4 production-ready Agent Skills for OpenShift AI 3.4 — platform architecture, MaaS governance, AI gateway routing, and inference optimization

Agent Skills for software distribution — apt-setup (Debian/Ubuntu) and choco-setup (Windows), SKILL.md standard

Structured skill for Claude Code that enforces disciplined, product-aware development. 20 anti-patterns, 5-level testing hierarchy, and product thinking framework.

👻 The friendly ghost in your git. Your AI said done — Casper makes it prove it. Claim-evidence hooks + a verdict ledger for Claude Code.

29 Claude skills for designers. UI/UX, brand identity, typography, frontend design, accessibility, and visual storytelling.

Weekly agentic-commerce news briefing skill for Claude Code — scans the past 7 days of X/Twitter, media, and VC announcements for VC-endorsed startups, products, and funding rounds.

Claude Code Multiplexer — Zellij × git worktree × Obsidian

Find out which of your Claude Code rules are actually enforced and which are just hope. Audits CLAUDE.md, classifies every rule, and converts the enforceable ones into hooks and permissions.

Engineering methods for code, agents, and architecture.

Turn a rough idea into a hardened engineering spec: goal-formatter -> goal-spec -> spec-review. Tool-agnostic Claude Code skills.

Public-safe skills and schemas for turning private work evidence into career signal

6 Claude Code skills for GitHub-native developers: pr-respond, release-notes, issue-triage, repo-tour, gh-pr-perm-audit, gh-repo-security-audit

Two free Claude Code skills for the boring parts of shipping software — PR description writer & CLAUDE.md tuner. Free tier of the Deckhand pack.

Live security incident-response & war-room playbook skill for Solana (Solana AI Kit).

Extract Claude Code skills from AI workflow YouTube transcripts. 10 ready-to-use skills + a meta-skill that automates the extraction process. Built from John Kim's 50 Claude Code tips.

A living reference for the Agent Skills ecosystem

Personal Claude Code skills by Santhosh Gandhi — context-manager and frugal-token-usage

Skill that reformats any task into a hand-off prompt optimized for strong autonomous models

Claude Code Skills framework for multi-platform ad operations — Meta, Google, LinkedIn Ads from the terminal / Framework de Claude Code Skills pra gestão de tráfego multi-plataforma

Five Claude Code skills I built and use—stress-test your work, make it leaner, rewrite it stronger, and don't let the model grade its own homework. MIT.

Write specs and handoffs that AI agents can follow — without guessing what you meant. Save your time, write right sepc, plz !!!

10 Claude Code skills for compound engineering workflows — session discipline, harness auditing, phase governance, and issue pipeline

A structured Claude Code setup for learning — mentoring rules, memory system, Mode A/B teaching protocol

AI plugin for coding standards for Go

Agent skills and eval utilities for reward-seeking, grader-targeting, and oversight-dependent behavior.

Dev-focused Claude Code harness — workflow-engine skills, in-repo memory, session continuity (/recall ↔ /vault-push), local telemetry, + a ready-to-fill vault scaffold. clone + ./install.sh and go.

An agent-ready AI Skill and Playwright scraper for extracting live posts, search queries, and child reply comment threads on Meta Threads (threads.net).

Claude skill that fixes LLM coding weaknesses identified by @karpathy, with insights from @bcherny (Claude Code team)

Accelerate server-side Swift development and Xcode Cloud automation with curated knowledge files for Claude Code.

🚀 Sync Claude's todos to Fizzy.do for real-time team visibility, turning tasks into persistent cards to boost collaboration and track progress effortlessly.

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents, branching workflows, memory persistence, human-in-the-loop, multi-agent systems, and production deployment. Supports 14+ AI coding agents via Agent Skill Standard.

Practical New Zealand life skills for international students, especially Chinese newcomers, with official-source-backed guides for Codex and Claude Code.

🏛️ Claude CodeGuard: A Staff-Level Engineering Protocol that mandates deep reasoning over speed. Fixes AI laziness, prevents code omissions, and enforces architectural integrity via P0-P2 escalation and bit-perfect SEARCH/REPLACE.

Claude Code skills marketplace — /claude-md (CLAUDE.md generator) + /learn (compounding self-learning rules)

Claude Code plugin marketplace — Remotion setup skill with Windows support

Claude Code plugins & skills

ex-cog — externalized cognition. Four Claude Code plugins. research-toolkit — self-checking investigation & verification. makers-toolkit — build-discipline & prompt-design. vasana-system — cross-session pattern memory (forms, not just facts). security-toolkit — dangerous-action guardrails.

Claude Code 用プラグイン集（skills, hooks, rules）

Five executable Claude Code skills for building autonomous agent harnesses that don't silently fail — failure-mode auditing, constraint-first CLAUDE.md, sub-agent briefing, context handoff, pre-flight checks.

Provide an MCP server that enables seamless integration and management of SkillsMP data with Node.js environments supporting Model Context Protocol.

Package agent skills once. Install them anywhere.

Specialized Claude Code skills for spec review, design fidelity, feature completeness, and multi-layer testing. Complements the superpowers plugin.

Create a handover summary to continue working on a task on another machine using Claude Code. This is useful because Claude Code’s session resume feature doesn’t work across machines.

BDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.

A Claude skill that decomposes an AI-built or unfamiliar project into learnable knowledge points — so you can explain it, trust it, and own it.

Compact Codex and Claude Code sessions into concise handoff documents for fresh LLM agent sessions.

Claude Code 用プラグインを集めた Marketplace。tech-docs（ADR / 技術仕様書 / 汎用ドキュメントを 1 枚 HTML で生成）と quality-architect（ISO/IEC 25010 でアーキテクチャ設計 / コードレビュー）を収録。

NEO — Claude Code plugin: Matrix-themed 11-agent orchestrator with a second brain that never forgets

OpenAI Codex CLI skill that consults one persistent Claude Code agent for a second opinion — the single-agent, mirror-inverse of codex-council.

Audit web and mobile UI code with AI to detect layout failures, responsiveness errors, and design system drift before deployment.

Compress tokens with caveman, a text simplifier that cuts word count while keeping meaning clear

Manage and switch OpenClaw AI agent presets, including personalities, toolsets, and model configurations, via a simple CLI utility.

An essential layer of Claude Code that makes it efficient and effective.

🎅🏽🧠 An experimental approach to Advent of Code where the entire puzzle-solving workflow is fully automated using Claude Code with custom skills.

Session continuity skills for Claude Code - maintain context across coding sessions

Document-driven development skill for Claude Code.

An IP subnet calculator for on-premises and public cloud (AWS, Microsoft Azure, Google Cloud, Oracle Cloud and AliBaba Cloud), generates Infrastructure-as-Code (IaC) code from web interface command-line interface (CLI) and Claude Skills