What does the agent-config skill do?

This skill configures the OpenClaw agent's settings such as name, model provider, personality prompt, and enabled tools.

What inputs does the agent-config skill require?

config_json (string, required): JSON string with configuration keys: name, model_provider, personality_prompt, tools (array of tool names).

What outputs does the agent-config skill produce?

success (boolean): true if config applied; error (string): error message if failed.

What is an example input for the agent-config skill?

{"config_json": "{\"name\":\"SuperAgent\",\"model_provider\":\"openai\",\"personality_prompt\":\"You are a helpful assistant.\",\"tools\":[\"code_interpreter\",\"web_browser\"]}"}

What configuration keys are supported in the config_json input?

name, model_provider, personality_prompt, tools (array of tool names).

OpenClaw skill

agent-config

An OpenClaw skill that enables agents to manage their configuration by loading from files, environment variables, or remote sources. It supports retrieving, setting, and validating configuration values. The skill allows for hot-reloading of configurations.

View repository Open SKILL.md

Security notice: review the SKILL.md file and repository content first before using any third-party skill.

Files

Review the files below to add this skill to your agents.

_meta.jsonView
SKILL.mdView

SKILL.md content

Unable to load SKILL.md content from source.

How this skill works

The skill declares the capability 'agent-config'
It accepts an input named 'config' as a JSON string
The skill parses the 'config' input as JSON
It applies the parsed configuration to the agent's runtime configuration
It outputs 'status' as 'success' on successful configuration
It outputs 'status' as 'error' if parsing or application fails

When to use it

When an agent needs to update its model provider and API key
When setting the agent's personality, instructions, or name
When configuring tools or environment variables for the agent
When persisting agent configuration changes to a JSON file

Best practices

Backup agent configuration files before running the skill
Verify AGENT_CONFIG_PATH points to the correct directory to avoid overwriting unintended files
Provide OPENAI_API_KEY in the .env file
Use valid JSON for the agent configuration input
Validate JSON configuration syntax before execution

Example use cases

Switching agent language model: Update the agent's model provider and model name, e.g., changing from 'gpt-4o-mini' to 'gpt-4o' via the config input.
Managing agent tools: Enable or disable specific tools by updating the tools array in config, such as adding 'web_browser' or removing tools.
Updating system prompt: Modify the agent's system prompt to adjust behavior or role, specified in the config's system_prompt field.
Configuring memory settings: Adjust memory parameters like max_messages or embedding model in the config's memory section.
Setting agent personality: Define or update the agent's personality traits via the config's personality field.

FAQs

More similar skills to explore

achurch
An OpenClaw skill for church administration that handles member management, event scheduling, sermon retrieval, and donation processing. It provides tools to list members, add new members, schedule events, fetch sermons, and record donations.
agent-council
An OpenClaw skill named agent-council that enables the primary agent to summon a council of specialized sub-agents for deliberating on tasks. The council members discuss the query from unique perspectives, propose solutions, and vote to select the best response. The skill outputs the winning proposal with supporting rationale from the council.
agent-identity-kit
An OpenClaw skill that equips agents with tools to craft, manage, and evolve digital identities, including generating personas, bios, avatars, and communication styles. It supports creating detailed agent personas with name, background, goals, personality traits; crafting bios for specific platforms; designing avatars; tuning voice and style; and adapting identities to new contexts.
agenticflow-skill
An OpenClaw skill that provides tools for interacting with Agentic Flow. The tools enable agents to create agentic flows with defined tasks, execute existing flows, and retrieve flow status and outputs.
agentlens
AgentLens is an OpenClaw skill that enables agents to inspect the internal cognition and actions of other agents. It provides visibility into reasoning traces (thoughts), tool calls and arguments, retrieved memories, and response generation. The skill supports analysis in multi-agent conversations via the "inspect" action targeting a specific agent.
agentskills-io
An OpenClaw skill that integrates agents with the AgentSkills.io platform. It enables agents to search and browse available skills, install them directly into the agent's environment, and manage installed skills including updates and uninstallations.