Engineering
98,648 rows, by stacks then stars
simplifier-ag/simplifier-mcp/io.github.simplifier-ag/simplifier-mcp MCP server
5★ repoMCP Server for Simplifier - manage Connectors, BusinessObjects, Datatypes and logins
singhpratech/notepatra/io.github.singhpratech/notepatra-mcp MCP server
5★ repoNotepatra editor MCP server — 35 tools; every write human-approved in the editor; local-only.
standardbeagle/devtool-mcp/io.github.standardbeagle/devtool-mcp MCP server
5★ repoDevelopment tooling MCP server with process management, proxy, and frontend diagnostics
sunshad0w/html2md-mcp/io.github.sunshad0w/html2md MCP server
5★ repoConverts HTML to Markdown with auto-summary and section extraction. Supports Playwright.
tcehjaava/tmdb-mcp-server/io.github.tcehjaava/tmdb-mcp-server MCP server
dormant5★ repoMCP server for The Movie Database (TMDB) API
theYahia/planfix-mcp/io.github.theYahia/planfix-mcp MCP server
5★ repoMCP server for Planfix API — tasks, contacts. 3 tools.
theYahia/yandex-direct-mcp/io.github.theYahia/yandex-direct-mcp MCP server
5★ repoMCP server for Yandex Direct — PPC campaigns, ads, keywords, statistics (Russia)
timmx7/styx/io.github.timmx7/styx-mcp-server MCP server
5★ repoMCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.
tushariitr-19/patents-mcp/io.github.tushariitr-19/patents-mcp MCP server
5★ repoPatent search and prior art discovery via Google Patents on BigQuery
txn2/mcp-trino/io.github.txn2/mcp-trino MCP server
5★ repoMCP server for Trino data warehouses. Query, analyze plans, and explore schemas.
Async Parallel Antigravity for Codex & Claude Code
varadfromeast/codex-agy-bridge/io.github.varadfromeast/codex-agy-bridge MCP server
5★ repoRun parallel, resumable, human-operable Antigravity CLI sessions from any MCP agent harness
varaprasadreddy9676/huly-mcp/io.github.varaprasadreddy9676/huly-mcp MCP server
no license5★ repoMCP server for Huly — manage projects, issues, documents and more via natural language.
vdalhambra/siteaudit-mcp/io.github.vdalhambra/siteaudit-mcp MCP server
5★ repoSEO, performance, and security audits for any URL — no API keys required
vish288/mcp-gitlab/io.github.vish288/mcp-gitlab MCP server
5★ repoMCP server for GitLab API — projects, MRs, pipelines, CI/CD, approvals, issues, code review.
xodn348/HNmcp/io.github.xodn348/readhn MCP server
5★ repoAI-native HackerNews MCP Server. Find HN content that matters with explainable quality signals.
xxxoooxoxo/wiff/io.github.xxxoooxoxo/wiff MCP server
5★ repoDeterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi.
yixuanzhong/PLAXIS-MCP/io.github.yixuanzhong/plaxis-mcp MCP server
5★ repoWindows-local MCP server for PLAXIS 2D Remote Scripting: geometry, staged construction, results.
yohasacura/drawio-mcp/io.github.yohasacura/drawio-mcp MCP server
5★ repoMCP server for creating and editing draw.io / diagrams.net XML files programmatically.
zackpeters93/ugs-mcp/io.github.zackpeters93/ugs-mcp MCP server
5★ repoCNC machine control via Universal G-code Sender. Jog, home, run files with hardware safety tokens.
Neonia: The Cloud Backend for AI Agents
Neonia-io/agent-mcp-examples/io.neonia/cloud-backend MCP server
5★ repoMultiple MCP tools, persistent graph memory, token-saving data pointers, and more.
