Tvdr Video

Skip the learning curve of professional editing software. Describe what you want — trim silent parts, add transitions, and export as MP4 — and get edited vid...

Security Scan

The skill's declared need for a single service token (NEMO_TOKEN) and cloud upload behavior match its stated purpose, but there are inconsistencies in the metadata (a referenced config path in the skill frontmatter that is not in the registry metadata) and some implementation choices (automatic anonymous token creation and implicit filesystem/platform detection) that deserve scrutiny before installing.

Purpose & Capability

Name/description describe cloud video editing and the skill requests a single service credential (NEMO_TOKEN) and uploads user media to a remote rendering API—this is proportionate to an edit/export service.

Instruction Scope

SKILL.md sticks to video-editing actions and API calls (session creation, uploads, SSE stream handling). It instructs the agent to read NEMO_TOKEN and to create/store a session_id. It also defines headers and instructs mapping GUI clicks to actions. Nothing in the instructions asks for unrelated system credentials. Note: instructions rely on detecting the install path to set X-Skill-Platform and reference translating GUI instructions to API calls—these imply the agent may inspect filesystem paths or platform context.

Install Mechanism

No install spec or code files are present — instruction-only, so nothing is downloaded or written by an installer. This is the lowest-risk install posture.

Credentials

The skill requires a single credential (NEMO_TOKEN), which is appropriate for a cloud service. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata listed no required config paths — this mismatch is unexplained. The skill will also auto-generate an anonymous token when NEMO_TOKEN is not present, and the instructions advise not to display raw tokens to users. Automatic token creation and implicit reading of install paths/config locations increase the risk surface and should be confirmed.

Persistence & Privilege

Skill is not always-enabled and is user-invocable; it does not request platform-wide persistence or to modify other skills. Storing a session_id for use during a session is expected for this workflow.

What to consider before installing

This skill appears to do what it says (cloud video editing) and only asks for one service token (NEMO_TOKEN). Before installing, consider: (1) confirm you trust the endpoint domain (mega-api-prod.nemovideo.ai) because uploaded videos will be sent there; (2) prefer to supply your own NEMO_TOKEN rather than letting the skill auto-create one if you want tighter control; (3) ask the author to clarify the discrepancy between the registry metadata and the SKILL.md frontmatter about ~/.config/nemovideo/ — does the skill read that path or store tokens there?; (4) understand that the skill may inspect install paths/platform info to set headers; if you’re uncomfortable with that or with automatic token creation/storage, don’t install or request a version that requires explicit token input and documents where tokens/sessions are stored.

Getting Started

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

Try saying:

• "edit a 2-minute raw screen recording or phone video into a 1080p MP4"
• "trim silent parts, add transitions, and export as MP4"
• "editing and trimming raw video recordings into clean shareable clips for content creators and marketers"

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.

TVDR Video — Edit and Export Video Clips

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

Here's a typical use: you send a a 2-minute raw screen recording or phone video, ask for trim silent parts, add transitions, and export as MP4, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 60 seconds process significantly faster.

Matching Input to Actions

User prompts referencing tvdr video, 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 tvdr-video, 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim silent parts, add transitions, and export as MP4" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "trim silent parts, add transitions, and export as MP4" → 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.