Python plugins

Enforces a structured TDD workflow with parallel task execution, code review, and root-cause debugging. Guides brainstorming into validated specs, creates isolated git worktrees for feature branches, and runs verification checkpoints before merging or committing.

Transforms Claude Code into an autonomous engineering platform with 64 specialized agents, 262 skills, and 84 commands for multi-agent orchestration, TDD, code review, security auditing, deployment pipelines, and cross-stack development across 30+ languages and frameworks.

Cut ~75% of tokens in Claude Code conversations by speaking like a caveman, compressing memory files, commits, PR reviews, and delegating tasks to specialized subagents for surgical code edits, read-only code location, and diff review.

Create, read, edit, and generate Office documents — Excel spreadsheets, Word reports, PowerPoint presentations — plus PDF manipulation, form filling, and conversion between formats. Also includes art/image generation, frontend UI building, and document co-authoring workflows.

Automatically generate C4 architecture diagrams (Context, Container, Component, Code) from your codebase via bottom-up analysis, producing Mermaid diagrams and documentation for system design, API interfaces, and deployment units.

Reverse engineer binaries, triage and unpack malware, extract and analyze firmware, perform memory forensics, and dissect network protocols using specialized AI agents and skills for authorized security research, CTFs, and incident response.

Orchestrate 1,388 specialized AI skills in Claude Code to automate expert workflows for Azure SDK integrations, Odoo/Shopify configs, SEO audits, security pentests, full-stack scaffolding, agent building, and DevOps pipelines across Python, React, AWS, Kubernetes.

Build production-ready Python applications with modern async patterns, type safety, and testing. Scaffold projects using FastAPI or Django, manage dependencies with uv, enforce code quality with ruff, and implement structured observability, retries, and background jobs.

Generate comprehensive technical documentation, tutorials, and API references from codebase analysis. Automates architecture diagrams, OpenAPI specs, READMEs, user guides, step-by-step tutorials, and long-form ebooks for onboarding or production docs.

Analyze code for smells, SOLID violations, and performance issues, then automatically refactor with prioritized fixes. Assess technical debt across code, architecture, testing, and infrastructure to produce a remediation plan. Modernize legacy code safely using the strangler fig pattern, and review code for security vulnerabilities and production reliability.

Run Claude in a continuous self-referential loop that feeds the same prompt back after each attempt, enabling iterative refinement until task completion. Track token usage across sessions.

Build production LLM applications with LangGraph agents, RAG pipelines, hybrid search, and advanced prompt engineering. Automate agent architecture design, vector index optimization, and prompt refinement for deploying reliable AI systems.

Orchestrate swarms of specialized AI agents to automate end-to-end software development: plan features, implement code with Rails/Python/TS patterns, conduct multi-perspective reviews for architecture/security/performance, resolve todos/PR feedback in parallel, run browser/iOS tests, sync Figma designs, generate docs/videos, and ship PRs.

Transforms Claude Code into a full-stack development assistant with curated expertise across 12 programming languages, major backend and frontend frameworks, DevOps tools, and software engineering practices—enabling code generation, debugging, architecture design, testing, and project management all from a single skill pack.

Orchestrate multi-perspective code reviews across architecture, security, performance, and best practices using specialized agents, with git diff analysis for PR descriptions.

Automate technical debt reduction, dependency updates, and code refactoring by scanning for vulnerabilities and code smells, generating prioritized remediation plans, and leveraging AI-powered test automation and code review.

Generate production-ready stateful CLI harnesses for GUI applications from local paths or GitHub repos, implementing Click CLI with REPL/JSON support, pytest unit/E2E tests, and docs. List installed harnesses, refine coverage gaps, run tests to verify functionality, and validate against standards.

Delegate architecture, implementation, optimization, and debugging of complex applications to specialized AI agents expert in Python/Django/FastAPI, TypeScript/React/Next.js/Angular/Vue, Go, Rust, Java/Spring Boot, PHP/Laravel/Symfony, C#/.NET, mobile (Flutter/React Native/Swift/Kotlin), Elixir/Rails, SQL, and DevOps tools.

Drive creative direction with algorithmic design manifestos, generative p5.js art, brand voice optimization, and portfolio interfaces that convert visitors to clients.

