A sophisticated tool designed to distill communication history and coding activity into a persistent, persona-driven AI programming partner.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install codegirl-skill
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 codegirl-skill 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 Codegirl Skill Creator?
The Codegirl Skill Creator is a specialized workflow within the Openclaw Skills ecosystem that transforms raw data—such as WeChat logs, Telegram messages, and GitHub activity—into a functional AI persona. This skill allows developers to create a digital twin or a highly specific pair programming partner that retains shared memories, technical preferences, and distinct behavioral traits.
By leveraging local parsing tools and structured analysis prompts, the skill generates a unique environment for the AI agent to operate. It focuses on authenticity, ensuring the generated partner reflects the specific speech patterns, technical stacks, and even the imperfections of the original source material, all while maintaining strict local privacy within the Openclaw Skills framework.
Codegirl Skill Creator Use Cases
- Creating a personalized pair programming partner that understands your specific workflow and technical history.
- Distilling digital footprints from collaboration tools into a persistent AI persona for professional or personal reflection.
- Building context-aware AI assistants that recognize project-specific inside jokes and past debugging sessions.
- Simulating specific technical mentors or collaborators based on historical GitHub and chat data.
How Codegirl Skill Creator Works
- Intake Phase: The user provides basic information including an alias, technical stack, and personality traits through a structured 3-question sequence.
- Data Import: The skill utilizes specialized Python parsers to ingest data from WeChat (txt/html/json), QQ, Telegram, or GitHub activity.
- Memory & Persona Analysis: It extracts two distinct tracks: Coding Memory (Part A) for shared experiences and Persona (Part B) for behavioral logic and speech patterns.
- Review & Generation: The skill generates a summary for user approval before creating the final file structure.
- File Serialization: It writes the memory, persona, and metadata to local directories and generates a runnable SKILL.md file for the new agent.
Codegirl Skill Creator Setup
To initiate the creation process within your terminal, use the following commands:
# Trigger the creation workflow
/create-gf
# Or provide a specific name to start
/create-gf [partner-name]
Ensure that your local environment has Python 3 installed to run the underlying parsers located in the Openclaw Skills tools directory.
Codegirl Skill Creator Data Schema & Taxonomy
The skill organizes data into a structured directory under ./gfs/{slug}/. The following files are generated:
| File | Description |
|---|---|
memory.md |
Contains the Part A 'Collaboration Memory' including shared experiences and debug logs. |
persona.md |
Defines the Part B 'Character Persona' including speech patterns and behavioral rules. |
meta.json |
Stores technical metadata, MBTI, technical stacks, and versioning information. |
SKILL.md |
The final executable skill file that combines memory and persona for the AI agent. |
All source materials like chat exports and photos are stored in dedicated subdirectories: /memories/chats/, /memories/photos/, and /memories/social/.
Codegirl Skill Creator Advanced Features
- Evolution Mode: Users can append new memories or logs to an existing persona using the
/update-gf {slug}command to keep the partner current. - Correction Handler: A feedback loop where the user can say 'They wouldn't say that' to trigger an automated adjustment of the persona logic.
- Multi-Invocable Triggers: The generated skills support specialized modes like
/{slug}-memoryfor pure recall and/{slug}-personafor personality-only interaction. - Local Version Management: Supports snapshots and rollbacks to previous versions of the distilled persona via a dedicated version manager in Openclaw Skills.
- Layer 0 Hard Rules: Integrated safety and authenticity constraints that prevent the AI from breaking character or violating privacy boundaries.
SKILL.md
Loading
Related Openclaw Skills
Diagram Cog
Diagram Cog transforms natural language descriptions into professional, interactive diagrams and high-quality PDFs without manual dragging or layout adjustments.
Context Memoize Skill
A high-performance caching utility designed to store and reuse frequently accessed context fragments to minimize AI processing overhead.
GIF Cog
GIF Cog is an AI-powered animation engine that creates seamless, platform-optimized GIFs and cinemagraphs from scratch using a multi-model production pipeline.
Sticker Cog
An AI-powered skill for creating platform-ready, character-consistent sticker packs and custom emoji sets with 20+ consistent expressions.
slopbuster
An AI text humanizer that strips robotic patterns from prose, code, and academic writing to restore a natural human voice.
Clawder
Clawder is a production-grade AI coding skill that implements JT directives to eliminate agent laziness through mandatory verification and autonomous bug fixing.
Featured*
