Ai Video Editor By Text

Turn a 2-minute interview recording into 1080p edited MP4 clips just by typing what you need. Whether it's editing videos by typing plain-text instructions i...

Security Scan

The skill's stated purpose (cloud video editing) matches most of its runtime instructions, but there are metadata inconsistencies and privacy-sensitive behaviors (automatic anonymous token creation, uploading user video to an external service, and references to reading local install/config paths) that warrant caution before installing.

Purpose & Capability

The name/description map to cloud-based video editing and the skill only requires a single service token (NEMO_TOKEN) and API endpoints on mega-api-prod.nemovideo.ai — that is coherent. However the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) which the registry metadata summary earlier said was 'none' — a mismatch worth calling out.

Instruction Scope

Instructions direct the agent to obtain/upload user video files and to POST them to external endpoints (rendering pipeline). The skill also instructs reading the skill's YAML frontmatter and detecting install path (e.g., ~/.clawhub/, ~/.cursor/skills/) to populate attribution headers. Automatic anonymous-token acquisition (if NEMO_TOKEN is missing) means the agent will create credentials and proceed without explicit user consent. These actions are within the declared purpose but are privacy-sensitive and broaden what the agent will read/transmit.

Install Mechanism

No install spec and no code files — instruction-only. That minimizes disk-write/install risk; nothing is downloaded or executed beyond API calls described in the SKILL.md.

Credentials

Only a single credential (NEMO_TOKEN) is declared as required, which is appropriate for a cloud editing service. However the skill's frontmatter mentions a config path (~/.config/nemovideo/) and instructs reading local install paths for attribution — if the agent actually reads those files or config directories it may access additional local data beyond the declared env var.

Persistence & Privilege

always:false (not force-included) and no instructions to modify other skills or system-wide settings. The skill does rely on session tokens and queues remote jobs (jobs can be orphaned), but it does not request elevated or persistent platform privileges.

What to consider before installing

This skill appears to legitimately implement cloud video editing, but consider these before installing: - Privacy: The skill will upload user video/audio to mega-api-prod.nemovideo.ai. Do not use it with sensitive or confidential footage unless you trust that service and verified its privacy policy. - Automatic token creation: If you don't set NEMO_TOKEN, the skill will obtain an anonymous token and proceed automatically. If you prefer control, set your own NEMO_TOKEN before using the skill. - Local reads: The skill asks to read its YAML frontmatter and detect install paths (and its metadata references ~/.config/nemovideo/). Confirm whether the agent will actually read those local files and whether that could expose anything you care about. - Attribution headers: The skill mandates adding X-Skill-Source/X-Skill-Version/X-Skill-Platform to every API call; ensure these values are acceptable for your environment. - No install code: There is no code written to disk by the skill itself (instruction-only), which reduces supply-chain risk — but all data transfer happens at runtime to the third-party API. Recommended actions: provide an explicit NEMO_TOKEN if you can, avoid uploading sensitive content, review the remote service domain and its privacy/terms, monitor network requests during first use, and decide whether automatic anonymous-token issuance is acceptable for your risk posture.

Getting Started

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

Try saying:

• "edit my raw video footage"
• "export 1080p MP4"
• "cut the pauses, add a title"

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.

1. 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.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. 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.

AI Video Editor by Text — Edit Videos with Text Commands

This tool takes your raw video footage and runs text-command AI editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-minute interview recording and want to cut the pauses, add a title card at the start, and fade to black at the end — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: be specific in your text commands — 'remove the first 10 seconds' works better than 'trim the beginning'.

Matching Input to Actions

User prompts referencing ai video editor by text, 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":"<lang>"}. 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/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"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.

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

• X-Skill-Source: ai-video-editor-by-text
• 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.

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

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the pauses, add a title card at the start, and fade to black at the end" — 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 platforms and devices.

Common Workflows

Quick edit: Upload → "cut the pauses, add a title card at the start, and fade to black at the end" → 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.