Perform end-to-end research workflows: market analysis, competitor benchmarking, trend detection, data validation, and idea vetting. A team of specialized agents retrieves and synthesizes information from web, files, and scientific literature to deliver actionable insights and strategic recommendations.

Run PluginEval certification pipeline on Claude plugins or skills to compute quality scores, badges (Platinum/Gold/Silver/Bronze), dimension breakdowns, anti-patterns, and recommendations via static analysis and LLM judging across 10 criteria including triggering, orchestration, and output quality. Compare skills head-to-head or evaluate directories for actionable insights.

Programmatically create, edit, and analyze office documents (DOCX, XLSX, PPTX, PDF) and Google Workspace files using Python scripts, enabling automated report generation, format conversion, and data extraction.

Design and document backend architectures using patterns like Clean Architecture, Domain-Driven Design, microservices, and event sourcing with CQRS, while generating architecture diagrams and managing Architecture Decision Records (ADRs) with MADR templates.

Produce scientific manuscripts, figures, and supplementary materials to Nature-journal standards. Converts raw results, Chinese drafts, or paper PDFs into polished prose, submission-ready figures (Python/R), Data Availability statements, BibTeX citations, PPTX presentations, and reviewer response letters. Also simulates peer review and reads papers with side-by-side translation.

Build production-ready data pipelines with Apache Airflow and dbt, manage scalable data warehouses, and implement vector search and RAG systems using embedding models and vector databases.

Automate the full TDD red-green-refactor cycle: generate failing tests, implement minimal passing code, safely refactor, and get AI-driven code review with security and performance analysis.

Build and manage cloud infrastructure and deployment pipelines with AWS serverless, Docker, Kubernetes, Terraform, and CI/CD workflows, including environment setup, containerization, GitOps, and production deployment strategies.

Centers Python backend development around async patterns, FastAPI, Django, and modern tooling, providing architectural guidance, testing strategies with pytest, and production best practices for scalable APIs and services.

Execute marketing and growth workflows including A/B testing setup, SEO diagnostics and optimization, analytics tracking audit, programmatic SEO strategy, and automated content/email campaign creation with brand voice analysis.

Perform business analysis workflows — KPI frameworks, predictive models, real-time dashboards, TAM/SAM/SOM calculations, and multi-year financial modeling for startups — using Python, SQL, and cloud data warehouses like Snowflake and BigQuery.

Delegate complex data engineering, ML, and AI workflows to specialized sub-agents that design scalable pipelines, build and optimize models, architect LLM systems, tune databases for performance, and deploy production infrastructure across clouds.

Manage Python projects via structured tracks for features, bugs, refactors: initialize context artifacts like product.md and tech-stack.md, create detailed specs and phased plans, implement tasks with strict TDD workflow using pytest coverage and git commits, monitor status, revert commits, and validate artifacts for consistency.

Develop and deploy Odoo ERP solutions with custom module scaffolding, ORM operations, security rules, eCommerce and CRM configuration, Docker-based deployment, and performance troubleshooting.

Enforce code quality and security checks after every change, automate git commits and pushes with conventional messages, generate structured task checklists, guide incremental refactoring, and apply systematic debugging—all within Claude Code.

Run the full academic research lifecycle inside Claude Code — from deep research and evidence mapping through structured writing, citation verification, peer review simulation, revision planning, and multi-format output generation, with a deterministic gate for citation correctness and bilingual abstract support.

Create video compositions from HTML with animations, captions, voiceovers, and audio-reactive visuals. Supports GSAP, Anime.js, Three.js, Lottie, WebGPU, and Tailwind CSS within a deterministic seek-driven time model. Includes CLI tooling for scaffolding, asset preprocessing, and rendering.

Build and evaluate production-grade AI agents using LangGraph, RAG systems, MCP servers, and prompt engineering patterns—with behavioral testing and reliability monitoring.

Enables Claude Code to conduct comprehensive security assessments across web applications, cloud infrastructure (AWS, Azure, GCP), and DevSecOps pipelines, including penetration testing, vulnerability scanning, privilege escalation, and audit reviews.

Autonomous investment banking pitch agent: pulls market data, builds DCF and football-field valuation Excel models, and produces branded pitch deck files on disk — all from a single natural-language request.

Enables startup founders to perform competitive landscape analysis, generate SEO-optimized competitor comparisons, write conversion-focused marketing copy, plan product launches, prioritize features using RICE, analyze customer interviews, and integrate Stripe payments.

