Cross-tool AI agent skills (SKILL.md) for Claude Code, Codex, Gemini CLI, Cursor & Copilot

Curated Claude Code plugins by Digital Pine. Framework setup, auditing, and modernization skills.

M&A Engineer Agent Skill for Claude Code — 9 DD workstreams with Python automation

Claude Code skills to bootstrap, compact, and maintain AI-readable project documentation — doc-init · doc-compact · doc-update

Universal config layer for Agent Skills — add global & project-scoped preferences to any skill via a single SKILL.md declaration. Compatible with Claude Code, Codex, Gemini CLI, and Cursor.

Senior Product Manager AI agent for Claude Code: discovery interview, codebase-grounded PRD with testable FR/NFR, dependency- and risk-aware roadmap, and opt-in epic-by-epic implementation with adversarial verification.

Lightweight Claude Code skills for daily AI-assisted development workflows.

Battle-tested Claude Code skills — audited and refactored using skill-forge. PySide6, network discovery, Windows CI/CD, mass-deploy UX.

Public repository for Agent Skills

Agent Skill that asks: should there be an agentic system at all? Then designs, builds, audits, verifies, and ports systems—from workflows to governed teams.

Curated collection of production-grade skills for Claude Code

Proof-carrying defensive security reviews for AI-assisted software, with deterministic policy, portable evidence, and human review required.

Make your AI coding agent argue with itself before writing code. A model-agnostic SKILL.md for engineering decisions.

Open-source AI Skills library for building, improving, and scaling modern SaaS applications.

Vault-first toolkit for Claude Code — curated plugins over an Obsidian-compatible knowledge vault, governed by an explicit contract, gated by evals, continuously delivered.

Cut Claude Code's own token consumption by up to 99% — delegate the heavy lifting to free opencode agents, keep Claude in the reviewer's or manager's seat.

A Claude Code skill for structured end-of-session handoffs — 7-section chat summary so a fresh agent can continue without losing context

Symmetric multi-agent build with mandatory cross-review for Claude Code + Codex. Splits coding tasks ~50/50, runs in parallel in isolated worktrees, has the opposite model review each diff.

A theory-first skills repository

A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.

A GitHub action to create and publish zip files for Claude/agent SKILL.md directories

Graduate admissions workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.

Reconstruct a full flight itinerary from unordered segments — Go/Echo REST API with Swagger, fuzzing, Newman E2E, cosign-signed multi-arch images

Tested recipes for Claude skills and hooks — methodology documentation, failure modes, and honest assessments. Not another awesome-list.

🤖 Automate Azure ML finetuning with the LLM skill. 🔧

Sample/PoC Claude plugin marketplace

The always-on operating system for Claude Code, Cursor, Codex CLI & beyond. 30+ frameworks, 8 core principles, 1,326+ skills catalog, 500+ MCP servers. One skill to rule them all.

Guide mycology research workflows using WeMush's MCP server for specimen tracking, research projects, cultivation analytics, and strain catalog exploration.

An agent Skills plugin for the Declarative Action Architecture (DAA). This plugin transforms Claude into an expert in the Declarative Action Architecture (DAA), offering four core capabilities.

An Agent Skill of Modellix documentation and capabilities reference.

A collection of skills / commands for Claude Code

EN: AI skill that converts web apps into Electron desktop applications. Generates main process, preload, icons, installer config, and build pipeline. ES: Skill de IA que convierte apps web en aplicaciones de escritorio Electron. Genera proceso principal, preload, iconos, configuración de instalador y pipeline de build.

Community marketplace of Claude Code plugins: DevOps skill packs (Terraform, Kubernetes, CI/CD, cloud platforms, DigitalOcean), CLAUDE.md optimization, and diagramming — gated by a best-practices lint + security-audit CI.

My personal directory of AI Agent skills

Claude Code Skillforge — The skill that builds, upgrades, and scans skills. Generate and upgrade Claude Code & Antigravity SKILL.md files with live best practices sync, marketplace search, skill upgrader, skill scanner, and self-validation — in minutes.

Agent Skill Depot — public skills social network for Claude agents. Publish, discover, install, and rank Claude skills by how much work they offloaded. Cloudflare Workers + Neon + pgvector + R2.

Claude Code skills for QA engineers. Built by practitioners, not vendors.

Azure apps that cost nothing when nobody's using them. A Claude Code skill pack — 14 composable skills, 37+ documented gotchas, branch-per-env CI/CD.

Curated Claude Code plugins by Knitli

Agent skills for TokenLab API integration, model picking, native endpoints, cost routing, and OpenAI-compatible migration

Tactical pipeline for AI-assisted coding: /design, /plan, /prebuild Claude Code skills. Pairs with /think from blooms-ai-collaboration.

SearchLens is a Google Search & Bing data analysis skill. When you drop GSC or Bing Webmasters exports, keyword CSVs, or ranking reports into the conversation, I'll automatically run a structured analysis instead of just describing the data.

A solo studio for growth operators — skills, playbooks, templates.

Reusable AI skills for Claude Code and GitHub Copilot — scan READMEs, sync forks, create skills, lint Python, and scan for security vulnerabilities

I will guess build and use one simple agent ai

Some Claude Code skills created and used myself.

11 systematic skills for Claude Code — structured protocols for debugging, code review, security, refactoring, testing, deployment, and more. No vibes, just discipline.

Production-ready Claude Code skills — code review, commit messages, PR descriptions, spec-driven dev, and context management

Skill that supports Opentrons dev env setup

Skill for analyzing, assessing, and prioritizing technical debt.

Claude Code skill that will generate interactive documentation for your project

Apcore ecosystem management skill for Claude Code. Handles cross-language SDK synchronization, framework integration scaffolding, multi-repo audits, coordinated releases, and documentation alignment.

Forensic codebase analysis. 16 diagnostics, health score, architecture map, complexity heatmap, risk matrix — all in one interactive HTML report.

openclaw-memhealth: Memory health monitor for OpenClaw — diagnose, guard, and remediate your agent's memory.

Codex/Claude Code-native workspace for analyzing local data files and saving reproducible notes, SQL, and charts.

A complete Remotion video production automation skill for creating product promotional videos

Expert Claude Code skills for building Tracecat SOAR workflows — action configuration, case management, workflow patterns, integrations & MCP tools guidance

Stop analyzing code manually. Understand your codebase, review changes for safety, find performance issues, or plan implementations with surgical precision. 4 modes, zero setup, complete confidence.

A powerful Famulor skill for seamless integration and automation of the Famulor AI platform.

A Codex skill that builds tiny task-specific CLI tools on demand when the model cannot directly access the data it needs.