Claude/agent skill: safe deploys when multiple agent sessions share one working tree (wrong-project guard, foreign-edit check, multi-session merge, live provenance verify).

Practical Solana/Anchor security audit workflow skill for the Solana AI Kit (static + manual + dynamic + report); fills the official seed. MIT.

Agent-first Kometa skill library for Codex and Claude: generate, review, and debug Plex automation YAML for configs, collections, overlays, metadata, playlists, defaults, operations, and reports.

Read-only CLI + MCP + skill: AI agents read xXTrade (Hyperliquid perps) markets + positions. No trading.

Production-grade quality skills for AI coding agents: red-first TDD, quality gates, and golden benchmark uplift loops.

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

Skills for driving GlassFlow ETL pipelines from AI coding assistants

AI agent skill for implementing modular, robust software architecture with scoped codebase discovery, clean boundaries, contracts, validation, migration safety, and verification.

A discipline for AI coding agents that keeps a codebase reading as a single authored work across many sessions, models, and thinking budgets. A Claude skill. MIT.

Security & trust vetting for AgentSkills: mandatory open-source scanner gate (Cisco, NVIDIA SkillSpector, Snyk, sentry), OWASP Top 10 for Agentic Applications mapping, and tiered review reports.

Codex skill and plugin for building, reviewing, and testing Java 11 RuneLite external plugins for OSRS with Plugin Hub and Jagex guideline checks.

Claude Code plugin: injects a capability self-awareness card at session start so Claude actually knows and uses its built-in capabilities — skills, subagents, dynamic workflows, hooks, MCP, plugins, GitHub Actions, the Agent SDK, and more.

An agent skill for configuring user's guitar and amplifier to play a certain song

Popperian reasoning agent skill for falsification, risky tests, and error elimination.

Free preview and trusted handoff templates for AI agents: AGENTS.md, SKILL.md, llms.txt, product.json.

Extensive code review powered by Claude Fable 5 — a skill for Claude Code and Codex. Inspired by openai/codex-plugin-cc.

Free Claude Code skill: a scored 10-category production-readiness audit for Python scripts — findings cite file:line, no vague advice.

Codex skill for preventing vendor marketing and SEO drift in software/API/tool decisions

Small, composable Agent Skills for better agent feedback loops, design judgment, and verification habits.

WaitSpin public client source, trust boundary, OpenAPI, and provenance.

Book Author Agent Skills

エージェンティックに動画解析するためのAgent Skills + スクリプト

Claude Code plugins, MCP servers & skills by CodeCrafters Automation. Includes Change Claude Profile (ccp): hand off / take over work between Claude Code profiles (claude-team ⇄ claude-max) and keep their plugins in sync.

Curated agent skills for Cursor — diagnose, triage, commits, workflows.

My curated collection of Claude Code Agent Skills — 21 skills across frontend, Sitecore, AI/agents, devex fundamentals, and personal workflows.

DeepAgents core understandings and developement of advanced ai agents. With memory, skill, tools, subagents, multiagents flow & cababilities etc.

DeepSight 深度推理研究法 v2.5 — 8框架 + 7对抗模板 + 多厂商Council交叉验证。AI驱动的结构化深度研究。

A manual AI session handoff skill that turns the current coding session into a clean Markdown handoff document for the next AI session.

a nightly journal of your AI agent sessions, written in your voice

Practice-built skills that give AI agents practical judgment for product, web, engineering, delivery, go-to-market, communication, and compliance work.

Agent skill for behavior-preserving clean-code refactoring of any codebase, based on Fowler's catalog (refactoring.guru): detect smell -> choose technique -> apply in safe small steps.

Claude Code skill: a phased Production Readiness Review go/no-go gate (reliability, security, operability, cost, observability) with static code probes and a dated PRR record.

Review agent setup files before you run them.

apify-scraper-builder - Claude Code Agent Skill (target LLM: Claude). Part of the mr-bridge.com toolkit.

Token-efficient shared project memory skills for developers and AI coding agents.

Test bench for custom developer-agent skills: SQL schema validation, Conventional Commits formatting, JSON-to-Pydantic conversion, and license-header injection.

Agent skill to integrate Graphify knowledge graph into any project

Agent skill for implementing WebMCP on websites — expose app features to browser agents via document.modelContext.registerTool(). Install: npx skills add Blackie360/webmcp-skill -g

Runs a documentation site like a product: audience & IA → Diataxis-structured docs-as-code repo → auto-generated API reference → CI doc-drift gate → publish, with verification at every step.

Ditsmod Agent Skills

Reusable AI agent skills for knowledge projects: ingest PDFs, wikis, and reports, extract structured entities, and build a navigable knowledge base (wiki) your agents can query.

A monorepo of agent-agnostic AI skills for Claude Code, Codex, Gemini CLI, Devin, and more

Make recurring AI-agent automations behave like reliable operators, not stateless prompts — persistent memory, run ledgers, concurrency locks, approval gates, and coordinated suites across Codex, Claude Code, Gemini CLI & Cursor.

Public Agent Skills built to the agentskills.io specification — start with terminal-poster (5-cluster reusable infographic system).

Designs, implements, and adversarially verifies an application's authorization + tenant-isolation model — closing the IDOR/broken-access-control gaps that are the #1 web vuln.

Drives high-risk major-version and framework upgrades across a large codebase as a dependency-ordered, codemod-first campaign with a per-step green-build gate and a resumable ledger.

The money layer for AI agents on Solana — pay and get paid via x402 (USDC) behind enforced, non-custodial spending limits. A Claude Code / Codex skill for the Solana AI Kit.

Skills and connected MCP server documentation exported from my agent.

scraping-expert - Claude Code Agent Skill (target LLM: Claude). Part of the mr-bridge.com toolkit.

Opinionated, cross-agent rules and skills for AI coding agents — one npx install into Cursor, Claude Code, Codex, OpenCode & Copilot.

Standalone governed Kubernetes ops — 15 MCP tools with built-in audit/budget/undo/risk-tier harness

Agent Skill for reviewing prompts, context packages, and Agent Skill bundles for structure, clarity, and practical quality risks.

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for PyMeasure, Python instrument control & measurement automation: Instrument/Channel base classes, manufacturer drivers (Keithley, Agilent, Lake Shore, Tektronix, +more), VISA/serial/Prologix/TCP adapters, and the Procedure/Experiment framework.

Evidence-backed topic radar for choosing what Agent Skill to build next.

Code Performance Optimizer Skill helps developers improve backend and API performance with structured optimization, Big-O analysis, and security-first guardrails. It identifies bottlenecks, ranks improvement opportunities, and guides production-safe changes that preserve reliability, security posture, and scalability

Codex plugin for Primitive — email infrastructure for AI agents

Agent Kaizen skill for Claude Code & Codex: faithful GIMP 3.2 reference (GNU Image Manipulation Program), layers, blend modes, masks, channels, selections, Bézier paths, levels, curves, ICC profiles, .xcf/PNG/JPEG export, and scripting via Script-Fu, Python-Fu & the PDB, including headless batch and GIMP MCP server runs.