Integrate external APIs for payments, communications, search, CRM, and financial data — Stripe, Twilio, Algolia, HubSpot, and Plaid — with production patterns for auth, webhooks, and compliance.

Build, deploy, and monitor AI-powered cloud applications on Azure using containerized apps, serverless functions, OpenAI integration, AI Search, and observability across .NET, Python, and Node.js.

Automate RevOps and CRM workflows across HubSpot, Stripe, Shopify, Zendesk, SendGrid, Google Calendar, and Outlook Calendar — manage contacts, deals, orders, subscriptions, tickets, campaigns, and events without leaving Claude Code.

Accelerate LLM application development with production-ready patterns for context window management, RAG pipelines, prompt caching, observability via Langfuse, and agent architectures.

Orient within a structured BMad workflow, brainstorm with creative techniques, distill raw input into validated specs, orchestrate multi-agent roundtables, split large markdown files, apply structured critique and adversarial review, enumerate edge cases, and improve prose and document structure.

Coordinate specialized AI agents through the full academic paper writing workflow: from literature search and argument blueprinting to drafting, citation verification, bilingual abstract generation, journal formatting, and simulated peer review, producing publication-ready LaTeX, DOCX, or PDF output.

Add persistent memory to AI agents by storing, retrieving, and searching user-specific learnings, decisions, and session states across Claude workflows using the Mem0 platform.

Add commerce and payment workflows to Claude Code projects: Stripe and PayPal payments, Plaid financial data integration, HubSpot CRM, and Algolia search — enabling subscriptions, checkout, and customer management.

Implement Domain-Driven Design with tactical patterns (aggregates, entities, value objects), CQRS, event sourcing, and saga orchestration. Design bounded contexts, map integration contracts, and build event stores with read models for scalable, event-driven systems.

Design, build, and deploy MCP servers for Claude by interrogating your use case to select deployment models like remote HTTP, MCPB, or local stdio, implementing tool patterns with auth, adding interactive UI widgets such as forms, pickers, and dashboards for inline chat rendering, and packaging into standalone Node or Python .mcpb bundles for local distribution without user toolchain.

Automate professional equity research workflows: generate earnings reports, initiating coverage, pre-earnings analysis, morning meeting notes, and sector landscapes. Screen stocks, track catalysts, update financial models, and maintain investment theses with cited sources.

Provides structured guidance for executing cybersecurity operations across penetration testing, incident response, threat hunting, cloud security, and malware analysis, with step-by-step procedures and tool usage.

Generate sector and thematic market research reports including industry overviews, competitive landscapes, comparable company analyses, and investment idea shortlists. Automates creation of structured .pptx and Excel outputs for financial analysis workflows.

Ingest GP valuation packages, run portfolio-company marks through valuation templates, compute NAV and waterfall, and stage LP reporting for IR review in private equity workflows

Perform the full ML lifecycle on Hugging Face Hub: create and manage datasets, find and evaluate models, fine-tune with TRL or Unsloth, build and deploy Gradio demos on Spaces, log training metrics, and publish research papers — all via CLI or agent skills.

Invoke MiniMax AI skills to scaffold React/Next.js frontends, fullstack apps with Node/Python/Go backends, Flutter/React Native/Android/iOS mobile projects; generate/edit DOCX/PDF/PPTX/XLSX files; produce GIF stickers, shaders, music playlists/videos; analyze images via CLI workflows.

Delegate specialized coding tasks to domain-expert subagents for building blockchain DApps and smart contracts, secure fintech payment systems with compliance, Unity-based games with multiplayer networking, scalable IoT edge solutions, native/cross-platform mobile apps, API documentation, quant trading models, and risk management frameworks.

Forces high-agency, exhaustive problem-solving when Claude detects frustration, repeated failures, or passive behavior — applying structured debugging, proactive investigation, and role-based engineering personas (P7–P10) inspired by Chinese tech corporate culture. Includes agents for task decomposition, code execution, review gates, and verification loops.

Build, integrate, and debug AI copilot features in React apps using CopilotKit — add chat interfaces, register frontend tools, connect agent frameworks, and migrate from v1 to v2

Automates equity research workflows: reads earnings transcripts and filings, updates financial models with new data, generates professional post-earnings reports with variance analysis, and drafts morning meeting notes — all without live Excel, using Python/openpyxl for .xlsx output.

