gsd-pro
A spec-driven AI coding workflow for Claude Code with subagents, slash commands and hooks, offering multi-model routing, rollback and recovery, and adaptive context management for developers.
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 →.
A spec-driven AI coding workflow for Claude Code with subagents, slash commands and hooks, offering multi-model routing, rollback and recovery, and adaptive context management for developers.
Make a project agent-ready by converging it toward a canonical agent-neutral structure. Re-runnable, and doubles as an audit.
Adversarial Architect subagent for the design-architecture skill. Red-teams the system by thinking like an attacker or a chaos…
Runs cloud hosted web scrapers and automation bots, called actors, to extract data from websites at scale.
Session lifecycle tools for Claude Code: start bootstraps context and CLAUDE.md, sync saves progress to memory files, stop wraps up and archives a session, and stepback reassesses architecture after repeated failed fixes. Includes a test spec generator.
Devil's advocate architectural reviewer. Critically analyzes implementation plans to find gaps, blind spots, and issues before…
Sets up Claude Code to run an Opus-class model as the main orchestrator that delegates work to cheaper workers, with session hooks that monitor usage so the session avoids hitting rate limits.
발표급 다크 에디토리얼 HTML 덱을 손으로 짓는 디자인 시스템. 브리프/원고를 받아 Apple·Linear·Stripe 키노트급으로 보이는 프레젠테이션을 프론트엔드(HTML/CSS, 1920×1080 슬라이드)로 만들고 헤드리스…
작업 결과물(코드·설계·조사 결론)과 작업 계획에 대한 적대적 검증 전담 서브에이전트. 메인 에이전트가 계획 수립 시, 완료 보고 전, 비가역 결정 전에 호출한다. 결과물을 승인하는 것이 아니라 반박하는 것이 임무. codex…
How to configure Mr. Meeseeks (which sounds play, and how to mute them)
Claude Code and Codex skills for Spring Boot 4 and Java 25. The main one, spring-boot-team-harness, gives every developer on a team the same agent setup and makes ./mvnw verify (or ./gradlew build) fail on the mistakes agents make.
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when…
Run a deep, autonomous brand review across all 6 AI engines. Review public web signals. Use connected Ahrefs Brand Radar data…
A Claude Code plugin with skills that search past sessions and tools before planning or debugging, preserve context across sessions, and coach prompt writing. Built for Claude Code users who want automatic history, tool discovery, and memory.
Define how multiple brands, sub-brands, and product lines relate to each other under one organization. Use when the user says…
You are a creative, persistent vulnerability hunter. You think like an attacker — not just running payloads from a list, but…
Check that Devin Handoff is ready to use (dependencies + API key)
Stores and retrieves facts across sessions through a persistent knowledge graph.
A Claude skill that removes signs of AI writing from English text. It targets word-level habits and structural ones such as over-explained conclusions, template paragraphs, and invented specifics.
Build, review, and refactor web interfaces that are easy for humans, screen readers, browser automation, Playwright tests, and AI…
View your cognitive methodology profile and reasoning patterns
Gives your coding agent a clear definition of done, so it works out what you mean and only calls a task finished once every check passes. Covers finite tasks, project outcomes, ticket work, design and pull-request review.
Build a Total Addressable Market list: size the audience, source companies from ICP filters, then find contacts at those…
Use this agent when you need to run tests for API skills, validate skill functionalities through direct invocation, or perform…
Record the present state in free text — a decision (ADR, RFC, rule), existing code (spec, guide, task-type, scenario, doc), or a…
Connects to Chrome over the DevTools Protocol to inspect the DOM, network requests and console output.
Turns data reports into web-based slide decks with ECharts charts, switchable themes, fullscreen playback and one-click PDF export. Built for people who make periodic work or quarterly reports.
Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or…
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Applies safe local…
Helps you start a new project or adopt an existing one for AI agent work, with commit and pull request helpers, memory cleanup, and a loop that improves the project over time.
Delegate tasks to Antigravity CLI (agy) to use its models, tools, and separate working context. Use when delegation can improve…
Analyst perspective agent for devpace. Handles metrics collection, retrospectives, and trend analysis. Data analysis with write…
REST API design best practices. Use when designing APIs, choosing status codes, or creating endpoints.
Creates web presentations from a topic, notes, or outline using reveal.js, with a custom theme and a short preview. Decks can be edited afterward by adding, removing, or revising slides.
Generate and enforce policy gates for AI coding agents (Copilot, Claude Code) — real-time session hooks that deny protected-path…
Use this agent when the user needs to implement a modern, professional website using frontend design system skills. This includes…
Stores and queries vector embeddings for semantic search and retrieval augmented generation.
Agent skills and hooks for development workflows, covering Git commits, GitHub pull request creation, review and merge, decision records, and skill authoring. Built for Claude Code users.
Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set…
Use this agent when the user wants to open a pull request, publish a session, or share work via a PR. This includes when the user…
Perform a comprehensive CSS audit across all project files. Scores overall Divi 5 compatibility, identifies patterns and…
Places trades and retrieves market quotes and account data through a securities brokerage API.
A marketing plugin for Claude Code with skills that research a company, its competitors and funnel strategy, extract a brand kit from screenshots or a website, and draw out a founder's point of view. Output is grounded in your own company context.
