Video Editor Filters

Skip the learning curve of professional editing software. Describe what you want — apply a cinematic color grade filter and smooth skin tone across the whole...

Security Scan

The skill's declared purpose (cloud video filter/export) matches its runtime instructions, but there are small metadata inconsistencies and it will upload user videos and obtain/store tokens on an external service — review before installing.

Purpose & Capability

The skill claims to apply AI filters and export videos and its instructions call the nemo video API endpoints for uploads, rendering, credits, and state; requiring a NEMO_TOKEN is coherent. However, the SKILL.md frontmatter lists a configPaths entry (~/.config/nemovideo/) while the registry metadata lists no required config paths — this mismatch should be clarified (does the skill need access to that config dir?).

Instruction Scope

Instructions are narrowly focused on authenticating (using NEMO_TOKEN or anonymously obtaining one), creating a session, uploading video files, driving SSE-based edits, polling render status, and returning a download URL. These actions are consistent with the described video-processing purpose. The skill does instruct the agent to read its own frontmatter and detect install paths to populate attribution headers — that requires filesystem access to the skill file and (optionally) probing common install directories, which is expected but should be noted.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is downloaded or written by an installer. That reduces risk compared to skills that fetch/extract remote archives.

Credentials

Only one credential is declared (NEMO_TOKEN) which fits a cloud video-processing backend. The SKILL.md will automatically obtain an anonymous token if none is present (by POSTing to the external API). The frontmatter's mention of a config path (~/.config/nemovideo/) is not reflected in the registry metadata — clarify whether the skill expects to read that directory (which could contain credentials or preferences).

Persistence & Privilege

always:false and normal autonomous invocation. The skill stores a session_id and will retain/use an obtained token for requests; tokens are described as short-lived (anonymous token valid 7 days). This is proportional to the task but you should be aware the session/token will be stored and used for subsequent API calls.

What to consider before installing

This skill sends any uploaded videos and edit instructions to an external service (https://mega-api-prod.nemovideo.ai) and uses a NEMO_TOKEN (or obtains an anonymous one) to authenticate. That behaviour is consistent with a cloud video-processing tool but has privacy implications: do not upload sensitive footage you wouldn’t want sent to a third party. Note the SKILL.md references a config directory (~/.config/nemovideo/) that is not listed in the registry metadata — ask the publisher whether the skill will read that directory or other local files. If you proceed, consider: (1) only grant NEMO_TOKEN if you trust Nemovideo's service and privacy policy, (2) revoke tokens/credits from the service if you stop using the skill, and (3) avoid uploading confidential media. The metadata mismatch lowers confidence slightly — request clarification from the skill owner before installing.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI filter application.

Try saying:

• "apply a 2-minute travel vlog recorded on a smartphone into a 1080p MP4"
• "apply a cinematic color grade filter and smooth skin tone across the whole clip"
• "applying color and style filters to raw video footage for content 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 Editor Filters — Apply Filters and Export Videos

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

Say you have a 2-minute travel vlog recorded on a smartphone and want to apply a cinematic color grade filter and smooth skin tone across the whole clip — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 60 seconds process significantly faster and let you preview the filter before committing.

Matching Input to Actions

User prompts referencing video editor filters, 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-editor-filters
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

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

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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Common Workflows

Quick edit: Upload → "apply a cinematic color grade filter and smooth skin tone across the whole clip" → 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 "apply a cinematic color grade filter and smooth skin tone across the whole clip" — 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 the widest compatibility across social platforms.