Marketplace
SkillHub Club catalog feed.
Public marketplace mirror sourced from skillhub.club. This source view keeps the new outcome-first browsing model while filtering server-side to a single upstream feed.
gastown
Gastown is a Go-based multi-agent orchestration system for Claude Code that enables parallel task execution. It provides work tracking through beads, manages agent lifecycles via polecats and crew, and handles automated code merging through the Refinery. Requires Go installation and terminal access.
project-analyze
A multi-phase workflow for generating structured project analysis reports with Mermaid diagrams. It systematically explores codebases, analyzes architecture and design patterns, and produces visual documentation through parallel agent execution and quality consolidation phases.
news
This skill fetches and analyzes Anthropic's official news, providing structured technical and business insights. It follows a four-step workflow: news collection, multi-dimensional analysis, knowledge organization, and report generation. Includes templates for technical updates and business dynamics with practical frameworks like SWOT and 5W1H.
ai-voice-cloning
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs alternative, natural voice, realistic speech, voice ai
regulatory-templates-gate2
Gate 2 validation sub-skill for regulatory template workflows. Validates uncertain field mappings from Gate 1 using test data, enforces strict validation thresholds (>90% pass rate, 100% mandatory validation), and prevents incorrect mappings from reaching production templates. Acts as a quality firewall before template generation.
regulatory-templates
A highly structured, risk-averse orchestration skill for Brazilian financial regulatory template creation, enforcing a rigorous 3-gate validation process to prevent costly compliance errors.
handoff-tracking
Creates structured handoff documents for session transitions, capturing task status, learnings, decisions, and next steps. Automatically indexes documents for future retrieval and integrates with git state and session traces. Uses a detailed template with specific sections for critical references, recent changes, and action items.
pre-dev-trd-creation
This Skill enforces a strict gate for creating Technology-Agnostic Technical Requirements Documents (TRDs). It blocks technology-specific decisions, mandates loading of organizational standards, and guides teams through abstract architectural pattern selection before implementation choices.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
using-dev-team
A skill that provides 7 specialized developer agents for backend, DevOps, frontend, design, QA, and SRE tasks. It enforces strict dispatch protocols with clear trigger conditions, blocker criteria, and pressure resistance rules. The skill prevents direct implementation by requiring specialist delegation for technical decisions.
smart-contract-generator
Generates boilerplate Solidity code for common token standards like ERC-20, ERC-721, and ERC-1155 using OpenZeppelin libraries. Includes security patterns, gas optimization tips, and basic deployment scripts. Useful for developers starting a new Web3 project who need a secure foundation.
pufferlib
Provides tools for high-performance RL training with PPO, vectorized environment simulation, and custom environment development. Includes CLI commands, Python code examples for training loops, environment templates, and performance optimization techniques.
serena
Serena enables Claude to understand and manipulate code at the symbol level using Language Server Protocol. It provides IDE-like capabilities for finding definitions, tracking references, and making precise edits across 30+ programming languages, bridging the gap between text-based LLMs and semantic code understanding.
Video Processor
Process video files with audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions video conversion, audio extraction, transcription, mp4, webm, ffmpeg, or whisper transcription.
pyhealth
PyHealth provides a specialized Python toolkit for healthcare machine learning with clinical datasets, prediction tasks, and medical coding. It offers standardized interfaces for EHR data, implements healthcare-specific models like RETAIN, and includes fairness evaluation tools for clinical deployment.
using-tw-team
Specialized agents for technical documentation tasks including functional guides, API references, and quality reviews. Provides clear dispatch patterns, voice/tone standards, and integration with development teams. Follows an orchestrator model where users delegate to specialized writers rather than writing manually.
apply-mantel-styles
Provides detailed Mantel brand styling rules for diagrams and frontend components. Includes Mermaid theme definitions, CSS variables, component guidelines, and Tailwind config. Helps maintain visual consistency across technical documentation and UI implementations.
repo-analyzer
Analyzes GitHub repositories to assess structure, documentation, dependencies, and contribution patterns. Provides health reports with specific recommendations like adding missing files or updating outdated dependencies.
mockup-extraction
Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.
anti-ai-validator
Detects and removes AI-generated text patterns in Korean writing. It scans for overused phrases like '~를 넘어', repetitive vocabulary, and unnatural sentence structures. Provides specific replacements and a step-by-step correction workflow to make content sound more human.
writing-openrewrite-recipes-js
This skill provides templates, guides, and examples for writing OpenRewrite recipes in TypeScript to automate code transformations. It covers visitor patterns, template matching, testing, and recipe registration. It clearly defines when not to use it and offers a structured workflow.
ebfe-validator
A specialized validation tool for HEC-RAS eBFE/BLE models that systematically checks file references, path validity, and data accessibility to ensure models are runnable and automation-ready.
executing-remote-plans
Enables distributed execution of HEC-RAS hydraulic models across multiple machines using PsExec, Docker, or SSH. Handles worker initialization, queue scheduling, and result aggregation for parallel processing. Specifically addresses GUI application requirements with session-based execution.
dbt-modeling
Provides structured templates and patterns for writing dbt models across bronze, silver, and gold layers. Includes CTE patterns, staging rules, and materialization guidance with concrete SQL examples for common data modeling scenarios.