USE WHEN a load-bearing architectural decision is being made in conversation (database / framework / auth model / integration…
Peer-to-peer communication between Claude Code sessions - start, connect, listen, ask, peers, status, stop
Claims the AI bounty on the aelf tDVV network through the reward claim contract, supporting both wallet and Portkey smart account claims. It requires explicit confirmation before any write action.
Transform conversations and discussions into structured Notion documentation
Run AgentLint diagnostic across all projects. Use when: user says /al, 'check all projects', 'agent lint', or '体检'.
Research Architect is a research workflow skill suite for moving from a raw topic, partial materials, or scattered results to a coherent research-paper draft.
Review an existing design and connect it to design system components.
Query NVD and OSV.dev for existing CVEs. Usage: /check-nvd <package-name>. Shows CVE count, severity breakdown, and recent fixes.
Traces where local files and artifacts came from, what depends on them, and what each task or run changed, with a searchable record. Built for Python and notebook work such as research code and data analysis.
End-to-end research paper generation, review, and revision for ML/AI/CV/NLP projects from repositories, notes, experiment logs,…
STRONGLY PREFER to delegate Apple platform builds, tests, and device operations to this agent to preserve your context window.…
Run a WoterClip heartbeat cycle (pick up issues, do work, report)
Context compression plugin for Claude Code. Automatically trims large tool output, JSON, YAML, stack traces, and logs, before it enters the context window. Works as a Claude Code plugin (automatic, zero-config) or as an MCP server (on-demand).
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript.…
Add a custom module repository (company or personal) to claude-code-setup.
Monitors network devices, maps topology and tracks configuration changes for managed service provider clients.
Part of the linkedin-skills family (400+ stars). Same voice engine and approve-before-publish flow, now for Threads. Also available for Instagram · X · YouTube · TikTok · Facebook. 8 skills that turn Claude Code and Codex into your Threads content team.
Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with…
Analyzes task description and codebase context to recommend complexity depth level (quick/standard/thorough). Lightweight…
A collection of agent skills for building interfaces with coding agents.
Transform any research material into SEO+GEO-optimized blog posts for Knox Hub. Takes any input (URL, article text, notes, video…
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
Shape Hush's final message - a configurator with a live preview in the Claude desktop app, or seven or eight short questions in a…
Records your screen while you perform a repetitive task once, then has Claude Code automate that task for you from the recording.
去除中文文本中的 AI 生成痕迹,使其更符合中国 MBA 毕业论文的自然写作风格。当用户提到"去 AI 痕迹"、"去除 AI 写作痕迹"、"MBA 论文改写"、"让这段文字更像人写的"、"去除机器感"等关键词时触发。适用于需要降低文本 AI…
Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes…
Route to the `content-seo` skill to brief, write, review, optimize, or publish public SEO content.
Fetches current, version specific documentation and code examples for a library, so the agent stops working from stale training…
Skills for building data work on MotherDuck with Claude Code. They cover dashboards, data pipelines, customer-facing analytics apps, the CLI, and connection setup.
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject google_mobile_ads +…
Implements a single fable-bench packet from a brief. Sonnet 5, builds with the six fable skills loaded. Use for bench/…
Diagnose connection or behavior issues with the Ableton MCP server. Use when tools aren't responding, AbletonMCP doesn't show up…
Deploys and manages websites and serverless functions on a cloud hosting platform.
A skill that guides an agent through deep research on a product, company, person, concept, industry chain, policy or trend. It gathers sources, checks them, synthesizes evidence and outputs a formatted PDF report of long length.
Turn any content into a top-tier McKinsey-style deck — a 1280×720 page-turning HTML presentation that also prints to a clean…
Reviews code diffs against section plans. Used by /deep-implement for section review.
An AI agent that analyzes compiled binaries to find vulnerabilities, malware and code similarity.
Gives Claude Code the working know-how of a construction project engineer, so it can split drawings, parse specs, tabulate and evaluate subcontractor bids, review submittals, draft RFIs and write subcontracts from your terminal or IDE.
GameForge Accessibility Specialist (Kael Oduya) with project memory, for an independent review or deliverable on motor, visual,…
Convert a complete HTML/CSS/JavaScript project into a production-ready WordPress block theme (Full Site Editing).
A financial market data API providing stock prices, fundamentals and economic data for global exchanges.
Gives Claude Code users a local, searchable copy of the official Claude documentation, plus skills to generate interactive HTML courses, changelog reports, and freshness checks of that cache.
Scaffold a new Deep Agents (LangChain) agent, a dcode CLI agent, or both, from one command. Use ONLY when the user explicitly…
Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the…
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
Let your Claude Code message you on Telegram when it needs decisions or finishes work, even when you’re away from your desk. Claude Code → Agent Reachout → Telegram → Human reply → Agent continues.
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user…
Run three-agent adversarial analysis -- advocate builds the case, adversary challenges it, judicial analyst synthesizes
小宇宙播客笔记生成器 · Turn a Xiaoyuzhou (Chinese podcast) episode into structured Markdown notes, a Claude skill using Qwen / Fun-ASR for transcription.