Pannelai Chat
Chat and code generation through pannelAI, in the OpenAI chat completions, Anthropic messages, or OpenAI Responses wire format, streamed or not. Covers the model field, streaming, combo routing, and the vision adapter. Use when a client needs an LLM answer from the gateway.
Install
npx skills add rusmanadodi2598/pannelAI --skill pannelai-chatgit clone --depth 1 https://github.com/rusmanadodi2598/pannelAI.git /tmp/pannelAI
mkdir -p ~/.claude/skills
cp -r /tmp/pannelAI/skills/pannelai-chat ~/.claude/skills/pannelai-chatPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# pannelAI: Chat
Three routes, one capability. Pick the route that matches the wire format the client already speaks;
the gateway translates to whatever the resolved provider expects.
| Route | Wire format |
|---|---|
| `POST /api/v1/chat/completions` | OpenAI chat completions |
| `POST /api/v1/messages` | Anthropic messages |
| `POST /api/v1/responses` | OpenAI Responses |
All three take `Authorization: Bearer $PANNELAI_KEY` and a `model` field resolved as described in the
entry skill (combo name, alias, or `provider/model`).
## OpenAI format
```bash
curl -s $PANNELAI_URL/api/v1/chat/completions \
-H "Authorization: Bearer $PANNELAI_KEY" \
-H "content-type: application/json" \
-d '{
"model": "openai/gpt-4o-mini",
"messages": [{"role": "user", "content": "Reply with one word: ready"}]
}'
```
The answer is the OpenAI chat completion shape: `choices[0].message.content`, with a `usage` block
carrying `prompt_tokens`, `completion_tokens`, and `total_tokens` when the provider reported accounting.
Add `"stream": true` for server-sent events. The gateway passes the upstream's SSE frames through in the
client's own format, so a client parses `data:` lines exactly as it would against the provider directly.
The stream ends with `data: [DONE]`, which is the marker a client waits for to release the connection. A
streamed answer carries its token accounting in a final frame before that marker when the providerDetails
- Skill name
pannelai-chat- Repository
- rusmanadodi2598/pannelAI
- Path
skills/pannelai-chat/SKILL.md- License
- MIT
- Repo updated
- 24 October 2026
FAQ
What does the Pannelai Chat skill do?
Chat and code generation through pannelAI, in the OpenAI chat completions, Anthropic messages, or OpenAI Responses wire format, streamed or not. Covers the model field, streaming, combo routing, and the vision adapter. Use when a client needs an LLM answer from the gateway.
How do I install the Pannelai Chat skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add rusmanadodi2598/pannelAI --skill pannelai-chat. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Pannelai Chat popular?
It lives in rusmanadodi2598/pannelAI, which has 49 GitHub stars and 6 forks.
Related skills
Pannelai
49rusmanadodi2598/pannelAI
Entry point for pannelAI, a self-hosted AI gateway that speaks OpenAI, Anthropic, and OpenAI Responses wire formats for chat, image generation, text-to-speech, speech-to-text, embeddings, and web search. Use when the user mentions pannelAI, a gateway base URL, or wants one key in front of several providers. Covers setup, gateway-key auth, model discovery, and links to one skill per capability.
Pannelai Embeddings
49rusmanadodi2598/pannelAI
Embeddings through pannelAI. Covers POST /api/v1/embeddings, the provider/model string, the input field, and the OpenAI embeddings answer with its usage block. Use when a client needs vectors for RAG or semantic search from the gateway.
Pannelai Image
49rusmanadodi2598/pannelAI
Text-to-image and async video generation through pannelAI. Covers POST /api/v1/images/generations, the provider/model string, the prompt and size fields, the normalized OpenAI images answer, and the two video job routes. Use when a client needs a generated image or video from the gateway.
Latticework Mental Models
49kangarooking/poor-charlies-almanack-skill
当用户分析复杂问题时只用了单一视角(如纯财务/纯技术/纯市场),或面对跨领域问题缺乏分析框架时激活。典型触发信号:用户说"我只懂XX方面""这个问题好像是XX问题"但明显只用了一个学科的解释。不适用于用户已经有成熟的多维度分析框架且正在有效使用的场景,也不适用于纯执行层面的简单任务。
Chat History
45tyrchen/claude-skills
Extract and organize Claude Code session history into project .chats directory. Use when users want to document their Claude sessions, export conversation inputs, or maintain a log of instructions given to Claude.
Hardware Agent
43NVIDIA/AI-Factory-Operations-Agent
Triage hardware faults on NVIDIA GPU compute nodes through the Hardware Agent. Starting a triage is read-only log collection and hardware_analyze_dut is available in View mode; never require Edit or Auto. Before asking to start any fresh NVDebug collection, you MUST say: 'A fresh NVDebug collection can take 5-30 minutes. Do you want me to start it?' Stop and wait for the next user response. An ordinary affirmative such as yes, let's go, do it, or proceed is sufficient; start immediately without demanding formal confirmation or asking twice. Use recent Hardware Agent triages for quick answers w
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.