技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 117 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：andyluvis/openfun
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's declared purpose (AI video creation) matches its instructions and install steps; the only minor inconsistency is an undeclared local config file for the CLI token.
目的
Name/description describe an AI video CLI. The skill only requires a single binary 'openfun' and the install spec installs an npm package 'openfun-cli' which provides that binary — this is proportionate and expected for a CLI-driven video generation tool.
说明范围
SKILL.md only tells the agent to run the openfun CLI commands (trends, remix, render, download, account). Those commands are within the declared purpose. However the docs state that login opens a browser and that a token is persisted to ~/.openfun/config.json — the runtime instructions therefore imply reading/writing a local config file that is not declared in the registry metadata.
安装机制
Install uses 'npm install -g openfun-cli' (node package). This is a common, expected mechanism for providing a CLI. It is a moderate-risk install source (public npm) but matches the skill's need to provide a binary named 'openfun'.
证书
No environment variables or credentials are declared, which is fine. But SKILL.md documents that authentication tokens are persisted to ~/.openfun/config.json; the skill metadata did not declare required config paths. The presence of a persistent token file (and a login flow that opens a browser) should be noted because it grants ongoing access to the remote service from the machine.
持久
always:false (normal). The skill will install a global npm binary and the CLI stores an auth token in the user's home directory — both are typical for CLIs. Global npm installs modify the system PATH and may require elevated permissions depending on environment; the token file gives the CLI persistent access to the user's OpenFun account.
综合结论
This skill appears to do what it says: it wraps an 'openfun' CLI delivered via the public npm package 'openfun-cli'. Before installing, verify the npm package and linked GitHub repo (https://github.com/andyluvis/openfun-cli) to ensure it is legitimate, review its code and install behavior, and check the auth flow and token storage. Note that 'npm install -g' writes a global binary and the CLI stores an auth token at ~/.openfun/config.json — if…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「OpenFun」。简介：Create viral short-form videos using AI. Analyze trending patterns, generate or…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/andyluvis/openfun/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: openfun
description: Create viral short-form videos using AI. Analyze trending patterns, generate original content that hits the same beats, render and download MP4s. Use when the user wants to create TikTok, YouTube Shorts, or Instagram Reels content, find trending video patterns, or automate video content creation.
metadata:
{
"openclaw":
{
"requires": { "bins": ["openfun"] },
"install":
[
{
"id": "node",
"kind": "node",
"package": "openfun-cli",
"bins": ["openfun"],
"label": "Install OpenFun CLI (npm)",
},
],
},
}
---
# OpenFun — AI Video Factory
Create original viral short-form videos by reverse-engineering what works.
**OpenFun is NOT a video clipper.** It analyzes viral patterns (hook timing, pacing, emotional arc) and generates original content that hits the same beats.
## Setup
```bash
npm install -g openfun-cli
openfun login
```
Login opens a browser for auth. Token persists in `~/.openfun/config.json`.
## Commands
### Find trending patterns
```bash
openfun trends --niche <niche> --count <n>
```
Returns trending content patterns in a niche. Use this to decide what to create.
### Remix a trend
```bash
openfun remix <trend-id>
--brand "Brand Name"
--tone casual
--hook "Your custom hook"
--cta "Your call to action"
```
Creates an original script based on a trending pattern, customized for the user's brand.
Options:
- `--brand` — Brand or creator name
- `--tone` — casual, professional, humorous, motivational, educational
- `--hook` — Custom hook text (optional, auto-generated if omitted)
- `--cta` — Call to action (optional)
- `--niche` — Override niche from trend
### Render a video
```bash
openfun render <remix-id>
```
Kicks off video rendering. Returns a job ID. Rendering takes 30-90 seconds.
### Check video status
```bash
openfun videos
```
Lists all videos with their status (rendering, ready, failed).
### Download a video
```bash
openfun download <video-id> -o output.mp4
```
Downloads a rendered video as MP4.
### Account info
```bash
openfun account
```
Shows plan, usage, and remaining credits.
## Typical Workflow
```bash
# 1. Find what's trending in your niche
openfun trends --niche fitness --count 5
# 2. Pick a trend and remix it
openfun remix abc123 --brand "FitLife" --tone motivational
# 3. Render the video
openfun render def456
# 4. Check status
openfun videos
# 5. Download when ready
openfun download ghi789 -o fitness-video.mp4
```
## Agent Tips
- All commands output JSON by default (add `--pretty` for human-readable)
- Exit codes: 0 = success, 1 = user error, 2 = API error
- Errors go to stderr, data to stdout
- No interactive prompts — fully automatable
- Run `openfun trends` across multiple niches to find the best opportunities
- Batch multiple remixes, then render them all
## Plans
- **Free:** 5 remixes/month + 3 watermarked videos/month
- **Pro ($19/mo):** 50 remixes + 20 videos + no watermark
- **Scale ($49/mo):** Unlimited remixes + 100 videos + priority rendering
## Links
- Website: https://www.openfun.ai
- CLI repo: https://github.com/andyluvis/openfun-cli