agent-skills
Walks a software change from a written spec through design, testing, code review, CI/CD, and release, applying the matching engineering skill at each stage. Useful for developers using Claude Code on full development workflows.
Flowy lists 112 plugins for GraphQL work in Claude Code. Each one bundles skills a Claude Code agent can load while you work. Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
Walks a software change from a written spec through design, testing, code review, CI/CD, and release, applying the matching engineering skill at each stage. Useful for developers using Claude Code on full development workflows.
Gives your app a hosted Postgres database with built-in auth, auto-generated APIs and file storage, and the explorer skill helps you build Studio surfaces like SQL snippets, notebooks and query cells.
Skills and an MCP server for Storybook, the tool for building, documenting, and testing UI components in isolation. Covers canary releases, docs review, PR comment handling, lint and type fixes, and QA labels.
A library of installable SKILL.md playbooks for AI coding agents, covering areas such as security audits, presentation generation, project analysis and planning. Users can browse the skills, review their full files and assemble an exact set to reuse in a project.
A library of installable SKILL.md playbooks for coding agents, covering security audits, presentation generation, planning and niche research. Users can find reusable instructions for a project, inspect the full files, and keep a set they can review and reuse.
Gives Claude Code a Payload skill for working with Payload CMS projects, covering collections, fields, hooks, access control and the Payload API, plus commands for dependency audits, CI flake triage, test conversion, UI review, issue triage and translation generation.
A skill pack for authorized reverse engineering, security research, and penetration testing that routes tasks to the right skill and sets up needed tools on demand. It covers API security assessment and Android APK analysis, among others.
Ready-made configurations for Claude Code, with AI agents, custom commands, hooks, MCP integrations, and skills for agent management, agent messaging, documentation search, code graph queries, and memory search.
Skills, agents and an MCP server for Phoenix, an AI observability tool. Helps build evaluators, run dataset experiments, manage prompts in the playground and query the Phoenix API.
Gives Claude Code users network observability for Kubernetes clusters, with skills for installing Kubeshark, writing its filter language, root cause analysis of past incidents, and security audits, backed by an MCP server for AI agents.
A plugin of skills for everyday development work in Claude Code: analyzing GitHub Actions failures, cloning the later half of a conversation to save tokens, writing handoff documents for the next agent, summarizing Hacker News threads, and searching all of your GitHub repos, including private ones.
A Claude Code skill that decompiles Android APK/XAPK/JAR/AAR files and extracts the HTTP APIs used by the app, Retrofit endpoints, OkHttp calls, hardcoded URLs, authentication patterns, so you can document and reproduce them without the original source code.
Open-source content platform. Self-hosted on AWS serverless. Built as a TypeScript framework you extend with code, not a closed product you configure through a UI. Runs on Lambda, DynamoDB, S3, and CloudFront inside your own AWS account. Scales automatically.
A terminal pair programmer that brings AI help into your coding workflow, with ready-made skills for pull request descriptions, executing structured task plans, and creating new skills. Works with many AI models, so you can keep working where you already work.
Runs recon on a target, tests it for real, reportable vulnerabilities, checks each finding against a strict validation gate, and writes a report ready to submit to bug bounty platforms. It also remembers patterns across targets and resumes unfinished sessions.
A Claude Code plugin for bug bounty hunters, bundling skills for reconnaissance, vulnerability hunting such as IDOR, SSRF and XSS, black-box audits of deployed AI agents, and CI/CD pipeline security.
A self-contained bundle of Claude skills and slash commands for bug bounty hunting and external red-team work, covering recon, Android APK analysis, and vulnerability reporting for Bugcrowd and HackerOne.
Generates, polishes, reviews, amends and publishes command-line tools for AI agents, so they can run with fewer wasted steps and tokens. Includes skills for importing and publishing CLIs from a shared library.
Gives Claude Cowork and Claude Code users a shared place to pick up extra abilities for jobs like simple topic explainers, interactive plans, AI media generation and Playwright test audits. Each one is a ready-made add-on, so you skip building the tool yourself.
