Top Agent Skills

Plan and orchestrate multi-slide PowerPoint creation from scratch, classifying each slide type, enforcing visual variety, setting typography/spacing rules, and running text-based QA to catch content issues.

Facilitate structured design critiques with clear feedback frameworks and actionable outcomes.

Specify wireframe layouts with content priority, component placement, and annotations for behavior, responsiveness, and accessibility.

Creates and maintains minimal, high-signal AGENTS.md files for AI coding agents, enforcing research-backed best practices for concise agent documentation.

Provides curated color palettes and font pairings for presentations and design tasks, including a complete design system with color tokens.

Generate structured documentation templates for components, patterns, or guidelines within a design system.

Provides design instructions for creating premium, agency-level visual interfaces with specific typography, spacing, shadows, card structures, and animations.

Redirects pull request creation to the canonical PR writing workflow for compatibility with the legacy skill name.

Design PostgreSQL schemas with best practices for data types, indexing, constraints, and performance patterns.

Generate comprehensive Product Requirements Documents (PRDs) for software systems and AI-powered features, including executive summaries, user stories, technical specifications, and risk analysis.

Create systematic QA checklists to verify that design implementations match specifications across visual accuracy, layout, interaction, content, accessibility, and cross-platform categories.

Generates a comprehensive brand design guide with color palette, typography pairings, UI component previews, and real-world mockups using AI image generation.

Audits Google Ads accounts across measurement, Search, Shopping, Performance Max, Demand Gen, YouTube-linked inventory, keywords, search terms, negative keywords, creative assets, bidding, budgets, settings, and policy.

Discovers and invokes agent skills by mapping tasks to development phases, with core operating behaviors for assumption surfacing, confusion management, and scope discipline.

Discovers, classifies, protects, and governs API keys, tokens, secrets, and credentials across all providers with enterprise-grade security auditing and governance.

Verifies that fix commits properly address security audit findings without introducing new bugs or vulnerabilities.

Generate an llms.txt file from repository structure, following the llms.txt specification to help LLMs navigate and understand the project.

Prevents AI agents from calling methods, imports, or variables that do not provably exist in the user's installed version, reducing hallucinated API usage.

Analyzes stocks using the AlphaGBM Five Pillars framework, returning a composite score, risk assessment, target price, and AI-generated report from real market data.

Run a heuristic evaluation of interactive UIs against Nielsen's 10 usability heuristics and interaction add-ons, scoring the rendered artifact and producing a prioritized fix list.

Guide users through learning new skills or concepts with structured lessons, reference materials, and progress tracking within a dedicated workspace.

Guides database design, implementation, optimization, migrations, data pipelines, and operations for SQL, NoSQL, and modern data platforms.

Provides a structured debugging workflow for analyzing errors, test failures, and unexpected behavior, including root cause analysis and fix recommendations.

Defines the product vision, architecture, pricing, and roadmap for Auri, an intelligent voice assistant built on Amazon Alexa and Claude.

Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures.

Write modern C# code with advanced features like records, pattern matching, and async/await. Optimizes .NET applications, implements enterprise patterns, and ensures comprehensive testing.

Write and review modern Python 3.12+ code with async patterns, performance optimization, and production-ready practices using the latest ecosystem tools.

Guides users through a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs across three stages: context gathering, iterative refinement, and reader testing.

Merges mature lessons from a domain memory file into its instruction file, preserving knowledge with minimal redundancy.

Generate ASCII art diagrams from PlantUML source files for use in terminals, documentation, and version-controlled environments.

Capture screenshots of web apps during development using Playwright and PIL. Supports full-page captures, interactive states, and an iterate-on-crop workflow that avoids slow re-screenshots.

Prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.

Provides best practices for writing JavaScript/TypeScript tests using Jest, including test structure, mocking strategies, async testing, snapshot testing, and React component testing.

Audits project dependencies for supply chain risks including single maintainers, unmaintained packages, low popularity, high-risk features, past CVEs, and missing security contacts.

Edit existing PowerPoint files or templates with XML-safe workflows for template-based deck updates.

Converts HTML content to images using the Composio Html To Image toolkit via Rube MCP, with tool discovery and connection management.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server, returning 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.

Coordinate staged releases across Stripe, Supabase, and Vercel from the shell using the Composio CLI. One script kicks off the whole 'ship it' sequence: product/price updates, DB migrations, frontend deploy, smoke checks, changelog post.

Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.

Build RAG pipelines that combine web search and LLMs for research, fact-checking, and grounded responses using the inference.sh CLI.

Turn rough notes, workshop content, or prompt dumps into compliant, publish-ready SKILL.md files that pass validation and integrate with repo documentation.

Add programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Define and organize design tokens for color, spacing, typography, elevation, and motion with naming conventions and usage guidance.

Establish clear naming conventions for design assets, components, and tokens to make design systems predictable and maintainable.

Generate aerial drone-perspective footage with sweeping bird's-eye views, orbit shots, and flyover sequences for landscapes, architecture, and events.

Load 3D models, textures, and HDR environments in Three.js with GLTF, OBJ, FBX, STL, PLY, and Draco/KTX2 compression support.

Handle user input in Three.js scenes with raycasting, mouse/touch interaction, and camera controls including Orbit, Fly, FirstPerson, PointerLock, Trackball, and Map controls.

Set up 3D scenes with Three.js, including scene, camera, renderer, Object3D hierarchy, coordinate systems, and math utilities.

Generates premium website design images, then deeply analyzes them to implement faithful frontend code for hero sections, landing pages, and marketing sites.

Guide a team through writing a structured, blameless post-mortem after a production incident, covering timeline reconstruction, root cause analysis, impact quantification, and action item generation.

Generate videos with synchronized audio using ByteDance Seedance 2.0 via the inference.sh CLI, supporting text-to-video, image-to-video, and reference-to-video modes up to 1080p.

Create refined user personas from research data with demographics, goals, frustrations, and behavioral patterns for product and UX design decisions.

Write efficient C code with proper memory management, pointer arithmetic, and systems programming best practices.

Automate SEO research with Ahrefs — analyze backlink profiles, research keywords, track domain metrics history, audit organic rankings, and perform batch URL analysis through the Composio Ahrefs integration.

Run SEMrush SEO analytics directly from Claude Code to research keywords, analyze domain organic rankings, audit backlinks, assess keyword difficulty, and discover related terms.

Scores any US stock ticker through Warren Buffett's four-lens framework (business simplicity, moat, management, valuation) and returns a weighted HOLDABLE/WATCHABLE/AVOID verdict.

Guide for continuous improvement, error proofing, and standardization in code and processes. Use when improving code quality, refactoring, or discussing process improvements.

Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure.

Analyze core dumps, debug live processes, and investigate crashes, deadlocks, and memory issues in C/C++ programs using GDB with source code correlation.

Stress-test a plan or design by interviewing the user relentlessly about every aspect until reaching a shared understanding.