nano-banana-pro-prompts-recommend-skill
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
Deep research using the Caesar API — run queries, follow up with chat, brainstorm, and manage collections.
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install alexrudloff/caesar-research打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
CLI for Caesar deep research. Runs multi-source research jobs with citations, follow-up chat, and brainstorming.
go install github.com/alexrudloff/caesar-cli@latest
export CAESAR_API_KEY=your_key_here
Run a query (waits for completion by default, prints events as they happen):
caesar research create "What are the latest advances in mRNA vaccines?"
Returns JSON with content (synthesized answer with [n] citations) and a results array of sources.
Fire-and-forget:
caesar research create "query" --no-wait
# Returns: { "id": "uuid", "status": "queued" }
Then check on it:
caesar research get <job-id>
caesar research watch <job-id>
caesar research events <job-id>
| Flag | Description |
|---|---|
--no-wait |
Return immediately with job ID |
--model <name> |
gpt-5.2, gemini-3-pro, gemini-3-flash, claude-opus-4.5 |
--loops N |
Max reasoning loops (default 1, higher = deeper research) |
--reasoning |
Enable advanced reasoning mode |
--auto |
Let Caesar auto-configure based on query |
--exclude-social |
Skip social media sources |
--exclude-domain x.com |
Exclude specific domains (repeatable) |
--system-prompt "..." |
Custom synthesis prompt |
--brainstorm <id> |
Use a brainstorm session for context |
queued → searching → summarizing → analyzing → researching → completed or failed
Ask follow-up questions about a completed research job:
caesar chat send <job-id> "How does this compare to traditional vaccines?"
Waits for the response by default. The answer includes inline [n] citations referencing the original research sources.
caesar chat send <job-id> "question" --wait=false
caesar chat history <job-id>
Get clarifying questions before research to improve resul...
这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
A command-line interface for the Caesar research API.
Requires Go 1.21 or later.
go install github.com/alexrudloff/caesar-cli@latest
Or build from source:
git clone https://github.com/alexrudloff/caesar-cli.git
cd caesar-cli
go build -o caesar .
This produces a caesar binary in the current directory. Move it somewhere on your $PATH to use it globally:
mv caesar /usr/local/bin/
Get an API key from caesar.org and set it as an environment variable:
export CAESAR_API_KEY=your_key_here
To persist it across shell sessions, add the export line to your shell profile (~/.zshrc, ~/.bashrc, etc.), or create a local .env file:
echo 'export CAESAR_API_KEY=your_key_here' > .env
source .env
The .env file is git-ignored and will not be committed.
# Run a research query (waits for completion by default)
caesar research create "What is quantum computing?"
# Return immediately with job ID
caesar research create "query" --no-wait
# Check on a job
caesar research get <job-id>
# Watch a job until it completes, printing events
caesar research watch <job-id>
# View reasoning events for a job
caesar research events <job-id>
Research options:
| Flag | Description |
|---|---|
--no-wait |
Return immediately with job ID |
--model |
Model to use (gpt-5.2, gemini-3-pro, gemini-3-flash, claude-opus-4.5) |
--loops N |
Max reasoning loops (default 1) |
--reasoning |
Enable reasoning mode |
--auto |
Auto-configure based on query |
--exclude-social |
Exclude social media sources |
--exclude-domain |
Domains to exclude (repeatable) |
--system-prompt |
Custom system prompt |
--brainstorm |
Brainstorm session ID to use |
Ask follow-up questions about a completed research job:
# Send a fo...
# Caesar Research
CLI for [Caesar](https://www.caesar.org/) deep research. Runs multi-source research jobs with citations, follow-up chat, and brainstorming.
## Setup
```bash
go install github.com/alexrudloff/caesar-cli@latest
export CAESAR_API_KEY=your_key_here
```
## Research
Run a query (waits for completion by default, prints events as they happen):
```bash
caesar research create "What are the latest advances in mRNA vaccines?"
```
Returns JSON with `content` (synthesized answer with `[n]` citations) and a `results` array of sources.
Fire-and-forget:
```bash
caesar research create "query" --no-wait
# Returns: { "id": "uuid", "status": "queued" }
```
Then check on it:
```bash
caesar research get <job-id>
caesar research watch <job-id>
caesar research events <job-id>
```
### Research Options
| Flag | Description |
|------|-------------|
| `--no-wait` | Return immediately with job ID |
| `--model <name>` | `gpt-5.2`, `gemini-3-pro`, `gemini-3-flash`, `claude-opus-4.5` |
| `--loops N` | Max reasoning loops (default 1, higher = deeper research) |
| `--reasoning` | Enable advanced reasoning mode |
| `--auto` | Let Caesar auto-configure based on query |
| `--exclude-social` | Skip social media sources |
| `--exclude-domain x.com` | Exclude specific domains (repeatable) |
| `--system-prompt "..."` | Custom synthesis prompt |
| `--brainstorm <id>` | Use a brainstorm session for context |
### Status Lifecycle
`queued` → `searching` → `summarizing` → `analyzing` → `researching` → `completed` or `failed`
## Chat (Follow-Up Questions)
Ask follow-up questions about a completed research job:
```bash
caesar chat send <job-id> "How does this compare to traditional vaccines?"
```
Waits for the response by default. The answer includes inline `[n]` citations referencing the original research sources.
```bash
caesar chat send <job-id> "question" --wait=false
caesar chat history <job-id>
```
## Brainstorm
Get clarifying questions before research to improve resul...# caesar-cli A command-line interface for the [Caesar](https://www.caesar.org/) research API. ## Install Requires [Go](https://go.dev/dl/) 1.21 or later. ```bash go install github.com/alexrudloff/caesar-cli@latest ``` Or build from source: ```bash git clone https://github.com/alexrudloff/caesar-cli.git cd caesar-cli go build -o caesar . ``` This produces a `caesar` binary in the current directory. Move it somewhere on your `$PATH` to use it globally: ```bash mv caesar /usr/local/bin/ ``` ## Configuration Get an API key from [caesar.org](https://www.caesar.org/) and set it as an environment variable: ```bash export CAESAR_API_KEY=your_key_here ``` To persist it across shell sessions, add the export line to your shell profile (`~/.zshrc`, `~/.bashrc`, etc.), or create a local `.env` file: ```bash echo 'export CAESAR_API_KEY=your_key_here' > .env source .env ``` The `.env` file is git-ignored and will not be committed. ## Usage ### Research ```bash # Run a research query (waits for completion by default) caesar research create "What is quantum computing?" # Return immediately with job ID caesar research create "query" --no-wait # Check on a job caesar research get <job-id> # Watch a job until it completes, printing events caesar research watch <job-id> # View reasoning events for a job caesar research events <job-id> ``` Research options: | Flag | Description | |------|-------------| | `--no-wait` | Return immediately with job ID | | `--model` | Model to use (`gpt-5.2`, `gemini-3-pro`, `gemini-3-flash`, `claude-opus-4.5`) | | `--loops N` | Max reasoning loops (default 1) | | `--reasoning` | Enable reasoning mode | | `--auto` | Auto-configure based on query | | `--exclude-social` | Exclude social media sources | | `--exclude-domain` | Domains to exclude (repeatable) | | `--system-prompt` | Custom system prompt | | `--brainstorm` | Brainstorm session ID to use | ### Chat Ask follow-up questions about a completed research job: ```bash # Send a fo...
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...
AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.
A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.