Video Editing With Gimp

Skip the learning curve of professional editing software. Describe what you want — combine my GIMP-edited image frames into a smooth video with transitions —...

Security Scan

The skill is internally consistent with a cloud-based video-rendering service: it only needs a NEMO_TOKEN to call a remote API and contains no install steps or unrelated credential requests, though a few minor documentation inconsistencies and vague instructions are present.

Purpose & Capability

The skill's name/description (assemble GIMP frames into video) matches the runtime instructions: all actions are remote API calls to a video-rendering backend and file uploads. Requesting a token (NEMO_TOKEN) to authorize API calls is proportionate to the stated purpose.

Instruction Scope

Instructions describe creating/using an auth token, opening SSE connections, uploading files, creating sessions, and polling render status — all consistent with a cloud render pipeline. Minor issues: some header references are vague ('three attribution headers above' but only some headers shown), and the skill asks the agent to detect its install path (to set X-Skill-Platform), which requires reading environment/paths but is explained as setting an attribution header. These are scope/clarity problems rather than clear misuse.

Install Mechanism

No install spec or code is included (instruction-only skill). Nothing will be downloaded or written to disk by an installer step, which reduces risk.

Credentials

The only declared credential is NEMO_TOKEN (primaryEnv) which is appropriate for calling the nemovideo API. The SKILL.md also documents an anonymous-token flow that obtains a short-lived token via network calls. Minor inconsistency: the SKILL.md YAML frontmatter lists a configPaths entry (~/.config/nemovideo/) while registry metadata showed none—this is likely benign but worth clarifying.

Persistence & Privilege

The skill is not marked always:true and does not request system-wide privileges or to modify other skills. It appears to operate per-session against a remote API and stores session_id client-side as needed.

Assessment

This skill uploads your images/video to a third-party service (mega-api-prod.nemovideo.ai) and requires an API token (NEMO_TOKEN). Before installing, verify you trust that service and owner (no homepage or known source is provided). If you prefer privacy, do not set a long-lived NEMO_TOKEN with privileged credentials — use the anonymous token flow or a limited account. Ask the publisher to clarify the minor documentation inconsistencies (missing header list, the YAML configPaths vs registry metadata, and why the agent needs to detect install paths) before granting broad or persistent credentials. If you want extra caution, refrain from sending sensitive imagery or metadata until you confirm service ownership and privacy/retention policies.

Getting Started

Got images or video clips to work with? Send it over and tell me what you need — I'll take care of the AI-assisted video editing.

Try saying:

• "convert a series of PNG frames exported from GIMP into a 1080p MP4"
• "combine my GIMP-edited image frames into a smooth video with transitions"
• "turning GIMP-edited frames or images into a finished video for graphic designers and digital artists"

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.

Video Editing with GIMP — Turn GIMP Frames into Video

Send me your images or video clips and describe the result you want. The AI-assisted video editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a series of PNG frames exported from GIMP, type "combine my GIMP-edited image frames into a smooth video with transitions", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: export your GIMP frames at consistent resolution before uploading for smoother results.

Matching Input to Actions

User prompts referencing video editing with gimp, 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.

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

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

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

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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.

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 "combine my GIMP-edited image frames into a smooth video with transitions" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, PNG, AVI for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "combine my GIMP-edited image frames into a smooth video with transitions" → 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.