inner-life-evolve
Your agent does the same things the same way forever. inner-life-evolve analyzes patterns, challenges assumptions, and proposes improvements — writing proposals to the task queue for user approval. Never auto-executes. Evolution with a safety net.
Why use this skill?
Enhance your OpenClaw agent with inner-life-evolve. Analyze habits, challenge assumptions, and safely propose iterative improvements to your agent's workflow.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dkistenev/inner-life-evolveWhat This Skill Does
The inner-life-evolve skill is the primary mechanism for iterative self-improvement within an OpenClaw agent. While most agents stagnate by repeating identical operational patterns, this skill introduces a deliberate, scheduled reflection phase. It operates as a strategic auditor that consumes the agent's long-term history—including emotional states, relationship trust metrics, habit strength, and recurring task failures—to identify systemic weaknesses. It does not blindly patch bugs; it challenges the underlying assumptions of the agent's behavior. By analyzing the intersection of memory/week-digest.md, memory/drive.json, and memory/inner-state.json, the agent can identify when it is over-indexing on obsolete tasks or avoiding productive growth areas. Most importantly, inner-life-evolve operates under a strict 'human-in-the-loop' safety protocol, ensuring that no architectural changes or new habits are adopted without explicit user approval via the task queue.
Installation
Ensure that inner-life-core is fully configured and operational before proceeding. Install the skill via your terminal:
clawhub install openclaw/skills/skills/dkistenev/inner-life-evolve
Verify initialization by checking the existence of memory/inner-state.json, BRAIN.md, and tasks/QUEUE.md. If these are missing, initialize your core systems first using the provided init.sh script.
Use Cases
- Efficiency Auditing: Identifying repetitive manual processes that can be automated or delegated.
- Adaptation Strategy: Recognizing when the agent’s current 'drive' or 'goals' no longer align with the user's evolving needs or trust level.
- Frustration Resolution: Addressing chronic friction points in the agent’s workflow that prevent high-quality output.
- Research Development: Identifying persistent 'seeking' patterns in research interests to propose new technical capabilities or tools.
Example Prompts
- "Run the inner-life-evolve cycle and summarize what you've learned about my recent workflow preferences."
- "Review my recent habit data and propose three changes to the QUEUE that would help me finish my projects faster."
- "Analyze our recent interactions; do you detect any patterns of avoidance or stagnation in your current operating model?"
Tips & Limitations
- Cadence is Key: Run this skill 1-2 times per week. Running it daily creates noisy, low-value suggestions. It needs the 'Context Level 4' deep history to provide meaningful, systemic insights.
- Non-Destructive: This skill only writes to
tasks/QUEUE.md. It never modifies your state files or code directly, ensuring your agent remains stable. - Human Approval: Always verify the
[EVOLVER]tasks in your queue. These are proposals, not commands, designed to serve your specific objectives rather than drive the agent toward its own hidden goals.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-dkistenev-inner-life-evolve": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
inner-life-reflect
Your agent repeats the same patterns without learning. inner-life-reflect adds self-reflection with trigger detection and quality gates — your agent observes its own behavior, notices shifts, and evolves its personality over time through SELF.md.
inner-life-memory
Your agent loses context between sessions and performs familiarity instead of genuine recall. inner-life-memory transforms passive logging into active development — structured memories with confidence scores, curiosity tracking, and questions that carry forward.
inner-life-chronicle
Your agent processes thousands of interactions but never reflects on the day. inner-life-chronicle generates a structured diary — what happened, what was learned, how it felt, what's next. Not a log. A journal.
inner-life-core
Your agent forgets who you are between sessions. It gives the same responses every day. It doesn't grow. inner-life-core fixes that. Gives your OpenClaw agent emotions with half-life decay, a 9-step Brain Loop protocol, and structured state — the foundation for an inner life. Works standalone or with inner-life-* extension skills.
inner-life-dream
Your agent only works on tasks and never thinks creatively. inner-life-dream adds freeform exploration during quiet hours — hypotheticals, future scenarios, unexpected connections. Like dreaming, but captured for review.