154 packages found
4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands
A Claude Code skill that encodes battle-tested editorial principles, section-specific rhetorical moves, and a structured
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your cl
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
AI-powered code review CLI with multiple providers (Gemini, Claude, OpenAI). Features 95%+ token reduction via semantic
B2B software vendor evaluation skill for Claude Code — domain-expert questions, vendor AI agent conversations, evidence-
A curated system of production-ready Claude Code skills with quantitative evaluation reports, golden test fixtures, and
Academic Research Skills for Claude Code: research → write → review → revise → finalize
@anthropics✓ OfficialThis repo contains detailed implementation information about Anthropic's paired prompts approach for evaluating politica
Production-ready Claude Code skills for building AI agents with Pydantic AI. Includes dependency injection, tools, valid
Claude Code skill for PaperBanana - Generate publication-quality academic diagrams with AI
A Claude Skill for scoring B2B website visual quality across 5 conversion-focused dimensions
AI Creative Director skill for Claude, GPT, Gemini — 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER), Cannes-calibra
A Claude skill embodying a 30-year veteran ID practitioner — 15 engagement modes, 31 reference files, full L&D spectrum
A powerful Rust library and CLI tool to unify and orchestrate multiple LLM, Agent and voice backends (OpenAI, Claude, Ge
Claude Code skill for Xcode SwiftUI workflow auditing
A Claude Skill that coaches you to write better coding prompts before implementing — evaluate, clarify, plan, code, revi
Claude Code skill for benchmark research. Survey papers to find datasets, metrics, and evaluation protocols used in a re
@anthropics✓ OfficialBenchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation
Evaluate and compare technology stacks — pros, cons, fit analysis
Autoresearch ALL THE THINGS. RLVR for the masses.
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads, notebook e
@anthropics✓ OfficialA Nix plugin that resolves Cargo workspaces natively and allows for crate level builds
AI design thinking framework with four roles (Strategist, Researcher, Executor, Critic) for Claude Code. Domain-agnostic
Agent Skill: TYPO3 extension conformance checker - validates against official standards | Claude Code compatible
Claude Code skill: Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a supreme judge
OpenCode skill for creating, testing, and optimizing other OpenCode skills. Adapted from Anthropic's skill-creator for C
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
10 applied skills for Claude Code and Cursor that turn the principles of Refactoring UI into structured AI-assisted desi
Production-tested commands, skills, and workflow patterns for Claude Code. Developed through 6+ months of daily use. Inc
@microsoft✓ OfficialSkills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
Agent-Native CLI design & review skill — design CLIs that serve humans, AI agents, and orchestration systems simultaneou
Systematic thesis review skill for AI coding agents — supports all disciplines (7 modules: life sciences, medicine, CS/A
Interview debrief skill for Claude Code — transcribe recordings, organize Q&A, generate evaluation, sync to Feishu docs
中文苏格拉底式一对一 AI 家教 · 基于 Bloom「2 Sigma」研究的交互式学习系统 | Socratic AI tutor as a Claude Code skill — teaches one lesson at a time
Teams-first Multi-agent orchestration for Claude Code
一个基于 Project Context 进行 Prompt优化 的 Claude Code SKILL，并配置有界面进行迭代优化；Advanced Claude Code skill for systematic prompt engin
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide.
VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Y
Claude Code plugin that replaces native tools with token-efficient precision equivalents. 75 MCP tools, 11 specialized a
@anthropics✓ OfficialRust implementation of protobuf with editions support, JSON serialization, and zero-copy views
A curated collection of battle-tested prompts for agentic coding - Browse, copy, and install as Claude Code skills
Claude Code skill for automating UI prototyping with Google Stitch via MCP
Professional skills for Claude AI — 167 skills across 17 professions. Save 8-10 hours per week. PM stands for Profession
The definitive UX/UI design mastery plugin for Claude Code — 19 skills, 55 references, 10 commands, 310K+ words
Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches
Premortem skill for Claude Code — finds the concrete ways a plan could fail before commitment. Multi-agent silent scan,
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - that works w