A recursive optimization framework that reviews weekly agent memory to extract friction patterns and crystallize them into permanent skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install weekly-self-improve-loop
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 weekly-self-improve-loop 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 Weekly Self-Improve Loop?
The Weekly Self-Improve Loop is a high-level maintenance protocol designed to prevent the degradation of AI autonomy. By analyzing the last seven days of operational memory, this skill identifies recurring mistakes and systemic blockers that manual or ad-hoc interventions often miss. It serves as a continuous improvement engine for your AI ecosystem.
Integrating this into your Openclaw Skills library ensures that your agent doesn't just perform tasks, but actually learns from its environment. It transforms raw interaction data into actionable intelligence, allowing for the automated creation of recovery skills and the refinement of the agent's baseline performance metrics.
Weekly Self-Improve Loop Use Cases
- Performing a scheduled weekly audit of AI agent task completion and failure rates.
- Identifying hidden friction patterns across multiple complex projects.
- Converting recurring blockers into automated recovery skills to ensure higher future autonomy.
- Generating data-driven reports to visualize agent progress and focus areas for the upcoming week.
How Weekly Self-Improve Loop Works
- The skill triggers a memory scan to aggregate all Markdown files generated in the last 7 days.
- It parses the content to calculate key performance indicators, including total tasks, completion rates, and blocker frequency.
- Using pattern extraction logic, it identifies the top three most frequent friction points based on blocker metadata.
- It automatically initiates the creation or update of local skills to address these specific friction patterns.
- Finally, it generates a standardized Weekly Report to document metrics and define the focus for the next cycle.
Weekly Self-Improve Loop Setup
To implement the Weekly Self-Improve Loop within your local environment, ensure your memory files follow the standard tagging convention (Task, Status, Blocker) and run the following PowerShell setup:
# Navigate to your agent root
cd your-ai-agent-directory
# Ensure the skills directory structure exists
mkdir -p skills/local
mkdir -p memory
# The loop can be triggered manually or via a scheduled task
./scripts/weekly-review.ps1
Weekly Self-Improve Loop Data Schema & Taxonomy
The skill utilizes a structured reporting and extraction schema to maintain consistency across the Openclaw Skills ecosystem:
| Data Point | Source Tag | Format |
|---|---|---|
| Total Tasks | Task: |
Integer |
| Task Status | Status: complete |
Boolean/Count |
| Blockers | Blocker: {description} |
String Pattern |
| Weekly Report | N/A | Markdown File (YYYY-MM-DD.md) |
| Skill Mapping | Friction Pattern | Kebab-case String |
Weekly Self-Improve Loop Advanced Features
- Automated Skill Crystallization: Converts recurring blockers directly into functional recovery scripts.
- Trend Analysis: Calculates percentage-based completion and blocker rates to track agent reliability over time.
- Multi-Agent Memory Support: Can aggregate memory files from various sub-agents if they share the centralized memory directory.
- Privacy-First Aggregation: Focuses on metrics and counts rather than raw content, ensuring safe local processing.
SKILL.md
Loading
Related Openclaw Skills
Qian Jiu Jiu (钱纠纠)
A specialized Chinese message preprocessor that identifies linguistic errors and requests user verification before AI processing.
Memory to Skill Crystallizer
An automated utility that scans memory logs for recurring patterns and crystallizes them into executable local skills.
Voice Call
A powerful telephony integration allowing AI agents to initiate, manage, and conclude voice calls through major providers like Twilio and Telnyx.
tg_search
An automated discovery tool to search and extract metadata from public Telegram channels and groups using Telethon.
ChessGuardian
A comprehensive chess integration skill that enables AI-powered gameplay, real-time move analysis, and live board rendering.
Medical Priority Scorer
A deterministic AI scoring engine that ranks medical messages into P1, P2, and P3 priority buckets using urgency, sentiment, and patient context.
Featured*
