Claude skills for service agencies — scope creep detection, project kickoff, and client handoff. Built and used in production by local marketing and design agencies in Colorado Springs!

my approach to building software, embodied in an agent-centric toolkit

A Claude Code plugin marketplace with skills for git workflows, code quality, safety, and more.

Hooks and skills for Claude to write better code and verify its work, and an easy start to using Claude Code

Turn Claude Code into a long-term collaborator on PostgreSQL internals — cited knowledge corpus, agent skills, slash commands, and task-shaped scenarios for backend hacking.

AI-powered skills for compliance, GRC, and knowledge work — built on the open SKILL.md standard.

TypeScript DDD Clean Architecture Skills

Static React portfolio skill for Claude Code / Codex — turn your context into a deployable personal site in editorial bilingual style. Zero build step.

Collection of Claude skills installable as plugins

Turn research papers into implementation-ready engineering plans and starter code.

Turn Claude Code into a full-lifecycle CTO. 2,388 curated skills, agents & commands. One-command install. Zero cost.

A Claude skill that audits and rewrites prompts. Validated by blind A/B test: 80% pair-level win rate, +5.37 verdict-aligned margin on a 50-point rubric.

Twelve Claude skills, curated by exclusion. Each does what a one-line prompt can't — memory, proof, or a real binary.

Bonusly's Claude Plugin

Debug — Forensic Engineering Agent for Claude Code. No guessing. Only evidence. Reproduce → Isolate → Hypothesize → Test → Fix → Verify.

3 installable Claude Skills for agent tool discovery, AI/ML job search, and enterprise AI research citation.

MaxVision's curated Claude Code marketplace — production-grade skills for n8n workflows, Google Tag Manager API, and more.

A skill that lets an AI agent (Claude Code, Codex, Cursor …) behave like a bug bounty triager and validate your report before you submit.

22 production-tested Claude Code skills: code review, planning, session audits, skill builders, and more.

Experiments in agent-driven video generation — declarative HTML frames with Python TTS narration

Personal fork of claude-code-best-practice with tokyo-time skills, hooks demo, and presentation work

First-pass version of a cross-vendor "steering file" auditor / linter "suite"; immediately runnable via provided scripts using 'claude' CLI. #yourewelcome

Chess puzzles for Claude Code.

First-principles thinking skill for AI agents: break problems into fundamentals, challenge assumptions, and rebuild better solutions.

Step-gated, reference-grounded Claude skills for laser process engineering — DOE for ablation/dicing, diagnostics, and operational SOPs.

Curated Agents skills handcrafted by I Nyoman Darma Kotama.

ACT-Edition brain template for AI coding assistants — critical thinking, epistemic calibration, and structured reasoning

A Claude skill that generates handoff files when your chat gets too long — works for studying, projects, research, any conversational session.

A claude code skill that classifies CLAUDE.md rules by enforcement type

Package a working Claude Code skill into a safe, spreadable GitHub repo: secret + de-personalization gates, README recipe, licensing, distribution.

Collection of Israel-specific skills for Claude Code and other agentic CLIs

Audit and prune Claude Code auto-memory — detects orphans, duplicates, stale facts, and bloat.

Open-source templates, skills, and frameworks for using AI as a personal systems architect.

Checklist público para auditoria de segurança em projetos Lovable + Supabase antes da publicação.

A skill for AI coding agents creating and maintaining a docs-first project memory layer for agentic development.

A Claude Code skill that runs a multi-agent discussion room

One markdown file per target account. Agents read it before every score, email, and call. Every signal compounds. Public Claude Code skill + heartbeat + per-account schema that mirrors your CRM.

nagi (凪): AI agent orchestration framework (remake nanoclaw)

Claude skills organized into domain layers — engineering, product, founder/GTM, design, and documents

The Bubble Shop — free, open-source Claude Code skills & plugins by Bubble Invest. One-command install. We're not developers — we built these to run our own family office. Help us improve them.

A leitura de superfície do Creative Oracle™ — skill do Claude que localiza onde o seu negócio trava (sem prescrever).

A Claude skill that cuts token waste lean replies, smart file reading, zero redundant work

34 Claude Code AI skills for Roblox game development: ideas, Luau architecture, gameplay systems, UX, economy, monetization, security, QA, publishing, and live ops.

Directional, cross-platform, transport-agnostic sync for Claude Code env (settings, memory, plans, skills) driven by an in-Claude skill. up/down/status.

Hub de Skills Thiago Feral

Resumable hierarchical workflow tracking for Claude Code — a Goal->Phases->Tasks tree with first-class forks that spawn sub-workflows and auto-resume the parent. State persists per-project so any session can pick up cold.

5 ready-to-use Claude Skills that teach Claude the operational best practices of working with MCP servers (auth, error decoding, tool routing, schema discovery, rate-limit handling)

A library of reusable Claude Code skills (SKILL.md). Includes setup/troubleshooting guides with human-facing HTML versions.

A curated pack of custom Claude Code skills for developers — installable as a Claude Code plugin marketplace.

Skills library for product data scientists working with Claude

A collection of Claude Code Agent Skills for docs & workflow tasks

llm-wiki

Behavior-preserving codebase cleanup: removes dead code, splits oversized files and classes, and merges duplicated logic without changing behavior.

Free, working Claude skills I use to run an AI automation studio. Drop-in SKILL.md files. By Robin Laires / Laires Labs.

Ship LLM features that work — prompts, evals, agents, and MCP servers.

Audit, test, and scale paid channels with rigorous, data-driven playbooks.

Lightweight suite of skills for managing memory on Claude Code.

Fusion-style multi-agent research skill for Claude Code: spawn N sub-agents in parallel, then Judge + synthesize while preserving the minority I-don't-know vote. 把 OpenRouter Fusion 思路用原生 Agent tool 落地。