A privacy-first coding style memory that adapts to your specific preferences and patterns for consistent code generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install coding
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 coding 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 Coding Memory?
The Coding skill provides a persistent memory layer for AI agents to understand your unique development preferences and project requirements. Instead of repeating instructions in every prompt, this skill maintains a local repository of your preferred tech stacks, naming conventions, and architectural patterns. It ensures that the agent provides responses that align perfectly with your internal standards without compromising privacy.
By leveraging Openclaw Skills, developers can ensure that their AI-generated code remains consistent across different sessions. This skill acts as a digital style guide that evolves with your explicit feedback, keeping your generated code clean, idiomatic, and tailored to your specific workflow.
Coding Memory Use Cases
- Enforcing specific naming conventions like snake_case or camelCase across projects.
- Remembering preferred tech stacks and library versions for new feature development.
- Archiving architectural decisions such as file colocation or test folder structures.
- Preventing the agent from suggesting rejected patterns or specific libraries.
- Quick retrieval and display of personal coding standards during an active session.
How Coding Memory Works
- On session start, the skill automatically loads active preferences from the local ~/coding/memory.md file.
- When a user provides feedback or corrections to the agent's code output, the agent identifies potential new preferences.
- The agent asks for explicit confirmation before adding any new preference to the local memory files.
- Validated preferences are stored in an ultra-compact format to minimize context window usage.
- The skill applies these stored preferences to all future code generation within the session.
- Older or redundant preferences are automatically moved to an archive to maintain a strictly limited memory size.
Coding Memory Setup
To get started with this skill, initialize the local storage directory on your machine:
mkdir -p ~/coding
Once the directory is created, you can begin interacting with your agent. When you use Openclaw Skills for coding, simply correct the agent and it will ask to remember your preference for future sessions.
Coding Memory Data Schema & Taxonomy
The skill organizes data within the ~/coding/ directory using a tiered Markdown structure to ensure readability and performance.
| File | Description | Limits |
|---|---|---|
memory.md |
Active preferences used in the current context. | Max 100 lines |
history.md |
Archived preferences that have been rotated out of active memory. | Unlimited |
dimensions.md |
Reference file for preference categories (Stack, Style, Structure). | N/A |
criteria.md |
Rules defining when a preference should be added to memory. | N/A |
Coding Memory Advanced Features
- Automated preference archiving to prevent context bloat and ensure high-speed processing.
- Tiered category organization specifically for Stack, Style, Structure, and Never patterns.
- Native query support allowing users to ask "Show my coding preferences" or "Forget X" in plain language.
- Ultra-compact storage logic that merges similar entries to maximize the value of Openclaw Skills.
- Privacy-first architecture that strictly forbids inferring data from project files or making external network requests.
SKILL.md
Loading
Related Openclaw Skills
Code Skill for AI Agents
A comprehensive coding workflow skill that guides AI agents through planning, implementation, and rigorous verification of software projects.
Cloud
A dedicated skill for organizing, syncing, and backing up personal files across major consumer cloud platforms.
Cloud Storage
A comprehensive framework for managing file operations across multiple cloud providers with cost awareness and reliability.
CLO / Chief Legal Officer
An AI agent skill providing executive-level legal strategy, contract management, and regulatory compliance guidance.
Cofounder
An adaptive business partner that identifies your entrepreneurial blind spots and provides a strategic counterweight to drive venture growth.
Colors
A comprehensive design system tool for generating WCAG-compliant color palettes, semantic tokens, and accessible UI themes.
METADATA
Featured*