Runs multi-AI workflows in Claude Code that split research, requirements scoping, implementation and review across several external AI providers, such as Codex, Gemini-style CLIs, Copilot, Ollama and OpenRouter, to cover each model's blind spots.
Gives your coding assistant Go-specific guidance on benchmarking and profiling, CLI app design, code style, concurrency, and context handling, loaded only when a task calls for it. Built for Claude Code, Codex, Cursor and similar tools.
Gives a research agent ready-made skills for genomics, protein structure and chemistry, such as reading AlphaFold confidence scores, estimating how a genetic variant affects gene activity, and looking up bioactive compounds and drug targets in ChEMBL, so you skip building these lookups by hand.
Agent Skills to help developers using AI agents with Supabase. Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently.
A set of Claude Code skills for open-source intelligence work, covering attack-surface discovery of cloud storage buckets, continuous exposure monitoring, email domain spoofability checks, secret detection, and risk scoring of recon findings for security teams.
Gives an AI agent offensive security playbooks for authorized testing, covering web and API attacks, Active Directory abuse, privilege escalation and reverse engineering. Use it for step-by-step attack guidance during bug bounties, pentests and CTF challenges.
Turns any MCP, OpenAPI, or GraphQL server into a command line tool at runtime, so you can call its endpoints without generating code.
Lets an AI assistant work with GitLab directly, reading and acting on merge requests, issues, pipelines and repositories without you switching to the web interface. Review a merge request file by file or check a failing pipeline from the chat.
Helps solo founders and indie makers with marketing work by generating banners, logos and images with AI, finding domain names and deals, and archiving session notes and debugging fixes. Skills work in Claude Code, Cursor and Codex.
Gives Claude Code a ready-made specialist for each part of a development job, such as code review, security audits, QA automation and performance work, so you can hand off a task to an expert persona instead of prompting from scratch each time.
Helps Rust developers in Claude Code with code style guidance, ownership and unsafe checks, code review, crate research, and learning Rust, through skills, agents, commands and hooks.
A Rust development assistant for Claude Code with skills, agents, commands and hooks for code style, ownership, concurrency, error handling and refactoring, plus research on Rust docs and crates.
A skill that helps Claude write secure web applications and runs security scans or audits, applying bug bounty experience to catch vulnerabilities before code reaches production.
Turns your coding assistant into a security scanner that checks your codebase for vulnerabilities such as business logic flaws, insecure file uploads, GraphQL injection and hardcoded secrets, without any third-party tools. Works with Claude Code, Codex, Cursor and other agent-skill assistants.
Gives a development team ready-made commands and agents for code review, testing, releases and deployment, plus skills for transcribing audio, extracting video frames and managing Cloudflare or BigCommerce work.
Skills for building and running Twitter/X agents, each with its own personality, storyline, and library of post images. Aimed at builders who want automated social media accounts.
Helps AI coding tools build, audit, debug and deploy Salesforce Agentforce agents, and trace live agent sessions to see what went wrong. Each job is handled by its own focused skill.
Gives AI coding tools Salesforce skills for building Agentforce agents, Flow, Apex, SOQL and Lightning apps, so they can build and debug those parts of an org with less hand-holding. Works with any AI tool that supports skills.
Skills for working on the arcade-mcp Python framework, which builds MCP servers and tools. They cover writing new error adapters for provider integrations and preparing changes for review by filling the repository PR template.
A bug bounty agent framework for Claude Code that automates reconnaissance, vulnerability hunting and exploit chaining, with skills for analyzing recon output, running autonomous hunt loops and correlating findings into attack chains.
Manage UniFi Network, Protect and Access from Claude Code, with skills for setting up the UniFi Access server, investigating device incidents over a set time window, reviewing area activity, and preparing sanitized support bundles for bug reports.
Lets you list, start and create Linear issues from the command line without leaving your repo. It reads your git branch or jj commit to find the right issue, and can open the issue in the web or desktop app.
