CI/CD pipeline skill — build status, logs, reruns, deployments via mcp-cicd

A Claude skill for honest synthetic customer discovery: grounded personas, anti-collapse interview rules, and outputs that tell you what to verify with real humans. No API keys, no backend.

Run a qualitative focus group on your MVP using N synthetic personas. A Claude Code skill — discovery-grade, honest about its limits.

Installable library of AI coding agents, skills, commands, guides & tools — the copy-paste mirror of agentscamp.com

Claude Code skills for genuine property-based testing: discovery workflow, anti-patterns, Hypothesis & beyond.

LLM agent skills for software architecture analysis and review. This repository equips AI agents with reusable capabilities to evaluate system design, review architecture decisions, identify risks, analyze trade-offs, and recommend improvements for scalable, reliable, and maintainable systems.

A Claude skill for developing creative art and technology project ideas — computational, generative, algorithmic, data-driven, or web-based. It works as a structured creative partner, not a shortcut to automate creativity.

Free MIT Claude Code skills: clarify rough ideas and scaffold your first skill.

A Claude Code skill: spawn 5 independent agents to stress-test high-stakes decisions and fight AI sycophancy. Inspired by Karpathy's LLM Council.

The SQL cost & performance audit skill for Claude Code. 20 rules, scores warehouse health 0-100, outputs a prioritized cost-reduction plan for BigQuery/Snowflake/Redshift/Postgres. Zero deps, MIT.

Triteme: a Claude skill for professional messages humans actually read (WhatsApp, email, Slack).

UK construction Claude Skills pack. Site diary, RAMS, CDM 2015, CIS, NHBC. Built by ConstructionX AI.

The definitive Claude Code setup skill. Run /forge to generate CLAUDE.md, settings.json, skills, hooks, agents, commands. 45 reference modules, 25 hook recipes, 12 agent templates, 20 commands, 10 CLAUDE.md examples. Zero dependencies. Educational and experimental.

Tabletop RPG Dungeon Master assistant skill inspired from the BMAD method. From worldbuilding to session planning, managed with a markdown file memory system, Obsidian compatible & RPG system agnostic.

A flexible Claude Skill for the full product & software development lifecycle

🚀A full-stack AI app builder methodology for Claude and other LLM agents. Zero-code to production.

Ralph skill for Claude Code

Claude Code skills I built so I'd stop forgetting where I left off. Sharing in case you need them too.

Cicada — Security Audit & Fix Skill for LLM coding agents (16 domains, cross-framework)

Multi-LLM Plan and TDD flow

/my-skills — Claude Code skill that maps ALL your local AI prompts & skills (Claude, Cursor, ChatGPT, or any folder), detects functional overlaps, and helps you decide what to delete.

A month of on-brand posts, repurposed everywhere, in an afternoon.

Governed payment skill for AI agents — intent-based payments with approval gates, evidence, reconciliation, and audit trails via mcp-payments for ADK-Rust Enterprise

Hermes Loop Engineering skills for self-improving AI delivery governance.

A curated collection of Claude Code skills, packaged as an installable plugin marketplace.

Claude Code plugin: turn bugs in your dependencies into upstream contribution PRs — without leaving your project.

Reidworks skills marketplace — install once, every shared skill loads in Cowork and Claude Code.

⚡ Native prompt-layer semantic compression engine for Claude. Squeezes agent contexts, logs, and prompt buffers by 60–70% using a programmatic dual-ratio (lossy/lossless) compaction skill. Maximize window efficiency, minimize token cost.

Claude Code skill that rules whether your next release is legally a patch, minor, or major — by diffing the actual public API surface against the last published version, exact breaking symbols named. 👮

IntelliJ plugin for creating and validating Codex, Claude and Gemini skills inside a project.

AI dev infrastructure framework for Claude Code. /dotclaude:bootstrap authors CLAUDE.md + docs/ + .claude/ tuned to your project. Per-domain: design (showpiece), coding, planning, testing, data, ai-workflow.

Companheiro executável de Deep Claude · O Currículo Executivo do Ecossistema Anthropic

Curated Claude skill pack for structured product discovery

For creators: turn expertise into a course and launch it to your list — outline to open cart.

Distilled Claude skills for Marvis — my personal toolbox of focused agent capabilities.

Search your claude context and provide rich outputs

Move old code to modern stacks without a risky big-bang rewrite.

A Claude Code skill that turns a raw screen recording into a polished, cropped, captioned social‑media clip — shot list to final render, no timeline scrubbing required.

One-paste Claude setup that turns Claude into an institutional multifamily research & underwriting teammate for Bristol Development Group — zero-config, fully cited, self-evolving (V1→V2→V3).

Multi-channel notification skill — push, SMS, email, in-app, templates, preferences via mcp-notifications

Test execution skill — unit, integration, E2E tests, coverage, and failure analysis via mcp-test-runner

Solid State Skills Directory and Marketplace

SKILLs for ai tools

Agent Skill that turns your Google Maps saved places into a personal dining knowledge base and gives taste-matched eating-out advice.

My collection of agent skills.

Official FastBound Agent Skills for AI coding assistants — integrate with FastBound's products and APIs.

Production-oriented template for building AI agent skills as verifiable software components — offline eval harness, source-grounding validators, structured logs/traces/metrics, replay artifacts, and a CI quality gate. Runs fully offline with a deterministic mock model.

A Claude Code skill that generates brand-consistent visuals (posts, carousels, stories, infographics) — with OpenAI's gpt-image-2, and refuses to make AI slop. Zero dependencies, pure Python.

Eight portable SKILL.md playbooks that make coding agents work like careful senior engineers. One-command install across Claude Code, Codex, Antigravity, OpenCode, Copilot, and Cursor.

Claude Code plugin marketplace: a set of domain experts (subagents) grouped into installable plugins.

Turn messy context into a brief you can think with for Claude and Codex.

Agentic project base: Claude Code skills bootstrap and evolve your project, a deterministic Python CLI verifies it. project.yaml manifest, doctor checks, path linting. A project-template alternative for coding agents.

Agentic CLI tool skills for Claude Code — 7 domain-grouped skills covering 26 CLI tools

A findings-first audit -> fix -> verify -> push skill for Claude Code.

Curated open-source AI Agent Skills built by and for GMBA Class 19. Drop-in compatible with Claude Code, Codex, Gemini CLI, Cursor, and any tool that supports the Agent Skills standard.

Let agents write structured readmes

An automated Python linting and refinement utility that enforces clean code principles and provides auto-fix suggestions for readability violations

AI가 생성한 흔적을 제거하고 사람이 이해하기 쉬운 문체로 바꿔주는 스킬

AI coding-standard skill for ML/DL research repos — keeps a fixed architecture intact and enforces uniform structure, naming, configs, FAIR data, and review via machine-executable Rule Cards.