AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
create-squad
Create multi-assistant squads in Vapi with handoffs between specialized voice agents. Use when building complex voice workflows that need multiple assistants with different roles, like triage-to-booking or sales-to-support handoffs.
antv-g2-chart
Create, customize, and troubleshoot G2 v5 declarative chart visualizations with Spec Mode.
game-audio
Game audio engineer using Web Audio API for procedural music and sound effects in browser games. Zero dependencies. Use when adding music or SFX to a game.
competitor-analysis
Benchmark competitor SEO, keywords, content, backlinks, and traffic to uncover strengths to learn and weaknesses to exploit.
agent-ui
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
experience-portal-create
Create new Digital Experience portals and communities in Salesforce with MIAW integration.
rslib-best-practices
Rslib best practices for config, CLI workflow, output, declaration files, dependency handling, build optimization and toolchain integration. Use when writing, reviewing, or troubleshooting Rslib projects.
bundle-splitting
Split large JavaScript bundles to reduce load times and improve FCP/LCP metrics.
tailwindcss
Utility-first CSS framework for rapid, consistent UI design with responsive variants and component patterns.
deployment-engineer
Deployment automation specialist for CI/CD pipelines and infrastructure. Use when setting up deployment, configuring CI/CD, or managing releases.
openclaw-rl-training
Asynchronous reinforcement learning framework that trains personalized AI agents from live conversation feedback.
memory-lancedb-pro-openclaw
Production-grade LanceDB-backed long-term memory for OpenClaw agents with hybrid retrieval and cross-encoder reranking.
agents-best-practices
Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
axiom-shipping
Prepare apps for App Store submission, handle rejections, manage App Store Connect, and triage crashes.
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics
session-analyzer
Validate Claude Code session behavior against SKILL.md specifications post-execution.
react-expert
Authoritative React API research using source code, tests, and git history—not training data.
fusion-rules
Entrypoint for AI coding assistant rule authoring across GitHub Copilot, Cursor, and Claude Code. USE FOR: setting up rules, reviewing existing rules, scaffolding instruction files, or asking which editor format to use. DO NOT USE FOR: authoring skills (SKILL.md), agent definitions (.agent.md), or CI enforcement of rule files.
create-branch
Create and checkout git branches with smart validation and GitHub issue integration
gsap-awwwards-website
SPYLT product landing with GSAP scroll animations, React 19, and Tailwind CSS 4.
markdown-documentation
Master markdown formatting and GitHub Flavored Markdown for professional documentation.
critical-code-reviewer
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
avoid-feature-creep
Keeps changes scoped to what was asked; flags feature creep and moves extras to a suggestions list.
storybook-story-writing
Use when creating or modifying Storybook stories for components. Ensures stories follow CSF3 format, properly showcase component variations, and build successfully.
using-n8n-mcp-skills
Router skill for n8n workflow automation—guides you to the right specialist skill for your task.
mastering-typescript
|
team-assemble
Dynamically assemble and execute specialist teams in parallel for complex multi-role tasks.
snipgrapher
Configures and uses snipgrapher to generate polished code snippet images, including syntax-highlighted PNGs, SVGs, and WebP exports with custom themes, profiles, and styling options. Use when the user wants to create code screenshots, turn code into shareable images, generate pretty code snippets for docs or social posts, produce syntax-highlighted images from source files, or explicitly mentions snipgrapher. Supports single-file renders, batch jobs, watch mode, and reusable named profiles via the snipgrapher CLI or npx.
compression
Reduce JavaScript payload sizes with Gzip and Brotli compression for faster network transfer.
harvard-artifacts-etl-pipeline
Build ETL pipelines and analytics dashboards using the Harvard Art Museums API with Streamlit, SQL, and Plotly