Kiro Skill Leaderboard

Audits repositories for over-engineering and aggregates shortcut comments into a technical debt ledger.

Generates multi-platform banners and creative assets using specific art direction styles and platform dimensions.

Converts code, docs, and media into a persistent knowledge graph with community detection for architectural analysis and GraphRAG integration.

A token optimization toolkit that compresses LLM prompts and responses to reduce consumption for coding agents.

Provides AI agents with engineering skills for API design, interface stability, and context optimization to improve production-grade code quality.

A knowledge graph tool for visualizing codebase structures, extracting domain flows, and analyzing code changes.

A frontend design skill for auditing UX, optimizing visual hierarchy, and implementing advanced UI effects and reusable design tokens.

Provides API integration for the Adaptyv Bio Foundry and computational tools for 13C-metabolic flux analysis and protein screening.

A comprehensive catalog of standardized agentic skills for AI automation builders, covering solution architecture, security auditing, and web development.

Generates branded architecture, data flow, and process diagrams including UML, ER models, and user journey maps.

Security workflows for AI agent prompt injection, APK hooking, and Active Directory certificate abuse within sandbox environments.

Implements persistent state management for AI agents using local markdown files to track task plans, findings, and session progress.

A code review methodology that identifies actionable defects by verifying implementation against boundary agreements and forcing violating executions.

SEO automation tools for backlink auditing, broken link detection, competitor analysis, and content planning.

A system for AI agents to distill conversation history into a structured Obsidian wiki for long-term memory and knowledge management.

Technical implementation guides for NVIDIA GPU acceleration, covering cuDF dataframes, dask-cuDF ETL pipelines, and cuOpt optimization.

Migrates Apple/Swift Expo native modules from the 1.0 definition DSL to the 2.0 macro API.

Diagnose-first guidance for Terraform/OpenTofu: identifies failure modes, proposes risk-controlled remediation, and enforces a response contract with validation and rollback plans.

Analyzes existing articles to extract writing style DNA and removes AI-generated linguistic patterns using a rule-based whitelist.

An architecture audit and technical debt assessment tool with automated remediation capabilities for codebase maintenance.

A set of 75 AI agent skills covering game engine integration, NPC AI behavior trees, audio design, and camera systems for rapid game prototyping.

A knowledge engine featuring parallel research decomposition, intelligent thought capture, and a closed-loop V-model verification process for AI tasks.

A design-centric skill for creating cinematic websites and multi-screen product systems with automated visual quality gates.

Fetches timestamped captions and subtitles from YouTube videos via transcriptapi.com for content review and translation.

A tool for auditing and improving website citability for AI search engines using a 47-method engine, robots.txt configuration, and llms.txt generation.

A library of plugins that give AI agents the ability to architect, deploy, and operate AWS services including Lambda, API Gateway, and Amazon Location Service.

Tools for generating platform-compliant ad copy and designing statistically rigorous A/B test plans with sample size calculations.

Provides SVG diagramming conventions for creating architecture diagrams and flowcharts with CJK-friendly typography.

A routing mechanism that transforms underspecified requests into typed IntentSpecs to ensure agent actions align with verified user intent.

Analyzes and rewrites prompts using 31 research-backed frameworks categorized by intent, including agentic and reasoning tasks.

Documentation-first project planner that outputs specification, implementation plan, task breakdown, branding, and a single-shot agent prompt for autonomous execution.