concrete API calls and a clear workflow (anonymous token acquisition if no NEMO_TOKEN, session creation, SSE editing, upload, export). All actions are directed at the nemovideo API, which is coherent for a cloud editor. Important operational behavior: user video files will be uploaded to a remote server (privacy/retention implications). The instructions do not appear to read unrelated system files or other environment variables, but the explicit mention of a local config directory in the frontmatter suggests potential local config access that isn't otherwise documented.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — there is nothing to write to disk or download during install, which reduces install-time risk.

Credentials

Only NEMO_TOKEN is declared as required, which is proportionate to a remote video-rendering service. But SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry listed no required config paths — this discrepancy could imply the skill intends to read a local config or token file that wasn't advertised. That increases the risk that local credentials/config may be read unexpectedly. Also, uploads of potentially sensitive video/audio data to a third-party endpoint are inherent to the skill and should be considered before providing tokens or content.

Persistence & Privilege

The skill is not always-included and does not request elevated platform privileges. It is user-invocable and allows autonomous invocation (the default), which is expected for skills. There is no evidence it attempts to alter other skills or system-wide settings.

What to consider before installing

Before installing, verify the skill's origin and the nemovideo service: 1) Confirm the owner and that mega-api-prod.nemovideo.ai is the legitimate backend for this vendor. 2) Prefer testing with an anonymous/starter token (as the SKILL.md describes) rather than a long-lived NEMO_TOKEN tied to your account until you trust the service. 3) Ask the publisher about the mysterious ~/.config/nemovideo/ entry (does the skill read local config files?) — the registry metadata did not list any required config paths. 4) Be aware that uploading video/audio will send potentially sensitive content to a remote server — request the service's privacy/retention policy. 5) If possible, run initial tests with non-sensitive content or in a sandboxed environment. 6) If you need higher assurance, ask for the skill source code or an official vendor reference that ties the skill to a known product. These steps will reduce the chance of accidentally exposing credentials or private media.

Getting Started

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

Try saying:

• "edit my raw video clips"
• "export 1080p MP4"
• "cut the pauses, add lower-third titles,"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Video Editor Freelance — Edit and Deliver Client Videos

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

A quick example: upload a 3-minute client interview recording, type "cut the pauses, add lower-third titles, and export a clean final cut", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: breaking long projects into shorter scene clips speeds up processing and gives you more control over each segment.

Matching Input to Actions

User prompts referencing video editor freelance, 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	video-editor-freelance
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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

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 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=<id>, 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the pauses, add lower-third titles, and export a clean final cut" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the widest client compatibility across platforms.

Common Workflows

Quick edit: Upload → "cut the pauses, add lower-third titles, and export a clean final cut" → Download MP4. Takes 1-2 minutes 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.