Video Compressor Gif

Get compressed GIF files ready to post, without touching a single slider. Upload your video files (MP4, MOV, AVI, WebM, up to 200MB), say something like "com...

Security Scan

The skill's requirements and runtime instructions largely match its stated purpose (cloud video → compressed GIF/MP4), but there are a few mismatches and missing provenance details you should be aware of before installing.

Purpose & Capability

The skill claims to convert and compress videos via a cloud backend and only requests a single credential (NEMO_TOKEN) which aligns with that purpose. However, the SKILL.md metadata declares a config path (~/.config/nemovideo/) while the registry metadata reported 'Required config paths: none' — this mismatch could mean the skill expects to read or write a local config directory even though the registry entry didn't advertise it. Also the package has no homepage and an unknown source/owner, reducing provenance.

Instruction Scope

The instructions are specific about authenticating (use NEMO_TOKEN or obtain an anonymous token via the nemovideo API), creating sessions, uploading files, and polling exports — all consistent with the described service. They also instruct the agent to detect install path to set an X-Skill-Platform header and to read YAML frontmatter for attribution; those steps require the agent to inspect its environment/install paths. The skill also instructs automatic anonymous-token generation and storing session_id for subsequent requests (storage location unspecified). These behaviors are reasonable for the service but expand scope beyond pure upload/convert actions and should be acknowledged.

Install Mechanism

This is an instruction-only skill with no install spec or code files, so nothing arbitrary is written to disk by an installer. That limits surface area compared with skills that download or extract archives.

Credentials

Only a single credential (NEMO_TOKEN) is declared as required and the SKILL.md describes using it (or creating a temporary anonymous one). That is proportionate for a cloud API service. No unrelated secrets or multiple credentials are requested.

Persistence & Privilege

The skill does not request always: true and does not declare modifications to other skills or system-wide settings. It does instruct storing a session_id and possibly using ~/.config/nemovideo/, which is normal for session management but the storage location and retention policy are not specified.

Assessment

This skill appears to do what it says: upload video and get compressed GIF/MP4s via the nemovideo cloud API, and it only needs one credential (NEMO_TOKEN). Before installing, consider: (1) provenance — the skill has no homepage and an unknown source/owner, so verify you trust the publisher or test in a limited context first; (2) token handling — the skill can create an anonymous token or use NEMO_TOKEN; if you supply credentials, be sure you trust the backend (mega-api-prod.nemovideo.ai) and prefer short-lived tokens; (3) local file access — SKILL.md references ~/.config/nemovideo/ and asks the agent to detect install path for attribution headers, so expect the skill to inspect its environment/install paths; (4) data privacy — uploading videos sends media to a third-party cloud GPU service; confirm retention and deletion policies if your media is sensitive; (5) if you want tighter control, set NEMO_TOKEN yourself (rather than letting the skill create one) and ask the publisher to clarify where session tokens are stored and for the apparent registry vs SKILL.md mismatch about required config paths.

Getting Started

Got video files to work with? Send it over and tell me what you need — I'll take care of the GIF compression conversion.

Try saying:

• "convert a 10-second screen recording or short clip into a 720p MP4"
• "compress this video into a small looping GIF"
• "converting short video clips into compressed GIFs for sharing for marketers, developers, social media creators"

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.

Video Compressor GIF — Convert Videos to Compressed GIFs

Drop your video files in the chat and tell me what you need. I'll handle the GIF compression conversion on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 10-second screen recording or short clip, ask for compress this video into a small looping GIF, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 720p by default.

One thing worth knowing — shorter clips under 5 seconds produce the smallest and sharpest GIFs.

Matching Input to Actions

User prompts referencing video compressor gif, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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: video-compressor-gif
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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)

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.

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 → "compress this video into a small looping GIF" → Download MP4. Takes 20-40 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 "compress this video into a small looping GIF" — concrete instructions get better results.

Max file size is 200MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Keep source video at 720p or lower before converting for the best GIF file size balance.