Philidor DeFi Vault Risk Analytics
Philidor-Labs/philidor-mcp/io.philidor/defi-vaults MCP server
5★ repoSearch 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.
manovagyanik1/clipy-mcp/online.clipy/mcp MCP server
5★ repoRead your Clipy screen recordings: search, transcripts, AI summaries, and key moments with frames.
meringlab/string-mcp/org.string-db/string-mcp MCP server
5★ repoQuery STRING interactions, enrichment, annotations, homology, and PPI networks.
ajaydata-vision/nuclear-bug-fix- Skill
no license4★Most powerful bug-fixing skill for bugs surviving code review, careful planning, and multiple fix attempts. Triggers on ANY stack, ANY language, ANY framework. Use when user says "still broken", "tried everything", "code review didn't help", "nothing works", "find the bug", "help me debug", "bug not resolved", or describes a silent failure. Also triggers for: UI rendering wrong, component not updating, CSS broken in prod, hydration mismatch, bundle error, CORS failure, WebSocket not connecting, API returns success but state not updated, DB write returns stale data, auth token rejected, background job silently failing, queue message not consumed, webhook not firing, microservice not responding, pipeline failing, data transform wrong, ETL dropping rows, CI/CD deploy succeeds but app broken, works locally but fails in prod, intermittent crashes, race conditions, bug came back after fix, any bug already looked at once. ALWAYS use this skill instead of a generic debugging response. Also triggers for: "rocket", "fast mode", "skip routing", or when user names a stack and wants immediate diagnosis without routing overhead.
adityasugandhi/skillsync-mcp Skill
4★SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.
The same file is in 1 other repository
wrsmith108/claude-code-docker-skill/skills/docker Skill
4★ repoContainer-based development for isolated, reproducible environments. Use when running npm commands, installing packages, executing code, or managing project dependencies. Trigger phrases include "npm install", "run the build", "start the server", "install package", or any code execution request.
The same file is in 2 other repositories
2389-research/test-kitchen/skills Skill
4★ repoThis skill should be used when implementing features with parallel exploration or competition. Triggers on "build", "create", "implement", "try both approaches", "compare implementations". Routes to omakase-off (entry gate for design exploration) or cookoff (exit gate for parallel implementation).
The same file is in 3 other repositories
Anyesh/skillprobe/.agents/skills/write-tests Skill
4★ repoWrite skillprobe YAML tests for LLM skills. Use when asked to write tests, create test scenarios, test a skill, generate skillprobe tests, or check whether a skill activates correctly.
mdrobniu/xsoar-pack-dev-skill Skill
4★Cortex XSOAR content pack development lifecycle - create packs, integrations, scripts, playbooks, run demisto-sdk lint/validate/pre-commit, build zip packs, manage versions and release notes, run unit tests, deploy to XSOAR instances, manage git branches/tags, handle marketplace vs local pack workflows. Use when the user wants to develop, test, build, validate, deploy, or manage XSOAR content packs.
leggiemint/legnext-skills/legnext-midjourney Skill
4★ repoGenerate AI images using Midjourney through the Legnext API. Use this skill when users request Midjourney-style image generation, visual content creation, or ask to create/generate images with natural language descriptions. Handles prompt engineering, API calls, task polling, and result retrieval.
tnisizawa/clasp-skill Skill
4★GASデプロイ。clasp push / deploy / clone / create / logs。GASプロジェクトの初期化・プッシュ・Webアプリ/ライブラリデプロイ・ログ取得。Google Apps Script deployment via clasp: push, deploy web app / library, rollback, logs.
houyongsheng/flutter_gemma_skill/flutter-gemma-scaffold Skill
4★ repoUse this skill when you need to add Gemma 4 on-device AI to a Flutter project. Handles: integrating flutter_gemma package, configuring iOS/Android/Web/Desktop platforms, model installation and loading, basic inference, function calling, multimodal input, and streaming responses. For developers building offline-capable AI features with local LLM inference.
Tanq16/claudex/internal/embedded/default-skills/cross-ai Skill
no license4★ repoUser-invoked dispatcher that hands a task to one or more external headless CLI coding agents (agy, gemini, codex, cursor) or Claude Code headless and relays their output. Invoked explicitly as `/cross-ai <agent> [task]`. Do NOT auto-trigger this from incidental mentions of these tools, and never use it for native Claude Code sub-agents (the Task tool).
