app-it
Turns a local web project or a hosted web app into a macOS Dock-launchable .app with its own native window and Dock icon. Includes Windows beta launchers and static-build packaging for finished sites.
4,248 plugins. 79,851 skills, agents, commands and MCP servers. 99 get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how →.
Turns a local web project or a hosted web app into a macOS Dock-launchable .app with its own native window and Dock icon. Includes Windows beta launchers and static-build packaging for finished sites.
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…
Cross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between…
Fetches current, version specific documentation and code examples for a library, so the agent stops working from stale training…
A practical configuration kit for Claude Code, Codex, and other coding agents. It contains architectural principles, enforcement hooks, skills, drop-in rules, starter templates, and dynamic-workflow commands.
Checklists for adding a new MCP tool, select or op, a new Flyway database migration, or a new Gradle dependency to the Task…
Use this agent whenever AT is invoked, with the rest of the account team members and never on its own, whenever there is a…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate…
The source file is the design brief. Turn existing HTML into a beautiful, usable page, without losing its meaning.
Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video…
Diagnose the Remember plugin — resolved paths, detected tools, storage mode, and whether capture is actually saving memory.
Yuan is a unified destiny-reading skill for Codex, Claude Code, and any Agent Skills–compatible runtime.
A secure local gateway for AI agents to reliably call approved enterprise APIs, tools, and services.
Meihua Yishu (梅花易數 / Plum Blossom Numerology / Plum Blossom I Ching) is a traditional Chinese I Ching divination method, attributed to Shao Yong (邵雍) of the Song Dynasty.
Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode).…
Read-only WIO subagent for discovering high-value test or workload candidates before implementation. Use during `$wio scan`,…
Check international patent application formalities for PCT compliance (PCT Rules 5-12, Administrative Instructions)
A skill that creates, evaluates, and improves other skills. Meta-level. Architecture-first skill lifecycle: design → build → test → evaluate → package. Most skill tools jump straight to "write SKILL.md."
Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft…
Clean-context multi-perspective reviewer of an SDD feature's candidate approaches. Use during specify's ideation pass (hard…
Tracks keyword rankings, backlinks and competitor SEO metrics through a subscription analytics platform.
SEO Landing: Give your AI coding agent the capabilities of a senior Technical SEO engineer. An agent skill for building high-performance, technically optimized SEO landing pages. Turn an AI coding agent into a technical SEO specialist.
Quickly save something as a single clean note in the right place — a link, a thought, an article, a snippet
Gives Claude Code a file-based memory system that records session context, compacts it into a daily, weekly, monthly and root summary tree, and searches it through qmd. No extra infrastructure is needed.
Save the current Claude Code or Codex session state to a temporary state file before running /compact. MANDATORY TRIGGERS:…
公司 CEO(Jeff Bezos 思维模型)。当需要评估新产品/功能想法、商业模式和定价方向、重大战略选择、资源分配和优先级排序时使用。
Find where the business should be recommended by ChatGPT/Perplexity/Gemini and which listicles to pitch
Browse the flagship Skill: skills.sh · Agentic Awesome Skills · Agent Skill Exchange · askill · Awesome Skills · skills.re · SkillsCat · OpenAgentSkill · AgentSkill.sh Have a repeatable workflow that is missing?
SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns.…
Simple greeting agent, use proactively when greeting the user. If they say 'hi claude' or 'hi cc' or 'hi claude code' use this…
Claude Code plugin providing skills for x64dbg debugger automation.
Capture or update a small business owner's brand brief — what they sell, who buys, the action they want readers to take, recent…
Verify a focused subject-matter claim with current authoritative sources and return only evidence useful to the lesson.
Show what memory context is currently available in this session.
Seven Agent Skills that support plain language writing, document audits, code, and organisational implementation. They apply principles inspired by the ISO 24495 Plain language series. The skills are plain SKILL.md files with agent-neutral wording.
Unleash Drunk Claude — the unfiltered, slightly tipsy genius who delivers absurdly wild ideas that weirdly, inexplicably work.…
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation…
Install pitchcraft skill for structured persuasion and executive reporting
Merge the current change to main and tag a release. Puts the changelog entry in the feature PR, squash-merges it, tags main, and…
A Claude Code skill for stealth browser automation that helps Playwright runs avoid bot detection and CAPTCHA checks. It uses a real headed Chrome built on rebrowser-playwright and undetected-chromedriver, exposed as a single createStealthBrowser() import.
Extract brand-relevant keywords from a website URL using meta tag analysis + AI semantic understanding. Useful for SEO, ad…
Senior ML/AI engineer agent for heavy-lift tasks — training config reviews, serving/inference optimization, pipeline debugging,…
The follow-up memory quality optimization adds canonical runtime path resolution, evaluation trend comparison, private registry linting, policy validity/conflict metadata, gbrain plan summaries, and an operator report. See the optimization report.
