Skill Creation Skill Leaderboard
An agentic skills framework for brainstorming designs, dispatching parallel agents, and standardizing AI-assisted development processes.
A set of engineering skills for domain modeling, architectural design, bug diagnosis, and standards-based code review.
A library of agent skills including API integrations, behavioral nudges, and p5.js generative art capabilities for LLM agents.
A converter that extracts frameworks and principles from documents to create structured skills for AI coding assistants.
Creates reusable Person Profiles from source material about colleagues, relationships, or celebrities.
Tools for designing agentic control loops and deploying iterated coding-agent workflows via GitHub Actions.
A library of agent skills and frameworks for adding specialized capabilities and auditing AI agent outputs.
Provides utilities for managing BB services via CLI and building custom plugins, agent tools, and system extensions.
A set of skills for systematic book study and expert code review focusing on knowledge retention and software architecture.
A set of 40 skills for automating biological data retrieval and genomic variant analysis using AlphaFold, AlphaGenome, ClinVar, and ChEMBL.
A monitoring skill that captures patterns and user corrections during agentic workflows to discover and document reusable AI skills.
A financial analysis skill library for news aggregation, sentiment scoring, time-series prediction, signal tracking, stock lookups, and professional report creation.
A meta-skill for engineering, evaluating, and governing the lifecycle of reusable AI agent skills from workflows and SOPs.
A utility for managing immutable-config workflows to ensure config.json edits and setting changes are properly released.
Authors and structures agent skills according to the agentskills.io spec, including metadata validation and procedural instruction drafting.
An agent orchestration system used to create custom skills and manage GitHub repositories and workflows.
A set of tools for creating and discovering AI skills by analyzing real-world case studies, GitHub projects, and marketplace recommendations.
Provides filesystem operations, Python package management via uv pip, and tools for creating and benchmarking AI skills.
A suite of tools and templates for the creation, review, and governance of custom Claude Code skills.
A collection of skills for AI agents to perform architecture-aware brainstorming, plan execution, and anti-entropy governance in complex codebases.
Captures before-and-after screenshots of web pages or elements for visual comparison and PR documentation.
A collection of tools for creating, simplifying, and auditing AI agent skill files and architectural decision logs.
Optimizes Claude Code skills by running autonomous loops that score outputs against binary evals and mutate prompts to improve reliability.
A meta-skill that captures successful multi-step workflows and project facts from active sessions to create reusable Agent Skills.
Tools for creating, editing, and measuring the performance of AI agent skills through evals and variance analysis.
A toolkit for creating, testing, and auditing agent skills with built-in utilities for duplicate detection and ecosystem maintenance.
Expert knowledge for Azure Active Directory B2C development, covering custom policies, IdP configuration, API security, and deployment patterns.
Restructures oversized SKILL.md files and scattered project rules into a organized directory to improve AI agent routing and maintenance.
Automates the creation of agent-native skills from any software target, with a configurable pipeline and multi-platform packaging.
A meta-skill for researching, packaging, evaluating, and publishing governed Qiaomu agent skills from existing workflows and scripts.
Creates evolving AI replicas of teammates from collected Slack/Teams/GitHub data, combining work expertise and a 5-layer persona for knowledge retention.