This repository contains the source code, examples, and project implementations for the book "Hands-on AI Agents", a practical, code-first guide to building AI agents and, more importantly, putting them into production.
A workflow plugin that takes a bug, idea or ticket to a pull request, with specs, cross-model review, live QA and records kept in your repo. Works across several coding agents.
Flutter and Dart skills that a coding agent loads on its own, covering architecture, Bloc state management, Dart idioms, accessibility, and code review. Each skill is a folder with a SKILL.md file.
An open source X/Twitter automation toolkit with an MCP server for AI agents, a CLI and browser scripts. It covers account backup, scraping, analytics, unfollow management and engagement automation.
Interact with a Marmot data catalog from Claude Code to search data assets, view lineage, browse glossary terms, check pipeline runs, and manage tags and owners. Gives AI agents access to catalog metadata for tables, topics, queues and APIs.
Gives AI coding agents access to Shopify's developer documentation, API schemas, and code validation for building apps and themes, plus store management through the Shopify CLI. Also includes a skill for finding and buying products from UCP merchants.
Gives Claude Code a team of specialized agents that plan, build, review, test and learn from past mistakes, so you can hand off a whole software task instead of directing each step yourself.
Automatically generates production-ready skills for software, APIs, CLI tools, libraries, workflows, or services, so AI agents can use them. Includes eval testing and packaging for multiple agent platforms.
Builds reusable agent skills from a short brief by filling in the requirements it leaves out and pulling working procedures from public docs, repositories and papers. It then packages the admitted procedures as installable skills you can reuse.
Lets AI agents read and update your monday.com boards and CRM records directly, so you stop copying data between tools. Ready-made skills cover morning briefings, sales forecasts, rep activity reports and data cleanup.
One Java engine for web, mobile, API, CLI, database, and desktop. Drivers, waits, and evidence are handled. Every run ends in an Allure report.
Gives Claude Code and Codex a repeatable development process for planning, reviewing, and shipping changes, so you stop rebuilding the same prompts each time. It also captures corrections and project conventions so future sessions build on what you have already learned.
Helps a bioinformatics or biostatistics analyst run common analyses in Claude Code, from Bayesian models and survival analysis to statistical tests with reporting and regression. Each analysis is guided step by step instead of built from scratch.
Coordinates multiple Claude Code agents to run tasks in parallel, with automated quality gates, a simulated expert board for major decisions, and planning and code-review workflows. Aimed at developers building larger multi-step projects.
Gives you ready-made prompts for common work such as testing, access control and sprint planning, so you can get expert-style help from an AI assistant without writing the prompt yourself.
A Claude Code plugin that adds skills, agents and hooks for development work. It can create API endpoints, backend and frontend tests, database migrations and React or Vue components, plus planning and release tasks.
Navigator is a Claude Code plugin for planning and delivering features across sessions. It adds skills to create API endpoints, database migrations, React or Vue components, and backend and frontend tests, plus agents and hooks for workflow orchestration.
Compiles and searches API specifications such as OpenAPI, GraphQL, AsyncAPI, Protobuf and Postman into a format AI agents can read. Useful for looking up endpoints and generating reference docs.
A Claude Code plugin for penetration testing and bug bounty work, with skills for driving Burp Suite, triaging proxy history, testing Active Directory attacks, and running responsible disclosure to a CVE.
Compiles scattered markdown notes or an entire codebase into topic-based wiki articles that an AI agent can read, reducing context costs. Works as a Claude Code and Codex plugin.
Resolves review comments on the current pull request. It fetches unanswered comments from review bots or human reviewers, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment.
Reverse engineer clean behavioral specs from any codebase. Greenfield reads source code, documentation, SDKs, runtime behavior, and binaries, then produces behavioral specifications, test vectors, acceptance criteria, and a full provenance trail.
A universal OpenCode workflow setup with specialized agents, skills, commands, and plugins for any software project.
