Maker Text Generator

Skip the learning curve of professional editing software. Describe what you want — generate on-screen text labels and title cards for my video — and get text...

Security Scan

The skill largely matches its stated purpose (upload a video, request text overlays, and call a cloud render API), but there are mismatches and a few instructions that broaden its scope in ways you should review before installing.

Purpose & Capability

The skill's declared primary credential (NEMO_TOKEN) and the described API endpoints are consistent with a cloud video-rendering/text-overlay service. However, the SKILL.md frontmatter claims a config path (~/.config/nemovideo/) for storing data while the registry metadata reported no required config paths — an inconsistency that should be resolved. Requesting a local config path is plausible for caching tokens but is not strictly necessary for a pure instruction-only skill.

Instruction Scope

Runtime instructions tell the agent to: use NEMO_TOKEN (or create an anonymous token by POSTing to an external URL), create sessions, upload local files (multipart with files=@/path), poll render status, and detect install paths to set attribution headers. These are expected for the feature, but two items raise concern: (1) the agent is instructed to 'keep the technical details out of the chat' (which encourages hiding network/system activity from users), and (2) detecting install paths and reading/writing a config directory implies filesystem access beyond just processing user-uploaded files. Confirm whether the agent will only access files the user explicitly uploads and whether it will write tokens/configs to disk.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest install risk. No external binaries or downloads are introduced by the skill itself.

Credentials

The skill requests only one environment variable, NEMO_TOKEN, which is proportional to a cloud API client. But SKILL.md also describes generating/storing an anonymous token and references a config path (~/.config/nemovideo/). That implies potential local storage of auth tokens — acceptable for a client but worth disclosing. There are no other unrelated secrets requested.

Persistence & Privilege

always:false (normal). The instructions imply creating and using session tokens and potentially storing credentials in ~/.config/nemovideo/. The skill does not request permanent platform-wide privileges, but writing tokens/configs into the user's home directory would be a persistent side effect — verify where tokens are stored and whether the skill will modify other skill/system configs (it should not).

What to consider before installing

This skill appears to do what it says (upload a video and call a cloud API to produce text-overlaid videos) but you should confirm a few things before installing: 1) The skill will send your video files to https://mega-api-prod.nemovideo.ai — only proceed if you are comfortable uploading the content. 2) It will use NEMO_TOKEN if present, or request an anonymous token and may store tokens under ~/.config/nemovideo/ — check that you consent to storing auth tokens locally. 3) The SKILL.md tells the agent to 'keep technical details out of the chat' — ask for full logs or a visible activity summary if you want transparency about network and file operations. 4) The skill's registry metadata and SKILL.md disagree about config path requirements; ask the publisher (or avoid installing) until that is clarified. If you proceed, prefer using a scoped/limited token for NEMO_TOKEN, and test in a sandboxed environment first. If you want, I can suggest exact questions to ask the publisher or a checklist to validate before trusting the skill.

Getting Started

Share your video clips and I'll get started on AI text generation. Or just tell me what you're thinking.

Try saying:

• "generate my video clips"
• "export 1080p MP4"
• "generate on-screen text labels and title"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Maker Text Generator — Generate Text Overlays for Videos

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

Here's a typical use: you send a a 60-second product demo video, ask for generate on-screen text labels and title cards for my video, and about 20-40 seconds 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 produce the most accurate auto-generated text placements.

Matching Input to Actions

User prompts referencing maker text generator, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

• X-Skill-Source: maker-text-generator
• 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 "generate on-screen text labels and title cards for my video" — 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 → "generate on-screen text labels and title cards for my video" → Download MP4. Takes 20-40 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.