Triggers when building any UI element in Figma — 'create a card', 'build a nav', 'add a section', 'make a component'. Enforces…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Connects to Chrome over the DevTools Protocol to inspect the DOM, network requests and console output.
Gives an AI agent a project spec written as a flat list of short claims, each tagged as a draft, a spec to build, or implemented. The agent works through the unbuilt claims and runs a shell command to check each one, so you can see what is done and what is still open.
Authoritative, source-cited playbook for designing, configuring, deploying, and troubleshooting production-grade AI agents on AWS…
Use proactively for PRP generation and codebase pattern analysis. Specialist for internal project analysis - discovering existing…
Deploy Sanity schema to the Content Lake with verification.
Реализация: написание кода, создание модулей, рефакторинг, UI-изменения
Interactive guide for creating a new Obsidian plugin with best practices
A Claude Code skill that edits existing German text, auditing and removing typical AI writing patterns and stiff phrasing while keeping the author's voice and the facts unchanged.
Curated, file-based long-term memory for an AI agent. Use this skill (1) at the start of a task or when resuming unfinished work…
Architecture design expert. Synthesizes code analysis, tech-spec context, and architecture advice into structured architecture…
Gera scripts de automação de testes ADVPR (Advanced Protheus Robot) - TestSuite, TestGroup, TestCase para rotinas MVC, ExecAuto,…
Offline security scanner that audits git repos, AI skills, plugins, MCP servers, and agent credentials for prompt injection, credential theft, and known vulnerabilities. Runs as a skill and as pre-tool-use hooks.
Use when designing multi-app Frappe architectures, deciding whether to split functionality into separate apps, or implementing…
Create a complete guardrail specification for an AI feature.
Open-source runtime that turns a LangGraph or Google ADK agent into a production-ready FastAPI service, with a chat UI, guardrails, MCP support, OpenTelemetry and OIDC. Self-hosted.
Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name. Use when…
Systematically clarify intent, challenge assumptions, resolve contradictions, and align goals, constraints, risks, and success criteria.
Use when building, editing, testing or inspecting a project through LayerFS with the JavaScript SDK (`@layerfs/agent`) from the…
A portable SKILL.md workflow that turns Claude into a tutor and project coach. It diagnoses your starting level, builds a study plan, runs project-based practice, checks mastery, and saves notes as Markdown files.
AI可读性审计工具,模拟AI爬虫视角评估网站对大语言模型的友好程度,分析结构化数据、语义HTML和Meta信息
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.
Use when conducting threat hunting or incident response with CrowdSentinel MCP tools. MANDATORY for any investigation involving…
A product manager skill for Claude Code that critiques PRDs, diagnoses SaaS metrics, plans roadmaps, runs product discovery, and coaches career moves. It also works in Codex, Cursor, and Windsurf.
为 Claude Code 提供完整的中文体验!包含工具提示、界面汉化、完整的自定义指南、实战经验和进阶开发教程, 让用户能够根据自己的需求修改和完善.
Tendril is an agent orchestration plugin for Claude Code with skills to debug jobs and plans, review changed files, manage the Ivy Tendril extension, and run releases. It covers parallel worktrees, plan management, and a verification gate.
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate…
A Claude Code skill that stops you from burning through your usage limit. Claude re-reads the entire conversation on every turn. One developer measured it: 98.5% of his tokens went to re-reading history, only 1.5% to generating responses.
Create mathematical animations with Manim Community Edition(manimce), with optional TTS voiceover and synced subtitles. Generates…
Use when a learner asks for help with MATLAB homework, labs, projects, graded assignments, take-home exams, quizzes, or any…
Copies the formatting of a reference Word (.docx) file onto new content, so fonts, spacing, page setup, styles and headers match without reformatting by hand. Runs only on macOS with Microsoft Word installed.
Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system…
Lets Claude Code investigate Dynatrace incidents, debug performance issues, and analyze logs through the dtctl CLI. It also manages workflows, dashboards, and queries from the terminal.
Polymarket integration for prediction market trading on Polygon. Covers authentication (L1 EIP-712, L2 HMAC-SHA256, builder…
A brutally honest, fully personalized 6-month plan to land a $100K AI job (or equivalent income through freelancing/consulting). From the video: "If I Wanted a $100K AI Job in 6 Months, I'd Do This"
Create dark-themed, animated technical diagrams as self-contained HTML+SVG files — flowcharts whose connectors visibly flow, and…
Automatically monitors OKX Flash Earn, Fixed Earn and Flexible Earn opportunities, sends push notifications, and guides…
AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports…
Goodable is a local-first Desktop AI Workspace (Desktop Agent Runtime) powered by Claude Agent SDK, combining OS/file control, browser automation, and coding into composable Skills (tool + app modes) to build, run, and publish real AI apps.