Instagram Editor Ai

Cloud-based instagram-editor-ai tool that handles editing and formatting videos for Instagram Reels and Stories. Upload MP4, MOV, AVI, WebM files (up to 500M...

Security Scan

The skill's behavior largely matches a cloud video editor, but its runtime instructions ask the agent to probe local install/config paths and will upload your videos and the NEMO_TOKEN to an external API — those extra filesystem probes and the unknown upstream service are reasons for caution.

Purpose & Capability

Name/description (cloud Instagram video editing) align with the actions in SKILL.md: uploading video files and requesting render/export from https://mega-api-prod.nemovideo.ai using an API token (NEMO_TOKEN). Requiring a service token and upload endpoints is expected for this purpose.

Instruction Scope

Instructions include expected behaviors (uploading files, SSE, polling render status) but also say the agent should detect an install path (~/.clawhub/ or ~/.cursor/skills/) to set an attribution header and reference a config path (~/.config/nemovideo/). Probing those filesystem locations is unrelated to editing content and grants the skill the ability to read local config/install state; this is scope creep and worth flagging. The skill will also instruct the agent to read local file paths when uploading user-supplied videos (expected) and to store session IDs (unspecified where).

Install Mechanism

Instruction-only skill with no install spec or bundled code — lowest install risk. Nothing is downloaded or written by a declared installer in the metadata, though the skill may create or use per-session data during runtime.

Credentials

Only a single credential (NEMO_TOKEN) is required and it's the primary credential used for authorization to the remote service, which is proportionate. However, granting any token will allow the skill to send that secret to the external API (nemovideo.ai). Metadata also declares a config path, implying potential local config access beyond the single env var.

Persistence & Privilege

Skill is not always:true and does not request broad platform privileges. It instructs saving session_id and references a config directory, but does not declare forced persistence. Autonomous invocation is allowed (platform default) but not a standalone red flag here.

What to consider before installing

This skill appears to do what it says (cloud video editing) but note three practical concerns: 1) it will upload whatever video files you give it to an external endpoint (mega-api-prod.nemovideo.ai) — do not upload sensitive video or audio you wouldn't want transmitted; 2) it will use whichever NEMO_TOKEN is available (or obtain an anonymous token) — treat that token as a secret and consider using a throwaway/limited token if possible; 3) the instructions explicitly describe probing local install/config paths (~/.clawhub/, ~/.cursor/skills/, ~/.config/nemovideo/) to set headers, which is unnecessary for core editing and increases privacy exposure. The skill has no source code or install spec to review and its origin is unknown. If you decide to proceed: prefer anonymous tokens, avoid uploading sensitive content, and don’t grant persistent credentials or place your primary secrets in NEMO_TOKEN unless you trust nemovideo.ai and the skill author.

Getting Started

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

Try saying:

• "edit my video clips"
• "export 1080p MP4"
• "crop to 9:16, add trending captions,"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Instagram Editor AI — Edit and Export Instagram Videos

Drop your video clips in the chat and tell me what you need. I'll handle the AI Instagram editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 60-second vertical phone recording, ask for crop to 9:16, add trending captions, and cut to 30 seconds for a Reel, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — vertical 9:16 video works best for Reels and Stories output.

Matching Input to Actions

User prompts referencing instagram editor 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is instagram-editor-ai, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

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

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.

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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

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 → "crop to 9:16, add trending captions, and cut to 30 seconds for a Reel" → 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 "crop to 9:16, add trending captions, and cut to 30 seconds for a Reel" — 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 best Instagram upload compatibility.