A precision execution engine that applies approved AI candidates to target files with built-in safety guards and automatic backup systems.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install auto-improvement-executor
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 auto-improvement-executor 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 Improvement Executor?
The Improvement Executor is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between AI-generated recommendations and final implementation. It automates the application of accepted candidates—such as documentation updates, frontmatter changes, or markdown section injections—while maintaining a rigorous safety-first approach. By creating pre-modification backups and detailed execution traces, it ensures that every change is traceable and reversible.
This skill is particularly vital for developers using Openclaw Skills to manage large-scale automated improvements. It handles the heavy lifting of file manipulation through four distinct action types, allowing AI agents to perform structured updates without human intervention, yet under the strict control of predefined recommendation scores and category checks.
Improvement Executor Use Cases
- Applying approved documentation improvements or reference updates to a codebase.
- Reverting problematic changes using generated receipt artifacts and backup files.
- Previewing potential modifications across a project using dry-run mode before final commitment.
- Automating YAML frontmatter metadata updates across multiple markdown files.
How Improvement Executor Works
- The tool receives a ranking artifact from the discriminator containing the candidate ID and execution plan.
- It validates the candidate against safety guards, checking for supported categories and the required acceptance status.
- A pre-execution backup is automatically generated and stored in the state root directory to prevent data loss.
- The specified action (append, replace, insert, or update) is performed on the target file.
- An execution trace is generated, providing a structured diff summary and a rollback pointer for subsequent validation stages.
Improvement Executor Setup
To install and run the Improvement Executor as part of your Openclaw Skills workflow, ensure you have the required dependencies (including PyYAML for YAML updates) and use the following CLI commands:
# Install dependencies
pip install PyYAML
# Execute a specific improvement candidate
python3 scripts/execute.py \
--input ranking.json \
--candidate-id cand-01-docs \
--state-root ./state
# Rollback a change using the execution receipt
python3 scripts/rollback.py --receipt receipt.json
Improvement Executor Data Schema & Taxonomy
The skill generates and consumes structured JSON data to maintain the integrity of the Openclaw Skills pipeline:
| Field | Description |
|---|---|
ranking.json |
The input artifact containing scored candidates and execution plans. |
execution_trace |
A dictionary capturing the action type, status, and diff summary for feedback loops. |
rollback_pointer |
Contains the path to the backup file and the restore method for emergency recovery. |
result.json |
The output artifact indicating success, modified status, and the next suggested workflow step. |
Improvement Executor Advanced Features
- Multi-Action Support: Native handling of markdown headings, bullet points, and YAML frontmatter merging.
- Recommendation Enforcement: Prevents execution of low-scoring candidates unless the explicit --force flag is used.
- Category Filtering: Restricts automated execution to low-risk categories like docs and guardrails by default.
- Feedback Loop Integration: Captures detailed diff summaries compatible with GEPA (Goal-driven Execution and Planning Architecture) loops.
SKILL.md
Loading
Related Openclaw Skills
ByteDance Organization Framework
A management methodology skill based on the ByteDance philosophy of Context not Control and algorithm-driven organizational systems.
Feelings Framework
A persistent emotional layer for AI agents that tracks mood and feeling intensities over time to shape dynamic response behaviors.
Improvement Gate
A multi-layered validation framework that protects code integrity by enforcing strict mechanical quality gates on AI-generated improvements.
Wang Xing Perspective
An AI-driven strategic mental model based on Meituan founder Wang Xing's core philosophy for long-term business success.
Improvement Learner
Improvement Learner provides a structural quality assessment and self-improvement loop for Openclaw Skills using a 6-dimensional evaluation framework.
Improvement Generator
An automated engine that produces ranked improvement candidates for AI skills based on feedback loops, failure traces, and target analysis.
Featured*
