Keyframes Video Editing

edit video clips into keyframe-edited clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. video editors and content creators use it for...

Security Scan

The skill's requests and runtime instructions align with a cloud-based video-editing service: it needs a single service token, uploads user videos to a remote backend, and contains no unexpected binaries or installs.

Purpose & Capability

The skill advertises cloud keyframe video editing and its instructions exclusively describe uploading media, creating a session, streaming edits (SSE), and exporting rendered MP4s. Requesting a service token (NEMO_TOKEN) and calling the described nemovideo.ai endpoints is proportionate to that purpose. One small inconsistency: the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata lists no required config paths.

Instruction Scope

Instructions stay within video-editing scope (check token, create session, upload files, use SSE, export). They explicitly instruct the agent to upload user-provided media to an external cloud API and to stream status to the user. This is expected for a cloud rendering service, but it means user media and generated session tokens will leave the local environment — ensure user consent. The skill also derives an attribution header from an install path (detects platform from install path), which may be ambiguous for an instruction-only skill.

Install Mechanism

No install spec and no code files — lowest-risk distribution model. The skill is instruction-only and relies on existing runtime HTTP ability; nothing is downloaded or written by an installer.

Credentials

Only NEMO_TOKEN is declared as required/primary, which matches a cloud API service. The skill also supports obtaining an anonymous token by calling the service if the env var is missing. The metadata in SKILL.md references a config path (~/.config/nemovideo/) which is not present in the registry's required config paths — clarify whether the agent will read that path or store tokens there.

Persistence & Privilege

always is false and there is no installation, so the skill does not request permanent/force-included presence or elevated privileges. It does suggest keeping a session_id for in-session operations, which is normal.

Assessment

This skill will upload your videos and associated edit commands to a third-party cloud service (mega-api-prod.nemovideo.ai) and requires a NEMO_TOKEN (or it will request an anonymous token for you). Before installing, be comfortable with sending your media to that service and check its privacy/retention policy. Note the SKILL.md mentions a local config path (~/.config/nemovideo/) but the registry metadata does not — ask the publisher whether tokens or session state will be written locally. If you prefer control, provide your own NEMO_TOKEN rather than letting the skill obtain an anonymous token automatically.

Getting Started

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

Try saying:

• "edit my video clips"
• "export 1080p MP4"
• "set keyframes to zoom in at"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Keyframes Video Editing — Edit Videos with Keyframe Control

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

Say you have a 2-minute interview clip and want to set keyframes to zoom in at 0:15 and fade out at 1:45 — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips with fewer keyframes render significantly faster.

Matching Input to Actions

User prompts referencing keyframes video editing, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is keyframes-video-editing, 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.

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 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)

Common Workflows

Quick edit: Upload → "set keyframes to zoom in at 0:15 and fade out at 1:45" → 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 "set keyframes to zoom in at 0:15 and fade out at 1:45" — 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 widest compatibility across platforms.