Agent Add Rule
Adds custom rules to the agent's decision-making process, influencing its actions and responses.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add agent-add-rule npx -- -y @trustedskills/agent-add-rule
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"agent-add-rule": {
"command": "npx",
"args": [
"-y",
"@trustedskills/agent-add-rule"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The agent-add-rule skill allows an AI agent to add rules to a defined rule system. This enables agents to dynamically modify their behavior and decision-making processes based on new information or changing circumstances. The skill facilitates the creation of flexible and adaptable agents capable of learning and evolving over time.
When to use it
- Dynamic Task Management: An agent managing project tasks needs to add a rule prioritizing urgent requests received after a certain deadline.
- Adaptive Chatbots: A chatbot requires adding a new rule to handle a newly identified user query or intent.
- Automated Trading Systems: An automated trading system needs to incorporate a rule based on real-time market data to adjust investment strategies.
- Personalized Recommendations: An agent providing product recommendations should add a rule to boost items from brands a user has recently shown interest in.
Key capabilities
- Adding new rules to an existing rule system.
- Defining conditions and actions for each rule.
- Prioritizing rules based on specified criteria.
- Modifying existing rules within the system.
Example prompts
- "Add a rule: If user sentiment is negative, offer a discount of 10%."
- "Create a new rule to prioritize tasks with a deadline less than 24 hours from now."
- “Update the ‘high priority’ rule to also consider task importance.”
Tips & gotchas
The skill requires a pre-existing and defined rule system for it to operate within. Ensure the agent has access to and understanding of this existing structure before attempting to add or modify rules.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.