Gives an AI agent live sports scores, standings, schedules, play-by-play and win probability for college basketball, college football, cricket and other leagues, plus odds math for betting analysis. Read-only data with no API keys or signup needed.
A guide to working with Claude Code in real development work, with patterns for using it from the terminal. It also bundles a skill that keeps git commit messages in a consistent conventional format.
Claude Code skills and agents for QA automation engineers, covering accessibility testing with Playwright and Selenium, REST and GraphQL API tests, live browser control from the CLI, and test strategy review.
Clone, commit, diff, branch, merge, rebase, cherry-pick, stash, tag, and manage worktrees in local git repos via MCP. STDIO or Streamable HTTP.
Generates Python command-line tools for web apps by capturing their HTTP traffic, and ships ready-made CLIs for sites such as Airbnb, Amazon, Booking.com, ChatGPT and Capitol Trades. Each comes with skills that let Claude Code run them from the terminal.
A plugin for Claude Code that gives coding agents Symfony expertise, covering API Platform resources, DTO mapping, filters, security and serialization for REST and GraphQL APIs.
An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks, from code review to AI agent security audits.
A comprehensive ecosystem of 76+ specialized AI agent personas designed to work seamlessly with Claude Code's Task tool, providing expert-level assistance across the complete spectrum of business and technical challenges.
Gives a Shopify store owner AI agent skills and scheduled routines that watch inventory, fraud, fulfillment, finance and customer health without manual checks. It also prepares the store for AI shopping assistants by fixing crawler access, product descriptions, image alt text and product metafields.
A GitHub CLI extension that lets you view and manage inline pull request review comments with full thread context from the terminal, which the built-in gh tool does not show.
Security skills for Claude Code that encode the judgment professionals bring, not another wrapper around a scanner. Offense, defense, and the reverse-engineering and code-audit core both sides share. Every skill is fact-checked against primary sources.
Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script, 100% local & read-only.
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
A monorepo of Unraid tooling: two MCP servers (Python and Rust) and three Unraid OS plugins, plus the Claude/Codex agent integrations that surface them. Repo name.
Bu repo, YouTube videomdaki Claude Code ajanlarฤฑ + skill'ler setup'ฤฑnฤฑn tam halidir. Kopyala, kendi makinene kur, 20 dakikada aynฤฑ sistem sende. Bรถlรผm 1, bu video ยท Ajanlar + Skills temel yapฤฑ Bรถlรผm 2, sonraki video ยท Ajanlar + Obsidian (kalฤฑcฤฑ hafฤฑza)
A comprehensive Claude Code skill for architecting production-ready Elixir/Phoenix applications with complete documentation, ADRs, guardrails, and handoff materials.
Nemp - The memory plugin for Claude Code that remembers everything.
Lets Claude create and update Linear issues, check project status and manage team workflows, so you can handle tracker work from your coding session instead of switching to the Linear app. It works through Linear's MCP tools, SDK and GraphQL API.
A fast, comprehensive command-line interface for Linear built in Rust. Manage issues, projects, cycles, sprints, documents, and more, entirely from your terminal.
A penetration testing plugin that gives Claude Code skills for authentication testing, application security checks, CVE vulnerability testing and domain reconnaissance. Built for security testers who want Claude to run offensive assessments.
Automates Android app reverse engineering in Claude Code. It decompiles APK, XAPK, AAB, DEX, JAR and AAR files with jadx or Vineflower and extracts HTTP API endpoints from Retrofit, OkHttp, Volley, GraphQL and WebSocket code.
Orchestrate Claude Code sessions as managed background processes from any OpenClaw channel.
Skills for AI coding agents working with Apollo GraphQL, covering Apollo Client for React, Apollo Federation subgraph schemas, Apollo iOS and Apollo Kotlin, plus an MCP server and Rover CLI.
One CLI for tools across protocols UXC helps agents and automation discover and invoke APIs and tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC through one consistent workflow.
