A dedicated AI programming agent designed for automated code generation, security audits, and intelligent refactoring via the opencode CLI.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install friday
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 friday 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 Friday (星期五)?
Friday is a specialized programming agent within the Openclaw Skills ecosystem, built to act as a virtual teammate for developers. By utilizing the opencode CLI, it assists in the entire software development lifecycle, from drafting initial feature implementations to performing complex code refactoring and debugging. This skill is optimized to work with various AI models to ensure high-quality code output that adheres to modern standards and security practices.
Whether you are working on a solo project or managing large-scale enterprise repositories, Friday provides a structured approach to coding. It integrates deeply with your local environment to analyze context, run tests, and provide actionable insights, making it a premier choice among Openclaw Skills for developers looking to automate repetitive tasks and improve code maintainability.
Friday (星期五) Use Cases
- Implementing new features like user authentication modules with JWT and OAuth2.
- Automating Pull Request (PR) reviews for code quality, security vulnerabilities, and performance bottlenecks.
- Refactoring legacy code to reduce complexity and improve readability.
- Troubleshooting and fixing bugs by analyzing error logs and identifying root causes.
- Generating comprehensive unit tests and technical documentation for existing modules.
How Friday (星期五) Works
- The user initiates a programming task using the opencode CLI command within a project directory.
- Friday analyzes the task requirements and gathers necessary context from specified files or the defined tech stack.
- Depending on the selected mode (Auto, Interactive, or Read-Only), the agent plans and executes code modifications or analysis.
- For complex or long-running tasks, the agent can run in background sessions, allowing for progress monitoring via session IDs.
- Once the task is complete, Friday provides a summary of changes, critical decision logs, and potential risk warnings for the developer to review.
Friday (星期五) Setup
To utilize this agent among your Openclaw Skills, ensure the opencode CLI is installed and configured on your system (Linux, macOS, or Windows).
# Run a specific programming task in the current directory
opencode run "Implement a REST API for user profiles"
# Start an interactive chat session for collaborative coding
opencode chat
# Check the status of a background task
opencode status <session-id>
Configure your preferred AI models in ~/.opencode/config.toml to customize the agent's behavior.
Friday (星期五) Data Schema & Taxonomy
Friday organizes its operations through configuration profiles and detailed output reports to maintain transparency in the Openclaw Skills workflow.
| Data Type | Description |
|---|---|
| Config File | ~/.opencode/config.toml - Stores model preferences and auto-approve settings |
| Session Logs | Detailed execution history for background tasks, accessible via CLI |
| Audit Reports | Categorized issues (Security, Performance, Style) with severity levels |
| Context Metadata | Stack-specific configurations for tools like Ruff, Pytest, or ESLint |
Friday (星期五) Advanced Features
- Background Session Management: Execute long-running architectural changes without blocking your terminal.
- Context-Aware Processing: Use the
--contextflag to provide specific directory or file references for better accuracy. - Tech Stack Profiles: Define specialized profiles for Python, JavaScript, and other languages to use specific linters and test runners.
- Multi-Mode Operation: Switch between
--autofor trusted tasks,--interactivefor collaborative work, and--read-onlyfor safe analysis. - Automated Linter Integration: Automatically run and fix issues found by linters during the code generation process.
SKILL.md
Loading
Related Openclaw Skills
Abby Watch
A streamlined time management utility for checking current time and tracking countdowns directly from the command line.
Abby Browser Skill
A natural language interface for browser automation that allows users to navigate, interact, and extract data from the web using simple commands.
Abby Autonomy Skill
An autonomous task execution system that transitions AI agents from passive heartbeat monitoring to proactive, queue-based workflow management.
Office Automation Assistant
An efficient AI agent skill that transforms raw notes into professional daily reports, weekly updates, and meeting summaries.
Kitful AI Article Generator
An AI-driven content engine that transforms keywords into fully researched, humanized, and publication-ready long-form articles.
MinerU
A sophisticated document parsing tool that converts complex PDFs, Word docs, and PPTs into AI-ready Markdown with full support for formulas and tables.
Featured*
