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 · 419 · 6 current installs · 6 all-time installs
⭐ 0
安装量(当前) 6
🛡 VirusTotal :可疑 · OpenClaw :可疑
Package:aiwithabidi/openai
安全扫描(ClawHub)
- VirusTotal :可疑
- OpenClaw :可疑
OpenClaw 评估
The skill largely matches an OpenAI CLI in purpose and requested credential (OPENAI_API_KEY), but the implementation contains multiple mismatches and unexplained behaviors (nonstandard endpoints/HTTP methods, a hidden .env lookup, and incomplete file-upload semantics) that make the package incoherent and worth closer inspection before use.
目的
Name/description claim full OpenAI REST coverage (chat, embeddings, images, transcribe, TTS, file upload, fine-tuning, assistants). The script only issues simple GET/POST calls to nonstandard paths (e.g., /chat, /embed, /file/upload) rather than the canonical OpenAI endpoints and methods; many features (e.g., file upload, transcription, image generation) appear declared but not properly implemented (no multipart upload, no request bodies for m…
说明范围
SKILL.md claims all requests go directly to OpenAI and that nothing is stored locally, but the script will attempt to read a .env file at WORKSPACE (or ~/.openclaw/workspace/.env) to extract OPENAI_API_KEY if the env var is not set. The manifest declared no required config paths but the code does access user files. The instructions also encourage commands (file-upload, transcribe, tts) that the CLI does not implement correctly (it never reads …
安装机制
No install spec; the skill is instruction-only with an included Python script (stdlib-only). Nothing is downloaded or written during an install step, which is low risk.
证书
Only OPENAI_API_KEY is declared and used as the primary credential, which is appropriate for an OpenAI integration. However, the script also reads the WORKSPACE env var and a .env file at ~/.openclaw/workspace/.env (if present) to find the key. That file lookup is not declared in the metadata and could read configuration files in the user's home directory; while it only parses the OPENAI_API_KEY line, reading user config files is broader acces…
持久
The skill does not request always:true, does not modify other skills or system-wide configuration, and does not persist data. Autonomous invocation is permitted (platform default) but not combined here with other high privileges.
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「Openai」。简介:OpenAI API integration — chat completions, embeddings, image generation, audio …。
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/aiwithabidi/openai/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: openai
description: "OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI REST API. Generate text, create images with DALL-E, transcribe audio with Whisper, manage fine-tuning jobs, and build AI assistants. Built for AI agents — Python stdlib only, zero dependencies. Use for AI text generation, image creation, speech-to-text, embeddings, fine-tuning, and AI assistant building."
homepage: https://www.agxntsix.ai
license: MIT
compatibility: Python 3.10+ (stdlib only — no dependencies)
metadata: {"openclaw": {"emoji": "🧠", "requires": {"env": ["OPENAI_API_KEY"]}, "primaryEnv": "OPENAI_API_KEY", "homepage": "https://www.agxntsix.ai"}}
---
# 🧠 OpenAI
OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI REST API.
## Features
- **Chat completions** — GPT-4o, GPT-5, o1 model responses
- **Embeddings** — text-embedding-3 for semantic search
- **Image generation** — DALL-E 3 image creation and editing
- **Audio transcription** — Whisper speech-to-text
- **Text-to-speech** — TTS with multiple voices
- **File management** — upload and manage files
- **Fine-tuning** — create and manage fine-tuning jobs
- **Assistants** — build and manage AI assistants
- **Moderation** — content moderation checks
- **Models** — list available models and details
## Requirements
| Variable | Required | Description |
|----------|----------|-------------|
| `OPENAI_API_KEY` | ✅ | API key/token for OpenAI |
## Quick Start
```bash
# Send chat completion
python3 {baseDir}/scripts/openai.py chat "Explain quantum computing in 3 sentences" --model gpt-4o
```
```bash
# Chat with system prompt
python3 {baseDir}/scripts/openai.py chat-system --system "You are a Python expert" "How do I use asyncio?"
```
```bash
# Generate embeddings
python3 {baseDir}/scripts/openai.py embed "The quick brown fox" --model text-embedding-3-small
```
```bash
# Generate an image
python3 {baseDir}/scripts/openai.py image "A sunset over mountains, oil painting style" --size 1024x1024
```
## Commands
### `chat`
Send chat completion.
```bash
python3 {baseDir}/scripts/openai.py chat "Explain quantum computing in 3 sentences" --model gpt-4o
```
### `chat-system`
Chat with system prompt.
```bash
python3 {baseDir}/scripts/openai.py chat-system --system "You are a Python expert" "How do I use asyncio?"
```
### `embed`
Generate embeddings.
```bash
python3 {baseDir}/scripts/openai.py embed "The quick brown fox" --model text-embedding-3-small
```
### `image`
Generate an image.
```bash
python3 {baseDir}/scripts/openai.py image "A sunset over mountains, oil painting style" --size 1024x1024
```
### `transcribe`
Transcribe audio file.
```bash
python3 {baseDir}/scripts/openai.py transcribe recording.mp3
```
### `tts`
Text to speech.
```bash
python3 {baseDir}/scripts/openai.py tts "Hello, welcome to our service" --voice alloy --output greeting.mp3
```
### `models`
List available models.
```bash
python3 {baseDir}/scripts/openai.py models
```
### `model-get`
Get model details.
```bash
python3 {baseDir}/scripts/openai.py model-get gpt-4o
```
### `files`
List uploaded files.
```bash
python3 {baseDir}/scripts/openai.py files
```
### `file-upload`
Upload a file.
```bash
python3 {baseDir}/scripts/openai.py file-upload data.jsonl --purpose fine-tune
```
### `fine-tune`
Create fine-tuning job.
```bash
python3 {baseDir}/scripts/openai.py fine-tune '{"training_file":"file-abc123","model":"gpt-4o-mini"}'
```
### `fine-tune-list`
List fine-tuning jobs.
```bash
python3 {baseDir}/scripts/openai.py fine-tune-list
```
### `moderate`
Check content moderation.
```bash
python3 {baseDir}/scripts/openai.py moderate "Some text to check"
```
### `usage`
Check API usage.
```bash
python3 {baseDir}/scripts/openai.py usage --date 2026-02-01
```
### `assistants`
List assistants.
```bash
python3 {baseDir}/scripts/openai.py assistants
```
## Output Format
All commands output JSON by default. Add `--human` for readable formatted output.
```bash
# JSON (default, for programmatic use)
python3 {baseDir}/scripts/openai.py chat --limit 5
# Human-readable
python3 {baseDir}/scripts/openai.py chat --limit 5 --human
```
## Script Reference
| Script | Description |
|--------|-------------|
| `{baseDir}/scripts/openai.py` | Main CLI — all OpenAI operations |
## Data Policy
This skill **never stores data locally**. All requests go directly to the OpenAI API and results are returned to stdout. Your data stays on OpenAI servers.
## Credits
---
Built by [M. Abidi](https://www.linkedin.com/in/mohammad-ali-abidi) | [agxntsix.ai](https://www.agxntsix.ai)
[YouTube](https://youtube.com/@aiwithabidi) | [GitHub](https://github.com/aiwithabidi)
Part of the **AgxntSix Skill Suite** for OpenClaw agents.
📅 **Need help setting up OpenClaw for your business?** [Book a free consultation](https://cal.com/agxntsix/abidi-openclaw)