The API client that lives in your terminal (and your git repo). Stop clicking through heavy Electron apps just to send a JSON body. yapi is a CLI-first, offline-first, git-friendly API client for HTTP, gRPC, and TCP.
A Claude Code plugin with agents, commands and reference skills for penetration testing, covering Active Directory attacks, exploit lookup, MITRE ATT&CK mapping, wordlists and pentest report writing.
A set of Claude Code skills for managed service providers, covering phone system administration, live call and queue operations, directory lookups, and abuse mailbox cases in Abnormal Security. Aimed at MSP technicians who work across these tools.
Skills for Shopify store owners and their AI agent: audit a catalog for product-data gaps, backfill missing image alt text, archive dead products, and assign Standard Product Taxonomy categories. It also drafts landing page concepts for a store.
Gives an AI agent a command line tool to read and act on X/Twitter, covering posting, direct messages, lists, scheduling and analytics. Each command returns one predictable JSON result, and it can manage several accounts at once.
A Claude Code plugin that enforces hexagonal architecture (ports & adapters) in Symfony projects. Works with both new projects (full scaffolding) and existing projects (progressive, module-by-module refactoring).
Practical agent workflows for Python, ML, and open-source maintenance. AI-Rig turns recurring work, scoping a change, reproducing a bug, reviewing a pull request, running an experiment, or checking release readiness, into explicit workflows with specialist.
Gives your coding agent ready-made playbooks for planning, debugging, QA, security, docs, data work, browser automation and shipping, so it stops starting every task from a blank prompt. Works with Cursor and Claude Code.
Gives Claude Code expert guidance for the tools in your stack, from React and Prisma to Redis and AI model APIs, so you stop looking up each SDK's patterns by hand. Install only the ones that fit your project.
A Claude Code plugin of offensive security skills, agents and commands for penetration testers. It covers API testing, network reconnaissance, cloud lateral movement, password attacks and payment security.
Searches the ENCODE genomics database, builds chromatin accessibility maps, runs batch analyses across many experiments, and helps with bioinformatics tool installation and ENCODE citations, all from natural language in Claude Code.
Runs software engineering work for you, from fixing one bug or implementing one ticket to planning and shipping a multi-ticket project with quality passes. It can also hunt for likely bugs in a codebase and write tests that reproduce them.
A plugin that lets Claude Code discover and call already-configured MCP servers through the mcpx command line tool, and generate project-local MCP routing skills.
Makes the AI agent work like a careful QA engineer: every pass or fail verdict must rest on an observed artifact such as a screenshot, network response or log, and anything not checked is marked as not tested instead of guessed. Includes help drafting bug reports and test cases.
Gives your AI coding assistant Go-specific guidance for reviewing changes, structuring services in clean architecture, writing idiomatic code, handling concurrency safely, and propagating context correctly. Built from common Go community practice.
A free, Apache-licensed Claude Code plugin of skills and agents for API pagination, caching strategies, conventional commits, safe database migrations, and error handling patterns.
Manages Linear issues from Claude Code through skills, agents, and slash commands. Creates, searches, edits, bulk-updates, and cleans up tickets, and can turn URLs into issues.
magento-claude-skills is a free, open-source Claude Code plugin that gives Claude (and the Claude Agent SDK) expert, current knowledge of Magento 2, Mage-OS, and Adobe Commerce development.
Gives AI-assisted coding projects a repeatable workflow for specs, implementation, review and memory, so features are not built before their acceptance criteria are written. Helps prevent LLMs from refactoring whole layers before anything works end-to-end.
An MCP server and Claude Code plugin that coordinates multiple AI agents through structured markdown documents, covering planning, workflow orchestration and code review.
A pre-ship audit for apps built with AI coding tools. It checks security, reliability, performance, AI integration, privacy and launch readiness, flags vulnerabilities, and gives the app a readiness score.
AI SAST framework for web & mobile apps, shipped as a Claude Code plugin. Agents read your source code and produce a validated, evidence-backed vulnerability report, no running the app, no network requests.