Automate KYC/AML screening of investor onboarding documents: parse identity, ownership, source of funds; apply risk rules; check sanctions/PEP lists; generate escalation packets for compliance sign-off.

Automate general ledger to subledger reconciliation: detect breaks, trace root cause to originating journal entries, classify break causes, and route exception reports for sign-off. Also audits spreadsheets for financial model errors and integrity.

Write SQL against warehouses like Snowflake, BigQuery, and PostgreSQL, profile tables, and generate interactive HTML dashboards or publication-quality Python charts — all from natural language, then share results via Google Docs or Jira.

Scaffold new Claude Agent SDK apps in TypeScript or Python by interactively gathering requirements, installing dependencies, and configuring projects. Verify apps post-creation or changes for SDK best practices, code quality, security, type safety, documentation, and deployment readiness.

Build production-grade n8n workflows faster with expert AI skills that validate and fix expressions, interpret errors, guide tool usage and node configs, provide architectural patterns, and generate JavaScript or Python code for Code nodes.

Run structured multi-LLM workflows across the Double Diamond process — research, scope, implement, and deliver with autonomous agents, code review, security audits, and TDD enforcement, all orchestrated via Claude Code.

Build and audit financial models (DCF, LBO, comps, 3-statement) in Excel, generate competitive landscape and pitch decks in PowerPoint, and access financial data from FactSet, PitchBook, Morningstar, and other sources.

Evaluate and improve LLM applications by instrumenting agents, chatbots, and RAG pipelines with DeepEval tracing, generating test suites, running evaluations, and exporting traces to Confident AI for observability and iterative refinement.

Spawn parallel AI subagents in isolated git worktrees to compete on tasks like code optimization, refactoring, test writing, or bug fixing. Evaluate results using pytest metrics or LLM judging on git diffs, rank agents, and merge the top performer into your base branch.

Generate professional briefing packs before each client meeting, including portfolio performance summaries, allocation analyses, talking points, and action items. Also creates quarterly investment reports and client proposals, outputting to .pptx files.

Build institutional-quality financial models (DCF, LBO, three-statement, and trading comparables) directly in Excel from a ticker and assumption set, with automated formula linkages, integrity audits, sensitivity tables exports as .xlsx files.

Run a full SEO audit on any website — crawl up to 500 pages, detect business type, and delegate to 15 specialist subagents that analyze technical SEO, content quality, backlinks, schema, Core Web Vitals, local SEO, e-commerce, and AI search visibility, then produce a health score and prioritized action plan.

Turns any Claude conversation into a persistent, self-organizing Obsidian wiki vault with hybrid retrieval, methodology-based filing (LYT/PARA/Zettelkasten/Generic), automated research loops, canvas management, pre-commit auditing, and health checks — enabling compounding knowledge that survives across sessions and projects.

Integrate semantic code analysis into your IDE via LSP for intelligent code understanding, refactoring suggestions, and seamless codebase navigation, powered by a remote MCP server.

Audit LP capital-account statements against the fund NAV pack before distribution — ties out balances, allocations, and fees, flags discrepancies, and checks spreadsheet formulas for errors, hardcodes, and circular references.

Automate month-end close tasks including accruals, roll-forwards, and variance commentary, and assemble a close package for controller sign-off.

Autonomously optimize code files by measurable metrics through iterative experiments: set up target file, eval command, and loop intervals (10min-monthly); AI edits code, commits to git branches, evaluates with Python, keeps improvements. Resume, run manually, or check dashboard status.

Audit and optimize paid advertising campaigns across Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, Apple, and Amazon Ads with 250+ automated checks, weighted scoring, AI creative generation, and deep-dive attribution analysis.

Automatically collect usage telemetry and session metadata across Claude Code lifecycle events (start, stop, end, user prompt submit) and check for pending skill notifications, using Python collectors via uv.

Install 124 ready-to-use Claude Code skills to automate 50+ third-party services including CRMs (HubSpot, Salesforce), PM tools (Jira, Asana), analytics (GA4, Mixpanel), cloud storage (Google Drive, Dropbox), GitHub/Vercel deploys, doc/PDF/image processing, React artifact building, design generation, and dev productivity tasks via Rube MCP/Composio integrations.