YousefNabil-SOC/claude-apex/skills/21st-dev-magic Skill
4★ repoGenerate premium React+TS+Tailwind UI components from natural language via 21st.dev Magic MCP server
ralvarezdev/ralvaskills/skills/databases/sql-architect Skill
4★ repoSQL standards — UUID v7 PKs, snake_case, soft delete, forward-only migrations, parameter binding, N+1 prevention, EXPLAIN-driven indexing. PostgreSQL 18 primary; MySQL 9 and SQLite 3.53 noted. Use when designing schemas, writing queries, or auditing a database layer.
zakisheriff/Claude-Liquid-Glass-Skill/claude-liquid-glass Skill
no license4★ repoEnforces native iOS 26+ Liquid Glass in all iOS UI — SwiftUI, UIKit, and React Native / Expo (expo-glass-effect + expo-router NativeTabs). Covers buttons, icons, navbars, tab bars, search bars, text inputs, sheets, cards, every interactive element. Two hard laws: (1) never hand-roll or custom-make Liquid Glass — always use the platform's native component (SwiftUI `.glassEffect`/ `.buttonStyle(.glass)`, or RN `GlassView`/`GlassContainer`/`NativeTabs`); never fake it with BlurView/ultraThinMaterial/opacity on iOS. (2) every touch fires a haptic. Use when writing, reviewing, or refactoring any iOS UI code (Swift or React Native/Expo), even if the user just says "make a button" or "add a nav bar" without mentioning liquid glass, haptics, or iOS 26. Trigger on SwiftUI views, buttons, NavigationStack/toolbar, TabView, .searchable, TextField, sheets; and on RN/Expo Pressable/TouchableOpacity, expo-router layouts, expo-glass-effect, expo-haptics, or any styling / press-feedback decision.
andreagroferreira/laravel-ai-sdk-toolbox/tests/Fixtures/plugins/memory-pack/skills/memory-tip Skill
4★ repoTips on using the agent memory tools.
nahiddotai/operator-powers/plugins/operator-powers/skills/agents-md-setup Skill
4★ repoCreate or improve AGENTS.md or CLAUDE.md when the user wants persistent instructions, better project context, or an AI that understands how they work.
CyrilLeMat/temper-skills/skills/temper-skills Skill
4★ repoGive an agent skill's decision logic a test suite and a deterministic implementation — a labeled validation dataset plus versionable Python — by driving the installed temper-skills CLI (never reimplementing the logic in prose). Use in agents without a native subagent primitive (Cursor, Hermes, generic tools) when the user wants to test, eval, audit, temper, freeze, or harden the routing/decision logic of a prompt, skill.md, or playbook ("test my skill", "what is this skill deciding?"), including auditing a whole skills directory; requires `pip install temper-skills` and a model backend (a logged-in claude/opencode CLI or an API key). Not for continuous scoring, text generation, or logic with no documentation the model can reach.
isatimur/excalidraw-skill-pack/packages/core Skill
4★ repoCreate Excalidraw diagrams as `.excalidraw` JSON that make a visual argument — not just labeled boxes. Use when the user wants to draw, sketch, visualize, or diagram a system architecture, software design, workflow, flowchart, sequence, data flow, state machine, pipeline, org chart, mind map, concept map, network topology, or process — in a hand-drawn, sketchy whiteboard style. Produces valid, themeable `.excalidraw` files that render to PNG and open in Excalidraw, Obsidian, or VS Code. Triggers on phrases like "make a diagram", "draw the architecture", "visualize this", "excalidraw", "flowchart", "system design diagram", "sketch this out", or "whiteboard it".
stealth-engine/skills/skills/agents-md-setup Skill
4★ repoSet up a project's agent instructions as a single source of truth — AGENTS.md as the real file, with CLAUDE.md (and optionally other agents' files) as symlinks to it. Use when starting/bootstrapping a repo, when asked to "add a CLAUDE.md / AGENTS.md", "set up project conventions / agent instructions", "make Claude use AGENTS.md", or when a repo has a standalone CLAUDE.md that should become cross-tool. Also use to fix duplicated/drifting CLAUDE.md + AGENTS.md, or to add per-workspace instructions in a monorepo (Turborepo / pnpm workspaces).
