← Back to Skills Marketplace
5928
Downloads
10
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent
Description
Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic.
Usage Guidance
Review this skill carefully before installing in agents with persistent memory. It is most appropriate where users know the agent may adapt from interaction patterns and where there is a clear way to disable, inspect, or clear learned preferences. Avoid using it unchanged for customer-facing, workplace, or sensitive contexts unless you add explicit consent and memory-retention rules.
Capability Analysis
Type: OpenClaw Skill
Name: agent
Version: 1.0.0
The skill bundle consists entirely of markdown files defining an AI agent's identity, personality, voice, boundaries, and adaptation rules, along with a standard metadata JSON. There is no executable code, no instructions for data exfiltration, unauthorized network calls, persistence mechanisms, or any other malicious activities. The `boundaries.md` file even explicitly defines restrictions on external communication and actions requiring user permission, indicating a focus on controlled behavior. The content is fully aligned with its stated purpose of defining an agent's identity.
Capability Assessment
Credentials
The boundary guidance allows autonomous technical work within approved scope and workspace-only effects, while requiring approval for spending, external communications, significant deletion, and irreversible external impact; this is broadly proportionate but users should confirm it matches their environment.
Install Mechanism
The artifact contains five non-executable Markdown files with no install scripts, dependencies, symlinks, remote payload retrieval, or hidden execution surface found.
Instruction Scope
The adaptation guidance explicitly tells agents to learn from implicit behavioral signals, habit patterns, relationship history, and trust level over time, but it does not define consent, disclosure, retention limits, or user review/reset controls.
Persistence & Privilege
The skill encourages continuity, remembering established boundaries, communication preferences, relationship history, and trust level, but does not distinguish session context from persistent memory or require explicit permission before retaining inferred preferences.
Purpose & Capability
The skill's purpose is coherent: it defines agent identity, voice, boundaries, and adaptation behavior using Markdown guidance only, with no bundled code or network behavior.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent - After installation, invoke the skill by name or use
/agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: voice, boundaries, adaptation, identity templates
Metadata
Frequently Asked Questions
What is Agent?
Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic. It is an AI Agent Skill for Claude Code / OpenClaw, with 5928 downloads so far.
How do I install Agent?
Run "/install agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent free?
Yes, Agent is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Agent support?
Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.
More Skills