Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
data-viz-plots
This skill provides ready-to-use Python code templates for generating publication-quality scientific plots using matplotlib and seaborn. It covers common visualization types like scatter plots, line charts, heatmaps, and specialized plots for bioinformatics. The skill runs locally, making it compatible with any LLM provider that can execute Python code.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
linkedin-post
This skill drafts LinkedIn posts by applying data-driven insights from Twitter performance analytics, adapting them for a professional audience. It provides specific templates, compliance guidelines for financial messaging, and a clear process to transform tweet patterns into effective LinkedIn content with proper tone adjustments.
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
hive-mind-advanced
This skill implements a queen-worker multi-agent system for coordinating Claude instances. It provides structured workflows for complex tasks, consensus voting mechanisms, and persistent memory storage. The system supports different queen types (strategic, tactical, adaptive) and specialized worker roles for development, testing, and analysis tasks.
agentic-jujutsu
A version control wrapper that enables multiple AI agents to work on code simultaneously without conflicts. It learns from past operations to suggest patterns and includes quantum-resistant security features. The tool tracks agent trajectories and provides success rate predictions for similar tasks.
reasoningbank-agentdb
This skill integrates AgentDB's high-performance vector database with ReasoningBank patterns for adaptive agent learning. It provides trajectory tracking, verdict judgment, memory distillation, and pattern recognition with 150x faster retrieval. Includes CLI tools, TypeScript API, and 100% backward compatibility with legacy ReasoningBank systems.
context-degradation
This skill provides patterns for diagnosing and fixing context degradation in LLM agents, focusing on issues like lost-in-middle effects and context poisoning. It offers concrete strategies like the four-bucket approach and architectural patterns to mitigate performance drops in long conversations.
call-prep
Prepare for a customer or prospect call using Common Room signals. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', or any call preparation request.
flow-nexus-swarm
A comprehensive cloud-based AI swarm orchestration platform offering sophisticated workflow automation, multi-topology agent coordination, and event-driven execution with strong practical applications.
golang
Provides concrete Go patterns for building backend services, including project structure, error handling, HTTP handlers, repositories, context usage, middleware, configuration, and testing. Shows actual code examples for common tasks like graceful shutdown and worker pools.
frontend-accessibility-standards
A comprehensive and well-structured accessibility guide that provides clear, actionable standards for building inclusive frontend interfaces with practical examples and WCAG compliance.
testing-writing-guidelines
This skill provides concrete guidelines for writing focused tests that prioritize core user flows over edge cases. It emphasizes clear test naming, mocking external dependencies, and fast execution. The decision framework helps developers avoid over-testing during feature development while ensuring critical paths are covered.
frontend-design
Generates frontend code with distinctive visual aesthetics by enforcing specific design principles. Avoids generic AI-generated patterns and encourages bold typography, color choices, and spatial composition. Provides concrete guidelines for typography, motion, and visual details.
nextjs
Build Next.js 16 apps with App Router, Server Components/Actions, Cache Components ("use cache"), and async route params. Includes proxy.ts and React 19.2. Prevents 25 documented errors. Use when: building Next.js 16 projects, or troubleshooting async params (Promise types), "use cache" directives, parallel route 404s, Turbopack issues, i18n caching, navigation throttling.
ai-content-pipeline
Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS, OmniHuman, media merger, upscaling. Use for: YouTube videos, social media content, marketing materials, automated content. Triggers: content pipeline, ai workflow, content creation, multi-step ai, content automation, ai video workflow, generate and edit, ai content factory, automated content creation, ai production pipeline, media pipeline, content at scale
evolving-skill-creator
A meta-skill framework for creating reusable, evolving workflow plans that improve through iteration, with excellent documentation structure and practical implementation guidance.
Writing Effective Prompts
This skill provides concrete techniques for structuring prompts to improve Claude's responses. It covers role definition, explicit instructions, context framing, XML structuring for complex outputs, and long-document handling strategies. The guidance helps users get more reliable and detailed outputs from Claude.
stream-chain
Provides sequential execution of Claude prompts where each step receives the previous output as context. Offers both custom chains and predefined pipelines for code analysis, refactoring, testing, and migration workflows. Integrates with Claude Flow's swarm and memory systems.
digital-brain
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
book-sft-pipeline
A comprehensive pipeline for creating SFT datasets from books and training style-transfer models with detailed architectural guidance and practical implementation examples.
read-arxiv-paper
Use this skill when when asked to read an arxiv paper given an arxiv URL
github-release-management
This skill automates GitHub release workflows using AI swarm coordination. It handles version bumping, changelog generation, multi-stage testing, artifact building, and deployment orchestration. Includes rollback mechanisms, release checklists, and troubleshooting guides for common release failures.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.