Ai Video Editor On Android

Get edited MP4 clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like "t...

Security Scan

The skill's requirements and runtime instructions are generally consistent with an AI video-editing service that talks to a remote API, but there are a few small metadata/instruction mismatches and privacy considerations you should review before use.

Purpose & Capability

Name/description (AI video editing) align with the declared primary credential (NEMO_TOKEN) and the runtime instructions which call a remote rendering API. No unrelated credentials or unrelated binaries are requested. One inconsistency: the skill frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata above listed no required config paths — this is likely an authoring mismatch but not clearly malicious.

Instruction Scope

SKILL.md instructs the agent to (a) use NEMO_TOKEN or request an anonymous token from https://mega-api-prod.nemovideo.ai, (b) create sessions, send SSE messages, and upload files (either via filesystem paths or URLs). It also asks the agent to read the skill's YAML frontmatter and detect the agent install path to set X-Skill-Platform headers. Those file-system checks (detecting install path, reading this file's frontmatter, and possibly accessing ~/.config/nemovideo/) are limited in scope but should be noted: the skill will need access to uploaded video files and may probe the agent's install path/config location to set attribution headers.

Install Mechanism

Instruction-only skill with no install spec and no code files — minimal on-disk footprint and no arbitrary downloads. This is the lowest-risk install mechanism.

Credentials

Only one required environment variable (NEMO_TOKEN) is declared as the primary credential, which is proportionate for a remote video editing API. The SKILL.md also describes generating an anonymous token if NEMO_TOKEN is absent. Again, the only minor mismatch is that the frontmatter lists a configPaths value (~/.config/nemovideo/) which the registry metadata did not; that suggests the skill may expect to read a local config path for tokens or provenance.

Persistence & Privilege

always:false and no install steps that write persistent system-wide configuration are present. The skill requests only session tokens for remote API calls and does not request automatic or persistent agent-wide elevation. Autonomous invocation is enabled by default (normal) but not combined with always:true or broad unrelated credential access.

Assessment

This skill appears to be a straightforward client for a remote video-editing service (https://mega-api-prod.nemovideo.ai). Before using: - Only supply NEMO_TOKEN if you trust the service; the token grants the skill permission to create sessions and render/export videos. - Uploaded videos will be transmitted to the remote service; do not upload sensitive/private footage unless you’ve verified the provider and its privacy/retention policy. - The skill can create an anonymous token for you if no NEMO_TOKEN is present; anonymous tokens have limited credits but still transmit data to the same backend. - The skill may read its SKILL.md frontmatter and probe common install paths (e.g., ~/.clawhub, ~/.cursor) and possibly ~/.config/nemovideo/ if present — this is for header attribution but means the agent may check those paths. If you prefer, run the skill in an environment where those paths are empty or restricted. - Confirm the service domain and ownership (the package source is unknown). If you need stronger assurance, ask the publisher for a homepage/owner contact, review their privacy policy/terms, and prefer short-lived or limited-scope tokens rather than long-lived credentials. Confidence is medium because the skill is instruction-only and coherent, but there's a small metadata mismatch (configPaths) and the backend domain is not documented in the registry entry; those would benefit from clarification.

Getting Started

Send me your raw video footage and I'll handle the AI video editing. Or just describe what you're after.

Try saying:

• "edit a 60-second phone recording from an Android device into a 1080p MP4"
• "trim the clip, add transitions, and overlay background music"
• "editing phone-recorded videos into polished clips for social media for Android users and mobile content creators"

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 on Android — Edit and Export Videos on Mobile

Send me your raw video footage 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 60-second phone recording from an Android device, type "trim the clip, add transitions, and overlay background music", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 2 minutes process significantly faster on mobile connections.

Matching Input to Actions

User prompts referencing ai video editor on android, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

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

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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

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

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.

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 "trim the clip, add transitions, and overlay 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 Android apps and social platforms.

Common Workflows

Quick edit: Upload → "trim the clip, add transitions, and overlay background music" → 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.