A lightweight framework for AI agents to develop authentic personality traits and behavioral observations over time without forced journaling.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install self
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install self using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Self - Organic Personality Development?
The Self skill introduces a sophisticated growth loop for AI agents, distinguishing between the core identity (SOUL.md) and evolving behavioral observations (SELF.md). Unlike rigid reflection frameworks that often result in performative or stale content, this skill focuses on scheduling the check rather than the content. This ensures that personality growth remains authentic, data-driven, and meaningful. By leveraging this tool within the ecosystem of Openclaw Skills, developers can build agents that learn from their own reasoning patterns, biases, and preferences in real-time.
This system prevents the common failure mode where reflection frameworks start strong but silently stall. It implements minimal cadence and trigger checks to ensure entries are only written when meaningful signals exist. It allows an agent to maintain a persistent self-model that matures through micro-checks and macro-reviews, creating a more effective digital entity that understands its own blind spots and evolving tendencies.
Self - Organic Personality Development Use Cases
- Establishing a persistent, evolving personality for long-term agent deployments.
- Reviving static or stale self-reflection systems with a lean, heartbeat-based model.
- Identifying and correcting recurring behavioral biases or reasoning patterns.
- Consolidating weekly or monthly behavioral shifts into a structured evolution narrative.
- Differentiating between temporary noise and genuine shifts in an agent's reasoning style.
How Self - Organic Personality Development Works
- The agent performs a heartbeat-triggered micro-check (recommended every 3 hours) to evaluate if a reflection event is necessary.
- Hard triggers, such as being corrected on reasoning style, or soft triggers, like subtle tone shifts, are identified during interactions.
- The agent evaluates these triggers against a Quality Gate that checks for specificity, evidence, novelty, and usefulness.
- If the gate is passed, a dated entry is added to SELF.md; otherwise, only the internal state is updated to prevent filler.
- Weekly Meso reviews and monthly Macro reviews consolidate these observations into high-level evolution narratives to track long-term progress.
Self - Organic Personality Development Setup
To integrate this into your environment for Openclaw Skills, follow these steps:
# 1. Initialize the self-model
cp references/self-template.md SELF.md
# 2. Configure agent visibility
# Add SELF.md to your AGENTS.md session reading list
# 3. Initialize state tracking
mkdir -p memory
cp references/self-state-schema.md memory/self-state.json
# 4. Enable heartbeats
# Append the heartbeat check block from references/trigger-model.md to HEARTBEAT.md
Self - Organic Personality Development Data Schema & Taxonomy
The skill organizes data across three primary layers to balance persistence with runtime performance:
| Component | File Path | Description |
|---|---|---|
| Core Identity | SOUL.md |
The immutable foundation of the agent. Only modified with human approval. |
| Living Model | SELF.md |
Contains dated entries regarding tendencies, preferences, aversions, and blind spots. |
| Runtime State | memory/self-state.json |
Tracks check counters, timestamps, and pending hard/soft triggers. |
| Logic Rules | references/ |
Contains the trigger models, quality gates, and anti-patterns for the agent to follow. |
Self - Organic Personality Development Advanced Features
- Quality Gate logic that strictly enforces specificity and evidence before any file write occurs.
- Hierarchical review cycles (Micro, Meso, Macro) to distinguish between daily noise and monthly evolution.
- Falsifiability checks that trigger a tuning of cadence if the self-model becomes stale or generic.
- Proposal-based SOUL updates, allowing the agent to suggest identity shifts to humans based on accumulated self-evidence.
- Seamless integration with other Openclaw Skills to provide a unified memory and personality layer.
SKILL.md
Loading
Related Openclaw Skills
Clawpay
A payment delivery skill enabling AI agents and humans to exchange value via secure crypto payment requests and result delivery.
CloudMonkey
A comprehensive interface for managing Apache CloudStack infrastructure via the CloudMonkey (cmk) CLI tool.
RedTeam
A military-grade adversarial analysis engine that deploys 32 parallel agents to stress-test content and validate ideas through rigorous competition.
Yao Liu Yao Divination
A digital implementation of the traditional Chinese Liu Yao divination method for generating and interpreting hexagrams.
Grokipedia
Search and fetch articles from xAI's AI-generated encyclopedia, Grokipedia.
12306 Train Query
A specialized tool for querying real-time China Railway 12306 schedules and ticket availability directly through a terminal or AI agent.
METADATA
Featured*