MarieLynneBlock/arcanum-artifex/skills/agentic/agent-governance-patterns Skill
no license4★ repoDesign and implement governance controls for tool-using and multi-agent AI systems, including policy enforcement, approval gates, audit trails, trust scoring, rate limits, and safe tool execution.
he8um/n8n-skills/n8n-skills Skill
4★ repoprofessional n8n workflow architecture and importable workflow json generation for ai agents. use when a user asks to design, build, audit, refactor, document, troubleshoot, or harden n8n workflows; produce import-ready workflow json, markdown specs, node graphs, api/webhook integration plans, credential-safe patterns, retries, error handling, observability, queue-mode guidance, and production runbooks.
jeremieb/swift-unit-test-instructions/skills/swift-architecture-audit Skill
4★ repoAudits an existing Swift/SwiftUI/UIKit codebase for MVVM compliance, testability issues, architectural violations, concurrency problems, and anti-patterns. Use when user says "audit the codebase", "review the architecture", "why is this hard to test", "onboard to this project", "analyze the code structure", "find issues in the code", or "what needs refactoring".
huyngopt1994/infras-kit/infras-kit-plugin/skills/infra-kit.domain.github Skill
no license4★ repoCreate, review, standardize, or troubleshoot GitHub repository and CI/CD assets (CODEOWNERS, templates, branch protection guidance, and GitHub Actions workflows).
WESTsyre21/setup-backend-stack Skill
4★Bootstraps a local Node.js backend development stack with Docker, PostgreSQL, and an ORM (Prisma or Sequelize). Use this skill whenever the user wants to: initialize a new backend project, set up a Dockerized database locally, wire up an ORM with automated migrations, scaffold an Express server with a health endpoint, or repair a broken local dev environment involving Docker + Postgres. Also trigger when the user mentions any of: "set up backend", "docker postgres", "prisma setup", "sequelize setup", "local dev stack", "migrate my database", "scaffold express", or "backend boilerplate". If the user is starting any server-side Node.js project and hasn't mentioned a database setup, proactively suggest this skill.
n-n-code/n-n-code-skills/.agents/skills/agent-skill-generator Skill
4★ repoCreate or revise reusable agent skills from a problem statement, workflow, or existing skill folder. Use when the user asks to build a skill, design an agent skill for a repo, improve a skill's triggering or structure, validate a skill with representative prompts, audit a skill for token efficiency, or turn a repeated workflow into a portable skill package.
Kaspa sovereign architect engine
gryszzz/Kaspa-Ai-Agent-Skill/skills/public/kaspa-sovereign-architect-engine Skill
no license4★ repoSource-grounded Kaspa protocol and Toccata engineering for Rusty Kaspa, KIPs, wallets, Kasware/Kaspium, indexers, WASM/TypeScript, covenants, ZK, vProgs, mining, infrastructure, repository audits, and current network or release status. Use when Codex must research, explain, design, implement, review, or verify Kaspa systems with UTXO-first architecture, DAG-aware correctness, explicit monetary flows, current primary sources, and reproducible validation.
tinoimammp/vantage-security-agent/skills/vantage Skill
4★ repoAutonomous, artifact-driven SAST (Static Application Security Testing) for web AND mobile app repositories, plus optional code-level remediation. Use whenever the user asks to security-review, pentest, audit, or scan a codebase for vulnerabilities — web (SQLi, XSS, IDOR/BOLA, auth bypass, SSRF, XXE, hardcoded secrets, vulnerable dependencies, business logic flaws) or mobile/Android/iOS (OWASP Mobile Top 10 2024: improper credential usage, insecure data storage, insecure communication, insufficient cryptography, etc.) — via static code analysis, never by running the app, installing it, or sending requests. Also use when the user asks to fix, patch, or remediate a finding this framework produced, or to check a single commit/PR/MR for newly introduced vulnerabilities without a full repo scan. Drives a 6-phase scan pipeline (recon, mapping, testing, validation, PoC, reporting) through the vantage plugin's specialized subagents, branching on platform, plus a separate on-demand fix step and a fast incremental commit/PR/MR check.
jsingh6/arch-decision/skills/arch-decision Skill
no license4★ repoArchitecture Decision Record (ADR) orchestrator. Given a feature request, GitHub issue, or free-text problem statement, explores the codebase deeply, generates 3 architectural approaches using parallel agents, produces a trade-off recommendation, and writes a formal ADR to docs/decisions/. Works on any language or framework. Config-driven for any team (GitHub Issues, Linear, or Jira; Slack or Teams notifications).
