Creating Agent Skills for Claude,Cursor and Antigravity

AI skills for SAP SuccessFactors consultants: configuration health, migration readiness, and HR transformation workflows

Rust low-latency Solana arbitrage execution skill for the Solana AI Kit: Yellowstone gRPC ingestion, simulate-first Jito bundles, tx landing, risk/kill-switch. MIT.

A Claude Code skill that turns any YouTube channel into clean, searchable transcript files -- with built-in rate-limit handling.

Build Godot games with a supervised AI team: specialists, independent reviewers, runtime QA, and evidence-gated milestones.

Public Hermes skill export prepared from a private Hermes skill.

137 skills installed. Only 15 get called. Find your blind spots.

Manager + workers skill: Claude directs, Gemini builds. Headless Gemini CLI + Antigravity (Gemini 3.5 Flash) handoff for building premium, non-templated websites.

Turn ordinary self-talk into identity votes, pattern reads, and one high-ROI next action.

44 stack-agnostic, production-grade Claude Code skills — exhaustive sub-atomic audits for security, databases, observability, testing, performance, SRE and more. Auto-discovered, defensive, fixed output format. (Skill bodies in PT-BR.)

Claude Code skill that strips the LLM smell out of prose (EN + RU). Kills AI word-tells, rule-of-three, em-dashes, performative honesty.

Official Model Context Protocol (MCP) Registry API manager skill for AI agents.

A skill and python code to help agents read TensorBoard logs without setting tokens on fire.

Cursor 3 port of OpenAI build-ios-apps — Agent Skills + XcodeBuildMCP for native iOS dev

Agent skills for glim.sh - live data for any agent

A Claude Code skill that teaches Claude how to build skills. Self-installing — clone it and paste one message into Claude Code.

Agent skills for AI coding assistants - starting with a structured architecture decision framework using weighted scoring, context profiles, and iterative refinement.

Startup Agent Skills Hub

🛠️ Dev Kit — lifecycle-driven Agent Skill for structured development workflows. Brainstorm, plan, implement, debug, fix, test & adversarial code review. Java/Spring Boot + TypeScript/React/Vue rules included. Compatible with Claude Code, Cursor, Kiro, and 40+ agentic clients.

Ten Claude skills that encode a design practice: journaling, critique, voice, and a ship verdict. Judgment, installed.

57 agent skills for Claude Code — creative production, paid growth, copywriting, ecommerce, email marketing & knowledge ops. By Novate Studio.

Bridge SwiftUI and UIKit: UIHostingController, representables + coordinators, cells, widgets, and lifecycle migration - Agent Skill

An agent skill for managing and accessing remote machines over SSH or Tailscale

Book-learn-distill + Cursor Skills for PM workflow. Fork to clone PRD gates, issue-ready checks, and skill factory patterns.

Muninn（穆宁）— Skill 练级系统：翻你的历史会话找出每个 Skill 实际掉链子的地方，修好它，并把每次翻车变成测试用例。会话考古 · 五级定级 · 失败铸题 · 红题冻级

Agent Skills.

Rigor for building, in the agent you already use. Validate an idea, grill it into a buildable spec, then build and deploy it. Portable Agent Skills, a Pi package, and a CLI. BYOK, MIT.

Agent-agnostic debug-mode skill with local NDJSON log collection.

Portable Starlight substrate skills for agent runtimes, SIS, ACOS, and cross-agent workflow activation.

TAPD workflow skill with branch-level context memory and a safe tapd-context CLI

Reusable agent skills for Codex, Claude Code, OpenCode, and other AI coding agents.

Set up a feature-based folder structure, scaffold features, and decide where components, hooks, services, stores, and types belong — for Next.js & Expo apps with AI

Portable Agent Skills demo kit: three SKILL.md skills (audience-analyst, vibe-check, meeting-rescue) that run across Claude Code, Cursor, and more — with sample data and live-demo scripts.

Free, portable AI-agent skills that write compliant code (audit logging, access control, encryption) mapped to SOC 2, ISO 27001, PCI-DSS & HIPAA at once. Works in Claude Code, Cursor, Copilot, Gemini & Antigravity.

AI coaches that refuse to do the work for you. Launch Dreams. Start Thriving. Write the book. Launch the business. Run the ultra. Open Agent Skills (agentskills.io) for Claude, Codex, Gemini, Cursor, and more. Free, from Ultra-Normal LLC

Goal-directed session handoff for AI coding agents (Claude Code, Codex, Pi, Grok). Hand a fresh session exactly what it needs to continue — not a lossy summary. Cross-platform, zero dependencies.

A skill that generates skills — interview-driven, portable Agent Skill generator for Claude Code, OpenAI Codex, and opencode.

Non-obvious Swift language & standard-library techniques: value semantics, generics, collections, strings, concurrency - Agent Skill

Agent discovery configuration and developer resources for benmilne.com

Unofficial Claude Agent Skill for designing and safely importing Kahoot quizzes

Two portable agent skills for passing work between sessions: handoff captures troubleshooting/debugging state, pickup resumes from the latest handoff.

Write like a human, kill AI-writing tells, and switch voice register to fit the reader. A Claude Code skill grounded in Wikipedia:Signs of AI writing plus peer-reviewed corpus studies.

Reusable Agent Skills for AI coding agents. Install: npx skills add Tar-ive/agent-skills

docs-first: portable agent skill that consults official docs before answering questions about specific software

Growth skills for open-source repos. Repo audit, README upgrade, demo builder, launch pack, ecosystem inclusion PRs — for your AI agent.

Portable open-source Codex toolkit with reusable skills, custom agents, plugins, project profiles, validation tools, and SDK examples.

Codex skill for bundling installed skills and localizing skill descriptions in Chinese.

An agent skill to migrate a Medium blog or publication to a self-hosted static site

Discover existing community Claude skills and merge the best into one tailored, security-scanned set.

Agent skill for Codex and Claude Code that diagnoses Windows GitHub auth false negatives (HTTP 401, Bad credentials, SEC_E_NO_CREDENTIALS) caused by sandboxes that cannot read the Windows keyring.

My reusable coding-agent conventions and a curated skill set, pulled into any project like a versioned package.

Claude orchestrates; the Antigravity CLI (agy) does the work — web search, downloads, scanning, validation, and first-draft code/UI — on a separate quota, so Claude spends far fewer tokens. Capability-based model routing across Gemini 3.x, Claude, and open-weight models.

Obsidian + Hermes agent intelligence economy kit: clippings harvest, skill optimization, token efficiency, verification, loop scoring.

Agent-agnostic template for a personal knowledge monorepo your coding agents read, write, and maintain: charter-routed sub-hubs, prime/capture/maintain skills, deterministic hygiene loop. AGENTS.md contract + plain CLIs work with any agent.

Public Hermes skill export prepared from a private Hermes skill.

Agent capability that loads only when the task needs it. The Skills layer of QA Veritas.

Run multiple real Chrome browsers on your desktop and drive them from elsewhere, perhaps an AI agent or an LLM CLI

A Claude Code / cross-agent skill for building Flutter apps with feature-first Clean Architecture and SOLID — codegen, 5 state stacks, SDK-aware.