agentleFS
B-M-Capital-ResearchB-M-Capital-Research/honeclaw/skills/image_generation/SKILL.md

Image Generation

Skill748 starsChanged 3 months agoMITView on GitHub

Generate dynamic portfolio screenshots, stock-analysis infographics, or general-style images. Real data must be fetched first

Files
SKILL.md

Image Generation Skill

Three image types are supported. The portfolio_snapshot and stock_analysis types must use real data before generation.

Image Types

1. Portfolio Snapshot (portfolio_snapshot)

Fetch the portfolio first, organize the data, and then generate the image:

portfolio(action="get")
-> organize the data (company name, ticker, price, percent change, shares, and so on)
-> image_gen(image_type="portfolio_snapshot", content="AAPL Apple $189.50 +1.2%\nTSLA Tesla $245.30 -0.8%\n...")

2. Stock Analysis Graphic (stock_analysis)

Fetch the stock data first, organize it, and then generate an infographic:

data_fetch(data_type="snapshot", symbol="ticker")
-> optionally use web_search to gather moat, competitive advantage, and similar context
-> image_gen(image_type="stock_analysis", content="Company: NVIDIA NVDA\nMarket cap: 3.2T\nPE: 65x\nMoat: CUDA ecosystem + AI training dominance\n...")

3. General Image (general)

Generate directly from the user's description:

image_gen(image_type="general", prompt="A futuristic image showing the global financial market")

Important Rules

  • portfolio_snapshot and stock_analysis must fetch real data first, and the content must include detailed, concrete numbers
  • You may use the prompt parameter to specify extra visual style preferences

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.