Run CodeQL and Semgrep to scan multi-language codebases (Python, JavaScript/TS, Go, Java, C#, Ruby, Rust) for security vulnerabilities via taint tracking and pattern matching. Parse, deduplicate, and aggregate SARIF outputs from scans, then integrate findings into CI/CD pipelines using GitHub Actions or bash scripts.

Delegate full-stack development workflows to Claude via 213 specialized agents, commands, and skills: refactor code, generate tests/deployments/Dockerfiles/K8s manifests, audit security/performance, document APIs/onboarding, orchestrate Git ops, and apply patterns across JS/TS/Python/Rust/Go/Java stacks.

Learn coding skills interactively with personalized tutorials and spaced repetition quizzes drawn from your own codebase. Use /teach-me for lessons, /quiz-me for practice with feedback, track progress, and sync tutorial data to a private GitHub repo.

Look up Python code examples and enforce Pythonic style — fetch syntax, concurrency, ML, and HPC references from pythonsheets.com while writing, debugging, or optimizing code, and get linting guidance for readable, idiomatic Python.

Accelerate preclinical life sciences R&D by connecting to biomedical databases (PubMed, ChEMBL, bioRxiv, clinical trials, Open Targets), analyzing multi-omics data (single-cell, RNA-seq, ATAC-seq), converting lab instrument files to standard formats, and generating Python parser code for data pipelines.

Provides a structured Plan/Work/Review workflow for solo developers, automating project initialization, task planning, code implementation with quality guardrails, CI/CD setup, deployment, and cross-session memory management. Integrates multi-agent collaboration (Cursor PM, Codex reviews) and browser automation for full-cycle contract development.

Automate web tasks with natural language: drives a local Playwright browser, captures screenshots and action logs, visually self-verifies results. Also generates reusable Python CLI tools from the workflows.

Generate SQL queries from natural language descriptions using your database schema for PostgreSQL, MySQL, or BigQuery. Analyze CSV or Excel user data to produce cohort retention heatmaps, engagement trends, churn insights, and research recommendations. Evaluate A/B tests for statistical significance, confidence intervals, lift, and ship/extend/stop decisions with Python-powered reports.

Generate PRDs, OKRs, outcome roadmaps, user stories, job stories, sprint plans, release notes, and stakeholder maps. Run pre-mortems for risk analysis, retrospectives for team feedback, prioritization frameworks, meeting summaries, and test scenarios with dummy data to manage agile product execution workflows.

Direct AI coding agents to create or update promptfoo evaluation suites with configs, prompts, tests, deterministic assertions, and provider setups following best practices. Streamline LLM eval coverage, regression debugging, and new eval matrix generation in JavaScript or Python projects using OpenAI or Anthropic models.

Implement Trail of Bits handbook security testing workflows: fuzz Rust, Python, C/C++, Ruby code with AFL++, libFuzzer, cargo-fuzz, Atheris; instrument AddressSanitizer; run static analysis via Semgrep, CodeQL; generate coverage reports, dictionaries, and bypass obstacles for vulnerability detection.

Automate the full lifecycle of academic research projects from literature discovery and review to experiment analysis, manuscript drafting, and reviewer rebuttals, while also offering code quality checks, git workflow enforcement, and project scaffolding for software development.

Audit smart contracts for vulnerabilities across Cosmos, Solana, Polkadot, TON, Algorand, and StarkNet blockchains using specialized scanners. Assess codebase maturity with scorecards, prepare for professional audits via static analysis and test improvements, analyze token integrations for ERC standards and risks, and apply Trail of Bits guidelines for architecture reviews and secure workflows.

Automate long-form webnovel creation: initialize projects interactively with genre/characters/worldbuilding/outlines, generate beat sheets/chapters (2000+ words), extract entities/relationships to SQLite indexes, visualize status/entity graphs in read-only dashboard, recover interrupted workflows, and validate chapters via agents for inconsistencies, pacing, OOC, reader pull, and quality reports.

Bridge IDA Pro with language models via MCP for AI-assisted reverse engineering, enabling natural language queries against disassembly, decompilation, cross-references, and database state using IDAPython scripting patterns.

Automate Korean daily life and work tasks through 90+ agent skills covering transportation booking (SRT, KTX, buses), shopping (Coupang, Daangn, Naver), food, real estate, government services, finance, and more. Each skill wraps Korean-specific APIs and services for agent-driven workflows.