Image Understanding
DocumentsImage Understanding is an Agent Skill for documents published in the B-M-Capital-Research/honeclaw repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Analyze images sent by the user, such as portfolio screenshots or candlestick charts, and combine the result with tools for a fuller assessment
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/B-M-Capital-Research/honeclaw/blob/HEAD/skills/image_understanding/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/image-understanding, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Image Understanding Skill
When the user sends an image that appears in the message as an attachment, you can perform visual analysis. The underlying model (for example Gemini 2.0 Flash) supports multimodal input and can describe the image directly.
Supported Scenarios
1. Identify Portfolio Screenshots
- Extract the ticker, company name, share count, cost basis, and similar details from the image
- After identification, guide the user to call
portfolio(action="add")to record the data
2. Analyze Market Charts
- Recognize candlestick trends and technical indicators such as moving averages, MACD, and RSI
- Combine the chart with real-time news from
web_searchfor a broader judgment
Tool Guide
| Tool call | Purpose |
|---|---|
portfolio(action="add", ...) | Record the extracted holdings |
web_search(query="...") | Search for news around the chart's time frame |
data_fetch(data_type="quote", symbol="...") | Get live market data for comparison |
Notes
- If the message contains multiple image attachments, analyze them one by one
- For unclear numbers, always ask the user to confirm instead of guessing
- After identifying a portfolio screenshot, summarize the extracted result and let the user confirm before writing it into
portfolio