hiadrianchen/challenge-plans Skill
4★Before you execute a drafted plan/spec/design doc, run a multi-agent adversarial cross-review to surface the flaws that cause downstream rework, aggregating "evidenced, cross-family-verified" objections into a verdict. Use when the user asks to "review this plan/spec", "can this approach be executed", "poke holes / adversarial review / QA this", "harden before executing", or when an agent is about to hand a drafted decision/QA back to the user — first run this skill and present the cross-review recommendation plus surviving objections. Runs on local subscription CLIs (claude/codex), no per-token API cost. Not for "help me pick among options" — that's the weigh-options deliberation skill.
BechsteinDigital/claude-shiploop/autonomous-loop Skill
4★ repoUse when a set-up project (project/BRIEF.md approved, PROFILE/STATE/backlog present) should continue building autonomously — orchestration of CEO/PO/DEV/REVIEWER cycles with parallel agents, without user input. Also for resuming after an interruption or handoff.
Trystan-SA/postkit/.claude/skills/postkit-release Skill
4★ repoCut a new postkit release — bump the version in package.json (asks the user whether it's major / minor / patch), commit, tag on GitHub, publish a GitHub Release so watchers get notified, and publish to npm. Use when the user says "ship a release", "cut a new version", "publish to npm", or "release postkit".
Hashaam101/prompt-optimizer Skill
no license4★Automatically refines every user prompt into a structured, actionable version, then immediately executes the optimized prompt. When triggered explicitly with "/optimize {prompt}", "optimize:", or "optimize prompt:", outputs the refined prompt as text instead.
akirtok/preflight-security-audit/plugins/preflight-security-audit/skills/preflight-security-audit Skill
4★ repoThis skill should be used when the user wants a comprehensive pre-ship audit of an app, product, or codebase — phrases like "audit my app", "security check before launch", "is this ready to ship", "preflight audit", "review my product for vulnerabilities", "check my code for security issues", or after building a feature/product and wanting a thorough security, reliability, performance, privacy, and launch-readiness review. Covers OWASP Top 10 (2025), LLM Top 10, GDPR/KVKK, accessibility, SEO, and Stripe/Supabase/Next.js stacks.
basteez/java-skills/.claude/skills/generate-integration-tests Skill
no license4★ repoGenerate integration tests for a Java class using Testcontainers. Supports Spring Boot (3.1+), Quarkus (3.0+), and Micronaut (4.0+). Detects class type (repository, controller, service) and applies framework-appropriate test patterns. Requires Java 17+.
sefaertunc/Worclaude/.claude/skills/agent-routing Skill
4★ repoAgent Routing Guide — when to spawn each installed agent
actual-software/actual-skill-openclaw Skill
4★Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, and drives the Actual Advisor (login, advisor, whoami, logout) for org-scoped architecture questions. Covers all 5 runners (claude-cli, anthropic-api, openai-api, codex-cli, cursor-cli), all model patterns, all 3 output formats (claude-md, agents-md, cursor-rules), and all error types. Use when working with the actual CLI, running actual adr-bot, configuring runners or models, troubleshooting errors, managing output files, or asking the Advisor what your team's ADRs say about a design choice.
SteveGrosbois/tidal-cli/skills/tidal-auth Skill
no license4★ repoAuthenticate with Tidal via OAuth. Use when the user wants to log in to Tidal, start authentication, or when a command fails with an authentication error.
medalsoftchina/workcopilot Skill
4★项目全生命周期工作站。统一编排所有 Agent 和 Skill,从项目初始化到交付的一站式工作流。 自动识别新项目/老项目,引导需求分析、系统设计、任务拆解、脚手架搭建和工程轨道配置。 USE FOR: 开始新项目、接手老项目、初始化工作流、workcopilot、工作站、项目启动、 新建项目、项目脚手架、scaffold project、init project、start project、work copilot。 DO NOT USE FOR: 单个文档生成(直接用 doa-ppt / doa-metting 等)、纯代码调试(用 systematic-debugging)。