← 返回 Skills 市场

DaVinci Auto Editor

Name: DaVinci Auto Editor
Author: afengzi

作者 afengzi · GitHub ↗ · v0.2.1 · MIT-0

darwinlinuxwin32 ⚠ suspicious

250

总下载

当前安装

版本数

在 OpenClaw 中安装

/install davinci-auto-editor

功能描述

Generate DaVinci Resolve import packages from local media plus a cloud editing API. Use when Codex needs to scan a material folder, request a cloud editing p...

使用说明 (SKILL.md)

DaVinci Auto Editor

使用这个 skill 时，按下面顺序执行：

读取 examples/config.example.json 同结构的配置文件。
校验 api_base_url、api_key、material_path、timeline_fps 等关键参数。
递归扫描素材目录，并向云端上报素材索引。
调用云端 API 创建任务并获取剪辑计划。
在本地只生成最小执行计划，不要把完整云端内部逻辑写入本地文件。
由 Node 生成 Resolve 可导入的 timeline.edl 和导入说明文件。
将准备结果回传云端。

输入参数

至少提供这些字段：

api_base_url
api_key
project_type
aspect_ratio
material_path
template_id
subtitle_mode
music_policy
pace_policy
output_mode
render_preset
timeline_fps
timeline_resolution

可选字段：

task_timeout_ms
poll_interval_ms
request_timeout_ms
task_name
webhook_url
extra_metadata

输出结果

默认在素材目录旁创建 _davinci_auto_editor/\x3CtaskId>/，包含：

resolve-import.json：最小本地导入计划
timeline.edl：Resolve 导入文件
IMPORT-TO-RESOLVE.txt：导入说明
execution-report.json：本地执行报告

依赖要求

Node.js 18 或更高版本
已安装 DaVinci Resolve
可访问云端 API 的网络环境

错误处理原则

缺少配置、素材目录不存在、API 调用失败时立即停止并返回非 0 退出码。
始终写出 execution-report.json 以便排查。
不在本地输出完整云端推理结果，只输出导入所需的最小执行数据。
明确提示第一版只覆盖基础拼接和时间线导入准备。

安全使用建议

Before installing or running this skill: 1) Verify and trust the api_base_url you will use — do not point the skill to unknown or untrusted endpoints (the example uses a raw IP which is unusual). 2) Understand what is uploaded: the tool sends a materials index containing absolute file paths, filenames, sizes, timestamps and hashed path IDs to the configured cloud API — do not run it against sensitive directories. 3) Store your api_key securely (avoid committing the config file to source control and consider using a secrets manager or environment variable instead). 4) If you want to evaluate behavior safely, run it first on a non-sensitive sample folder and inspect all HTTP requests (e.g., with a local proxy) and the remote service’s privacy/retention policy. 5) If you cannot vet or trust the remote API endpoint, do not provide real credentials or sensitive media; consider adapting the script to target a local test service or to skip uploading paths you do not want shared.

功能分析

Type: OpenClaw Skill Name: davinci-auto-editor Version: 0.2.1 The skill is designed to automate DaVinci Resolve timeline creation by scanning local media and communicating with a cloud-based editing API. The script `scripts/index.js` recursively indexes media files (names, absolute paths, and hashes) and sends this metadata to a user-configured endpoint (example IP `43.137.46.105`). While sending local file paths to a remote server is a privacy risk, it is the explicitly stated and documented purpose of this 'cloud-assisted' tool. The code uses standard Node.js APIs, lacks obfuscation, and does not attempt to access sensitive system files, environment variables, or establish persistence.

能力评估

✓ Purpose & Capability

Name, description, manifest, SKILL.md, README, and scripts/index.js are consistent: the skill scans a material folder, builds a materials index, calls a cloud API for a plan, and writes Resolve-importable files locally. Requiring only Node is proportionate to the described functionality.

⚠ Instruction Scope

Runtime instructions and the implementation explicitly instruct scanning the entire material directory and POSTing a materials index to the cloud. The materials payload includes absolutePath, relativePath, name, size, modifiedAt and a SHA1-based id (path hashed). Sending absolute paths and file metadata to a remote API is outside pure local editing work and is a privacy/exfiltration risk unless you trust the target API.

✓ Install Mechanism

No install spec is provided (instruction-only plus included Node script). That minimizes installer risk. The project ships a local Node script (scripts/index.js) which will run on the user's machine — review that script (included) before running, but there is no remote installer download of code at runtime.

⚠ Credentials

The registry metadata lists no required env vars, but the config schema and examples require api_base_url and api_key (supplied in a config file). Requiring an API key is expected for a cloud-driven skill, but the example config uses a raw IP address (http://43.137.46.105:8787) which is unusual and potentially suspicious. Also, secrets are expected to be placed in a JSON config file (not an env var), which could leave credentials on disk if not managed carefully.

✓ Persistence & Privilege

The skill does not request always:true, does not modify other skills, and only writes outputs under a project-adjacent _davinci_auto_editor/<taskId> directory. It does create files (resolve-import.json, timeline.edl, execution-report.json) in the filesystem as part of normal operation, which is expected for its purpose.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install davinci-auto-editor
安装完成后，直接呼叫该 Skill 的名称或使用 /davinci-auto-editor 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.2.1

Update default cloud API address to 43.137.46.105 and refresh publish metadata.

v0.2.0

Initial public release with pure Node local execution.

元数据

Slug davinci-auto-editor

版本 0.2.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题