Agent Skills Hub

Documenting Code

Synchronize project documentation with code. Maintains feature specs, API contracts, and READMEs using init-project standards to ensure traceability and completeness.

writing-plans

Creates detailed, step-by-step TDD implementation plans for software development tasks.

data-visualization

Create professional data visualizations with Python using matplotlib, seaborn, and plotly. Includes chart selection guidance, design principles, accessibility standards, and code patterns for publication-quality figures.

code-formatting

Format and lint JS, TS, and JSON files on the current branch using Biome. Useful for code cleanup before commits or PRs.

debugging

Standardized debugging and diagnostic guidelines for AI coding agents.

testing-strategies

Implement robust software testing strategies, including unit, integration, and E2E tests, mocking frameworks, TDD patterns, and best practices for high-quality, reliable code across any stack.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

pr-operations

Manage PR review workflows, resolve threads, and handle discussion comments using specialized erk exec commands.

avoid-feature-creep

A framework for software teams and AI agents to prevent feature creep, enforce scope discipline, and ship focused MVPs by applying strict validation, backlog hygiene, and clear decision-making processes.

lading-optimize-submit

Automates the submission workflow for lading performance optimizations, including branch management, git commits, and PR creation.

qa

Browser-based QA automation for web applications. Performs automated site audits, visual regression testing, user flow verification, and issue tracking with real-time browser snapshots.