Ai Video Editor Change Words

edit existing video file into updated edited video with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it f...

Security Scan

The skill's requirements and runtime instructions are generally consistent with a cloud-based video edit service, but there are a few small inconsistencies and privacy implications you should understand before use.

Purpose & Capability

The skill claims to perform cloud-based video text replacement and only requests a single service credential (NEMO_TOKEN) needed to call that API. Required formats, endpoints, and session flow in SKILL.md align with that purpose.

Instruction Scope

Instructions are focused on connecting to the nemo API, creating sessions, uploading video, streaming SSE edits, and exporting results. They do instruct the agent to read this file's YAML frontmatter for skill attribution and to probe common install paths to determine X-Skill-Platform; that involves reading paths in the user's home directory, which is limited but outside strictly necessary editing tasks. Importantly, the runtime clearly requires uploading user videos to an external cloud service — a privacy/data-exfiltration consideration for sensitive content.

Install Mechanism

This is an instruction-only skill with no install spec and no code to download or execute. That minimizes installation risk.

Credentials

Only one credential is declared (NEMO_TOKEN) which matches the described API authentication. The SKILL.md also supports obtaining an anonymous token if NEMO_TOKEN is absent. This is proportionate to a cloud service integration. However, the frontmatter inside the SKILL.md lists a configPaths value (~/.config/nemovideo/) while the registry metadata showed none — a minor inconsistency about whether a local config is expected or read.

Persistence & Privilege

The skill does not request always:true, does not install background components, and does not ask to modify other skills. It will create ephemeral sessions/tokens for cloud rendering but does not request persistent elevated privileges.

Assessment

This skill appears to do what it says: it uploads your video to nemo's cloud rendering service and returns an edited file. Before installing or invoking it, consider: (1) Privacy — your video (and any spoken/text content) will be uploaded to https://mega-api-prod.nemovideo.ai; do not use it for sensitive or private footage unless you trust that service. (2) Credential handling — you can supply your own NEMO_TOKEN or let the skill obtain an anonymous token; treat any token like a secret. (3) Local reads — the skill may read its own frontmatter and check common install paths or a ~/.config/nemovideo/ path for attribution/versioning; if you disallow file reads, block those operations. (4) Inconsistency — registry metadata omitted configPaths that SKILL.md lists; confirm with the publisher if you need to allow a local config directory. If you need high assurance (privacy, compliance), run this only with non-sensitive videos or use a service account/token you control.

Getting Started

Share your existing video file and I'll get started on AI text replacement editing. Or just tell me what you're thinking.

Try saying:

• "edit my existing video file"
• "export 1080p MP4"
• "change the word 'Free Trial' to"

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.

AI Video Editor Change Words — Replace Words in Videos

This tool takes your existing video file and runs AI text replacement editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-minute product demo video with outdated pricing text and want to change the word 'free plan' to 'Get Started' in the video — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips with clear audio produce the most accurate word replacements.

Matching Input to Actions

User prompts referencing ai video editor change words, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: ai-video-editor-change-words
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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)

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

Common Workflows

Quick edit: Upload → "change the word 'Free Trial' to 'Get Started' in the video" → 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 "change the word 'Free Trial' to 'Get Started' in the video" — 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.