Alex Agent Motivator
Skill by bowen31337
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bowen31337/alex-agent-motivatorWhat This Skill Does
The Alex Agent Motivator is a high-agency meta-skill designed to counteract common failure patterns in AI agents. Built by bowen31337, this skill acts as a cognitive framework that forces the agent to move beyond passive failure modes such as infinite retry loops, excuse-giving, or premature resignation. It embeds an explicit set of anti-patterns and activation levels that guide the AI through systematic recovery, ensuring that if a task encounters resistance, the agent shifts to a more autonomous, investigative, and exhaustive problem-solving mode.
Installation
To install this skill, use the following command in your OpenClaw environment:
clawhub install openclaw/skills/skills/bowen31337/alex-agent-motivator
Use Cases
This skill is essential for complex, long-running tasks where an AI might otherwise hit a wall. Use cases include:
- Debugging: When an agent attempts the same failed fix multiple times.
- Complex Research: When an agent claims it cannot find specific data without first utilizing advanced search or diagnostic tools.
- Deployment/Automation: When an agent is stuck in a loop during an execution phase and needs a 'mindset reset' to re-evaluate its approach.
- Mission Critical Ops: When you want to ensure the agent maintains maximum autonomy and minimizes 'permission-seeking' behavior on reversible tasks.
Example Prompts
- "The agent is stuck on this API integration and keeps throwing a 403 error. Please use the Alex Agent Motivator to force a strategy reset."
- "I'm tired of the agent saying it 'cannot find the file'. /motivate it to search the parent directories and index the structure itself."
- "Try harder on this deployment script; stop giving up after the first failure and instead run the full recovery checklist."
Tips & Limitations
The Agent Motivator is most effective when integrated into high-agency workflows. A key limitation is that it requires the agent to have access to sufficient diagnostic tools; if the environment lacks visibility, the L3 'Full recovery checklist' may fail to provide useful data. Always ensure your agent has appropriate write and read permissions for log files, as the skill relies on checking previous failure logs to reset the agent's mental model. Remember that this skill triggers automatic behavioral changes, so monitor your agent's activity during the first few implementations to ensure it is not becoming overly aggressive in its autonomy.
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-bowen31337-alex-agent-motivator": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: code-execution
Related Skills
Terse
Skill by bowen31337
Identity Resolver
Skill by bowen31337
agent-self-governance
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging). Use when: (1) receiving a user correction — log it before responding, (2) making an important decision or analysis — log it before continuing, (3) pre-compaction memory flush — flush the working buffer to WAL, (4) session start — replay unapplied WAL entries to restore lost context, (5) any time you want to ensure something survives compaction, (6) before claiming a task is done — verify it, (7) periodic self-check — am I drifting from my persona? (8) cost tracking — was that expensive operation worth it? (9) discovering infrastructure — log hardware/service specs immediately.
rsi-loop
Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect their own failure patterns and generate concrete improvement proposals (new skills, routing fixes, SOUL.md updates, memory improvements). Use when: (1) logging a task outcome (success/fail/quality), (2) running periodic self-improvement analysis, (3) reviewing or deploying improvement proposals, (4) integrating RSI into EvoClaw hub/edge agents via MQTT, (5) checking agent health score, (6) any mention of "self-improvement", "recursive improvement", "fix my own mistakes", "improvement loop", or "agent evolution". Core EvoClaw primitive.
clawchain
ClawChain RPC client for EvoClaw agents. Connects to Substrate-based blockchain, queries on-chain agent data, submits transactions, and enables agents to participate in on-chain governance and reputation tracking. Use when working with ClawChain L1 blockchain, agent DIDs, token economics, or agent reputation systems.