Hydra Ai

Turn a 2-minute raw interview recording into 1080p multi-version edited clips just by typing what you need. Whether it's generating multiple edited video ver...

Security Scan

The skill's declared requirements and runtime instructions are generally consistent with a cloud video-editing service, but there are small metadata inconsistencies and privacy/operational things to verify before use.

Purpose & Capability

Name, description, and runtime actions (uploading video, creating sessions, starting renders) align with a cloud video-editing backend. The single required credential (NEMO_TOKEN) is appropriate for an API-backed service. Note: the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this mismatch should be clarified.

Instruction Scope

Instructions stay within the stated purpose: they describe auth, session creation, SSE for edits, uploads, and render polling against mega-api-prod.nemovideo.ai. The skill asks the agent to derive attribution headers from the skill frontmatter and to detect install path for X-Skill-Platform (reading agent install path), which is reasonable but does expand file-system probing beyond purely API calls. It also includes logic to obtain an anonymous token if NEMO_TOKEN is not present (posts to the service to receive a token).

Install Mechanism

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

Credentials

Only NEMO_TOKEN is required (declared as primary credential), which matches the service usage. However, SKILL.md frontmatter also references a config path (~/.config/nemovideo/), which could imply reading local configuration files; the registry metadata did not list required config paths. Confirm whether the skill will read that config path and what data it expects (it may contain tokens or user config).

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent or system-wide privileges and does not instruct modifications to other skills or global agent config. Autonomous invocation remains allowed (platform default).

Assessment

This skill appears to be a normal client for the 'nemovideo' cloud rendering service. Before installing: (1) Confirm the service domain (mega-api-prod.nemovideo.ai) and review its privacy/retention policy because you will upload potentially sensitive video content. (2) Prefer supplying your own NEMO_TOKEN from a trusted account rather than relying on the skill's anonymous-token flow if you need auditing or control. (3) Ask the maintainer to clarify the config-path discrepancy (SKILL.md frontmatter vs registry) and what, if anything, the skill will read from ~/.config/nemovideo. (4) Understand that uploads and renders happen on the remote service and that attribution headers require reading the skill frontmatter and possibly the agent install path — if you are uncomfortable with any local path probing, request that the skill avoid that behavior. If those items are acceptable or clarified, the skill is coherent with its purpose.

Getting Started

Send me your video clips and I'll handle the AI multi-stream editing. Or just describe what you're after.

Try saying:

• "create a 2-minute raw interview recording into a 1080p MP4"
• "split this video into multiple edited versions for different platforms"
• "generating multiple edited video versions from a single source clip for content creators"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Hydra AI — Generate Multiple Videos From One

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

Say you have a 2-minute raw interview recording and want to split this video into multiple edited versions for different platforms — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter source clips produce faster and more accurate multi-version outputs.

Matching Input to Actions

User prompts referencing hydra 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.

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: hydra-ai
• 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.

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

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.

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

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 "split this video into multiple edited versions for different platforms" — 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 across platforms.

Common Workflows

Quick edit: Upload → "split this video into multiple edited versions for different platforms" → 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.