功能描述

Get captioned video files ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, MKV, up to 500MB), say something like "gen...

使用说明 (SKILL.md)

Getting Started

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

Try saying:

"generate my video clips"
"export 1080p MP4"
"generate and burn in captions for"

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.

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.
Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer \x3Ctoken>, Content-Type: application/json, and body {"task_name":"project","language":"\x3Cdetected>"}. 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.

Caption Generator for DaVinci Resolve — Auto-Generate Captions for Videos

Name: Caption Generator Davinci Resolve
Author: linmillsd7

Send me your video clips and describe the result you want. The AI caption generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute DaVinci Resolve exported interview clip, type "generate and burn in captions for my DaVinci Resolve video in English", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: export a clean MP4 from DaVinci Resolve first for fastest caption processing.

Matching Input to Actions

User prompts referencing caption generator davinci resolve, 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":"\x3Clang>"}`. 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/\x3Csid>`	POST	Upload a file (multipart) or URL.
`/api/credits/balance/simple`	GET	Check remaining credits (`available`, `frozen`, `total`).
`/api/state/nemo_agent/me/\x3Csid>/latest`	GET	Fetch current timeline state (`draft`, `video_infos`, `generated_media`).
`/api/render/proxy/lambda`	POST	Start export. Body: `{"id":"render_\x3Cts>","sessionId":"\x3Csid>","draft":\x3Cjson>,"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 caption-generator-davinci-resolve, 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).

Include Authorization: Bearer \x3CNEMO_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=\x3Cid>` (get `\x3Cid>` 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.

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 "generate and burn in captions for my DaVinci Resolve video in English" — concrete instructions get better results.

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

Export from DaVinci Resolve as H.264 MP4 before uploading for best compatibility.

Common Workflows

Quick edit: Upload → "generate and burn in captions for my DaVinci Resolve video in English" → 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.

安全使用建议

This skill connects to a third‑party cloud service (mega-api-prod.nemovideo.ai) to upload your video and perform captioning. Before installing: (1) Confirm you trust nemovideo.ai — uploaded media and generated tokens will leave your machine. (2) Be aware the skill will auto-create an anonymous NEMO_TOKEN if you don't provide one; tokens are short‑lived (7 days) and may be stored in a local config folder (~/.config/nemovideo/ per metadata). If you prefer control, supply your own NEMO_TOKEN rather than relying on auto-generation. (3) The skill inspects the agent install path to set an X-Skill-Platform header — this reveals some environment/path information to the service. (4) Do not upload sensitive or regulated content unless you have verified the provider's privacy/retention policy. If you want further assurance, ask the skill author for source/homepage, a privacy policy, or explicit details on where tokens and session metadata are stored.

功能分析

Type: OpenClaw Skill Name: caption-generator-davinci-resolve Version: 1.0.0 The skill is a functional integration for a video captioning service (nemovideo.ai). It provides detailed instructions for an AI agent to handle authentication, file uploads, and rendering workflows via a remote API. While it includes logic for environment detection (checking install paths like ~/.clawhub/) and automatic token generation, these behaviors are consistent with the stated purpose of providing a seamless cloud-based video processing experience. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found in SKILL.md or _meta.json.

能力评估

✓ Purpose & Capability

The skill claims to generate/burn captions via a remote rendering backend and its only declared secret is NEMO_TOKEN for that backend. No unrelated binaries or credentials are requested, so the declared requirements match the stated purpose.

ℹ Instruction Scope

Instructions stay within the captioning workflow (obtain token if missing, create session, upload media, stream SSE, start render). Two items to note: (1) the skill auto-generates an anonymous token by POSTing to the nemovideo API if NEMO_TOKEN is absent (this happens automatically per the instructions), and (2) it derives an attribution header from the agent's install path (e.g., checking ~/.clawhub/ or ~/.cursor/skills/), which implies reading install-path information. Both are explainable for this skill but worth user awareness.

✓ Install Mechanism

There is no install spec and no code files — the skill is instruction-only and makes HTTP calls at runtime. This is the lowest-risk installation posture.

ℹ Credentials

Only NEMO_TOKEN is required and that is appropriate for a hosted caption/render service. The SKILL.md instructs generation/storage of anonymous tokens (valid 7 days) when NEMO_TOKEN is absent and references a config path in its YAML metadata (~/.config/nemovideo/), but the top-level registry summary listed 'required config paths: none' — a minor inconsistency. Users should expect the skill to store session/token metadata locally or in that config path unless they supply their own NEMO_TOKEN.

✓ Persistence & Privilege

The skill does not request 'always: true' or elevated platform privileges. It can be invoked autonomously by design (default for skills), but its actions (auth, upload, render) are consistent with its purpose and do not modify other skills or system-wide settings.

版本历史

v1.0.0

Initial release with full-featured cloud captioning workflow for DaVinci Resolve users: - Upload video files (MP4, MOV, AVI, MKV, up to 500MB) for fast, server-side caption generation and burn-in. - Easy setup: automatic anonymous authentication and session creation with free trial credits. - Simple prompt-based interface—just tell it to generate captions and export video. - Clear guidance and error handling for uploads, exporting, credits, file formats, and common issues. - Supports interactive workflows: uploads, caption generate/burn-in, 1080p MP4 export, and timeline previews. - All rendering and edits are processed remotely; no DaVinci Resolve plugin or local install required.

元数据

Slug caption-generator-davinci-resolve

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Caption Generator Davinci Resolve 是什么？

Get captioned video files ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, MKV, up to 500MB), say something like "gen... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 91 次。

如何安装 Caption Generator Davinci Resolve？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install caption-generator-davinci-resolve」即可一键安装，无需额外配置。

Caption Generator Davinci Resolve 是免费的吗？

是的，Caption Generator Davinci Resolve 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Caption Generator Davinci Resolve 支持哪些平台？

Caption Generator Davinci Resolve 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Caption Generator Davinci Resolve？

由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。

Caption Generator Davinci Resolve