Agent Skills Hub

test-data-management

Strategic test data generation, management, and privacy compliance for scalable, secure, and realistic quality engineering workflows.

skills-management

Search, discover, install, update, and manage skills for AI coding agents. Centralized interface for ecosystem-wide skill discovery and local organization.

github-commit-recovery

Tool for recovering deleted or force-pushed GitHub commit content, diffs, and metadata using the REST API, git fetch, and direct URL access.

solana-dev

A unified Solana development skill hub featuring multi-agent orchestration, progressive skill loading, and deep integrations for Anchor, Token-2022, DeFi protocols, and security auditing.

variant-analysis

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, or performing systematic code audits.

feature-dev

Guided, systematic feature development agent that orchestrates codebase exploration, architectural design, implementation, and automated testing.

claude-code-mechanism-selector

A decision-support tool for Claude Code users to select the optimal extension mechanism—slash commands, skills, subagents, or hooks—based on project requirements.

pdf

A comprehensive PDF toolkit for extracting text/tables, merging, splitting, rotating, and programmatically generating or filling PDF documents using Python and CLI tools.

git-advanced

Advanced Git workflow automation including rebase strategies, bisect debugging, cherry-picking, and conflict resolution with safety guardrails.

new-analyzer

Guide for implementing a new AI coding agent analyzer in Splitrail to track token usage, costs, and performance metrics.

figma-create-new-file

Create new Figma design or FigJam files directly via the MCP server. Automatically resolves plans and initializes new canvases for your design workflows.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.