Video Editor With No Ai

Turn a 3-minute unedited screen recording into 1080p edited video clips just by typing what you need. Whether it's trimming and cutting videos without AI aut...

Security Scan

The skill's declared purpose (cloud video editing) matches the main API usage, but there are inconsistencies in declared requirements and runtime instructions that could allow unexpected file reads and token handling — review before installing.

Purpose & Capability

The skill's stated purpose (cloud video editing) aligns with the API endpoints and the single required credential (NEMO_TOKEN). However the SKILL.md frontmatter includes a config path (~/.config/nemovideo/) and instructions to detect install paths for header attribution, while the registry metadata shows no required config paths — this mismatch is incoherent and worth clarifying.

Instruction Scope

Instructions require the agent to: (a) read the SKILL.md frontmatter at runtime to populate headers, (b) detect the agent's install path (~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform, and (c) potentially read or write session/token state. These actions imply filesystem access beyond simple API calls and are not reflected in the top-level requirements. The upload instructions reference multipart file paths (files=@/path) which assumes access to local file system locations for user media. The agent is also instructed to generate/store tokens; where and how to store them is unspecified.

Install Mechanism

No install spec or code is provided (instruction-only), so nothing will be downloaded or written by an installer. This lowers installation risk compared to skills that fetch remote binaries.

Credentials

Only NEMO_TOKEN is required, which is appropriate for a third-party service. But SKILL.md suggests creating an anonymous token if none exists and implies saving it (makes it effectively a credential). The frontmatter's mention of a config path (~/.config/nemovideo/) is not declared in the registry metadata and would grant access to user config files if read; this is disproportionate unless the skill explicitly needs and documents that file access.

Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills or system-wide settings. Saving session_id or ephemeral tokens for a session is normal for this kind of integration, but the storage location is not specified and should be constrained to ephemeral memory or a clearly-scoped config path.

What to consider before installing

This skill appears to be a legitimate cloud video editor, but there are a few red flags you should confirm before installing: - Confirm where NEMO_TOKEN and any anonymous token will be stored and for how long; avoid writing long-lived tokens to global environment variables or files you don't control. - Ask the author to reconcile the mismatch between registry metadata (no config paths) and SKILL.md frontmatter (~/.config/nemovideo/) — explicitly state whether the skill will read any local files or directories and why. - Clarify how file uploads are handled: the instructions reference multipart uploads from local paths (files=@/path). Ensure the agent will only upload user-supplied media blobs you approve, not arbitrary local files. - Because the skill reads its own frontmatter and attempts to detect install paths for an attribution header, verify the implementation will limit filesystem reads to the skill directory and not traverse other user folders. - Prefer using ephemeral anonymous tokens (and in-memory storage) rather than persisting tokens on disk. If you must provide a token, create a scoped/test account with minimal privileges. If the author can confirm these points and update the metadata to match the runtime instructions, the inconsistencies would be resolved. If they cannot, treat the skill as higher-risk and avoid granting it access to sensitive files or long-lived credentials.

Getting Started

Ready when you are. Drop your raw video clips here or describe what you want to make.

Try saying:

• "edit a 3-minute unedited screen recording into a 1080p MP4"
• "trim the beginning, cut dead air, and add transitions between clips"
• "trimming and cutting videos without AI automation for content creators and YouTubers"

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 Editor With No AI — Edit and Export Videos Manually

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

Here's a typical use: you send a a 3-minute unedited screen recording, ask for trim the beginning, cut dead air, and add transitions between clips, 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 2 minutes process and export faster.

Matching Input to Actions

User prompts referencing video editor with no ai, 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 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.

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

• X-Skill-Source: video-editor-with-no-ai
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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 "trim the beginning, cut dead air, and add transitions between clips" — 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 the beginning, cut dead air, and add transitions between clips" → 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.