Trimmer Flutter

Get stabilized trimmed clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something...

Security Scan

The skill's behavior mostly matches a cloud video-processing tool, but there are inconsistencies and a few scope/privilege details (automatic token issuance, hidden tokens, filesystem attribution detection) that deserve caution before installing.

Purpose & Capability

The skill claims to upload user videos to a cloud render backend and requires a NEMO_TOKEN — that is consistent with a cloud video service. However the SKILL.md frontmatter references a config path (~/.config/nemovideo/) for attribution/behavior while the registry metadata lists no required config paths, which is an internal inconsistency to clarify.

Instruction Scope

Runtime instructions direct the agent to upload user media to https://mega-api-prod.nemovideo.ai, stream SSE responses, poll state, and automatically obtain an anonymous token if NEMO_TOKEN is absent. They also instruct the agent to detect the install path to populate attribution headers (requires reading local install paths) and to 'store' session_id/token for subsequent requests. Hiding raw API responses/tokens from the user is explicitly required. These behaviors are plausible for the service but expand the agent's actions beyond simple request forwarding (filesystem access, secret handling, persistent storage) and are not fully specified.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest installation risk. Nothing is downloaded or written by an install step in the manifest.

Credentials

Only NEMO_TOKEN is declared as required, which is appropriate for a cloud API. However SKILL.md implies additional local context (install path detection and a config directory) that could require reading files or paths not declared in the registry. The agent will also create/obtain an anonymous token automatically if NEMO_TOKEN is missing — that token is returned by the remote service and the instructions ask to keep it hidden, so storage/persistence behavior should be clarified.

Persistence & Privilege

always:false and no claims to modify other skills or system-wide settings. The only persistence requested is storing session_id (and using the token for up to 7 days) which is typical for sessioned cloud APIs, but where/how these values are stored is unspecified.

What to consider before installing

This skill will upload any video you provide to a third‑party backend (mega-api-prod.nemovideo.ai) and uses a bearer token (NEMO_TOKEN) for authorization. If you don't supply a token it will request an anonymous token for you and instruct the agent to keep that token hidden — ask where and how that token/session_id will be stored (in memory only, or persisted to disk/config?). Clarify the config-path mention (~/.config/nemovideo/) and whether the skill will read local files or install paths to create attribution headers. Before installing: verify the service owner and privacy policy (there is no homepage/source listed), avoid supplying any high‑privilege credentials (use a throwaway/test token if possible), and request explicit confirmation of what data is sent and how long it is retained. The metadata inconsistency (registry vs frontmatter configPaths) should be fixed or explained; if you need stronger assurance, ask the developer to publish source or provide a canonical API/service page.

Getting Started

Share your raw video footage and I'll get started on AI trim stabilization. Or just tell me what you're thinking.

Try saying:

• "edit my raw video footage"
• "export 1080p MP4"
• "trim the unstable sections and smooth"

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.

Trimmer Flutter — Trim and Stabilize Video Cuts

Drop your raw video footage in the chat and tell me what you need. I'll handle the AI trim stabilization on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 3-minute handheld vlog with shaky cuts, ask for trim the unstable sections and smooth out the cut transitions to remove flutter, 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 — trimming closer to a stable frame boundary reduces flutter artifacts significantly.

Matching Input to Actions

User prompts referencing trimmer flutter, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: trimmer-flutter
• 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.

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

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 → "trim the unstable sections and smooth out the cut transitions to remove flutter" → 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 "trim the unstable sections and smooth out the cut transitions to remove flutter" — 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 best quality-to-size ratio after stabilization.