Financial Literacy Q&A for Openclaw

Prerequisites

• An AI agent platform that supports SKILL.md, such as Claude Code, Cursor, Codex, or Gemini CLI.
• Windows, macOS, or Linux.
• An LLM API supplied by the agent platform.
• A-share data from a public financial API or an approved user-owned dataset.
• Optional API keys for data providers, stored as agent-platform environment variables.

Install the skill

The source document does not define a package manager or dedicated installer. Install it by placing the skill directory and its SKILL.md file in the skills location supported by your agent platform.

mkdir -p ./skills/fin-literacy
cp SKILL.md ./skills/fin-literacy/SKILL.md

Restart or reload the agent so it discovers the skill. If your platform uses a different skills directory, copy the same directory structure into that location.

Configure data access

Set provider credentials through your platform’s secret or environment-variable mechanism; do not hard-code keys in prompts, source files, or logs.

export A_SHARE_API_KEY="replace-with-your-provider-key"

Use HTTPS for API communication, restrict key permissions, rotate credentials periodically, and confirm that the selected data source permits your intended use. The skill exposes read and exec tools and may require agent execution support for MD+EXEC workflows.

Input schema

Common domain metadata

• stock_code: A-share security identifier.
• time_period: Analysis interval such as 1M.
• user_id: Identifier used for learning-path and personalization workflows.
• risk_preference: User risk profile used for decision-support classification.
• strategy: Strategy name and parameters for backtesting.
• portfolio: Holdings and position weights for risk analysis.
• timestamp: Market-data observation time.

Output envelope

{
  "success": true,
  "data": {
    "result": "Financial literacy or analysis result",
    "metadata": {
      "skill": "fin-literacy",
      "version": "1.0.0",
      "direction": "A-share"
    }
  },
  "error": null
}

Result taxonomy

Sensitive data should be protected with TLS in transit, AES-based storage encryption, log desensitization, input validation, access control, monitoring, and periodic security audits.