uv plugins

Scaffold and develop production-ready Python projects with FastAPI, Django, and microservices using uv, pydantic, ruff, and pytest. Enforce best practices for async patterns, type safety, packaging, observability, and background tasks.

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.

Implement a complete QA and testing workflow: set up A/B tests with hard gates, automate browser testing with Playwright/Puppeteer, enforce code review checklists and TDD, debug systematically, and fix failing tests using pytest patterns.

Crystallize vague project requirements into executable Seed specifications through Socratic interviews, then run, evaluate, and iteratively refine them with three-stage verification, drift detection, and evolutionary loops.

Generate, edit, and inpaint images via GPT Image 2 CLI skill, using a reference prompt gallery to match styles for UI mockups, diagrams, posters, research figures, anime, and Chinese typography workflows.

Read, send, and manage Gmail messages; create and edit Google Docs, Sheets, and Slides; access and organize Drive files; manage Calendar events, Tasks, and Contacts; orchestrate Chat messages, Apps Script execution, and Custom Search via MCP tools from the command line or uvx.

Automatically learn from corrections across Claude Code sessions, building a project playbook and user profiles over time, while enforcing structured workflow gates for planning, TDD, brainstorming, and PR review.

Run local ONNX Runtime model inference via an HTTP daemon, with automatic provisioning of Python and ONNX Runtime using uv, and lifecycle management through session hooks.

Package, release, and distribute Python libraries with modern tooling: pyproject.toml, build backends, PyPI publishing, and GitHub Actions automation. Includes workflows for testing, documentation, security auditing, API design, CLI building, and release management.

Build Bridgic amphibious agents with LLM-driven reasoning and deterministic workflow execution, automate browser tasks like login-gated page access and social media scraping, and scaffold complete Python projects from task descriptions using a CLI pipeline with OpenAI/vLLM backends.

Build annotated collections of research papers by retrieving PDFs from arXiv, DOIs, titles, or sci-hub; extract structured notes, claims, concepts, justifications from them; cross-reference citations, identify new leads, tag, audit directories, and integrate into propstore knowledge stores via CLI workflows.

Develop, test, and deploy Fastly edge applications with VCL linting/formatting, local WASM execution, CDN service management, WAF auditing, and XVCL transpilation for modular configurations.

Extend Claude Code with specialized AI agent skills for structured brainstorming, multi-agent orchestration, cross-model code review, git operations, Python tooling (uv, ruff, ty), TUI design patterns, and Tilt-based Kubernetes development workflows.

Formalize scientific papers, textbooks, or knowledge sources into structured Gaia knowledge packages via a six-pass process: extract propositions, connect reasoning, assign priors, compile DSL to IR, then generate Obsidian vaults, Mermaid graphs, READMEs, and publish to GitHub.

Manage Pipefy business processes, pipelines, cards, and automations directly from Claude Code. Create and configure AI agents, database tables, portals, and reports; automate workflows with if/then rules and prompt-driven logic; and monitor execution logs and usage stats — all through MCP tools and GraphQL API fallbacks.

Controls a local Stata installation from AI agents to run do-files, inspect datasets, check stored results, export graphs, and execute econometric workflows like causal inference, regression audit, and publication review.

Synthesize Zotero collections of academic papers into theoretical maps, thematic clusters, and identified debates for deep literature analysis before writing research papers or reviews.

Clone untrusted Python dependencies from GitHub, decompose them into verifiable sub-packages via test-driven evaluation, generate focused pytest unit tests, rewrite imports, and iteratively implement secure from-scratch replacements to mitigate supply chain attacks.

Run 47 ENCODE genomics research skills and 20 API tools from Claude Code — search experiments, download files with MD5 verification, execute Nextflow/Docker pipelines (ATAC-seq, ChIP-seq, RNA-seq, etc.), cross-reference 14 databases (GTEx, ClinVar, GWAS, gnomAD, Ensembl), track provenance, and generate publication-ready methods sections.

Convert binary Office documents, PDFs, and images to structured Markdown preserving headings, tables, and lists, enabling Claude to read formats it normally garbles like .docx and .pptx.

Download videos from 1800+ platforms like YouTube, TikTok, and Twitter, then auto-generate MP4 files, MP3 audio extracts, VTT subtitles, TXT transcripts, and Markdown AI summaries. Everything saves directly to your downloads folder for easy access and reuse in projects.

Automate end-to-end maintenance of Python/ML open-source projects on GitHub: triage and analyze issues/PRs/discussions, resolve PR conflicts with attributed fixes, conduct multi-agent code reviews for quality/security/performance, prepare release artifacts/changelogs/migration guides, and optimize GitHub Actions CI/CD pipelines.

Index multimodal directories, explore/search files, extract text/images/keyframes from PDFs/videos, and process visuals via natural language with Orion VLM agent for OCR, object detection, summarization, and multi-modal generation.

Authenticate with Yutori to deploy persistent web scouts that monitor competitors, APIs, changelogs, and market changes, plus run deep multi-source research and automate browser interactions like form filling and data extraction.

Develop, test, debug, review, and migrate Keboola Python components for data pipelines—including extractors, writers, apps—with AI skills for config schemas (conditional fields, UI), code quality (Ruff, architecture), local datadir/pytest/VCR testing, uv/pyproject.toml upgrades, Docker builds, and platform context via MCP/Datadog.

Generate domain-specialized images like banners, ads, YouTube thumbnails, illustrations, logos, product photos, portraits, and web assets via Google Gemini. Uses auto-built prompts, keyword triggers, format/aspect ratio detection, and reference image editing for quick design workflows.

Bootstrap Claude Code with 17 specialized agents, skills, and hooks to audit/evolve .claude/ configs, engineer/refactor Python code via TDD, profile/optimize ML workloads, generate docs/tests, design systems, diagnose issues, and manage workflows professionally.

Orchestrate autonomous Claude-based research agents to investigate hypotheses, spawn experiment runners that execute Python scripts and analyze outputs with LLM judges, generate interactive Quarto HTML reports, send supervisor notifications, perform fresh-eyes reviews, and run batch evaluations.

Summon Python specialists to scaffold production Django/FastAPI projects with uv/Docker/PostgreSQL, enforce Mypy/PEP8/security reviews, audit codebases for multi-agent parallelization, implement Celery tasks/WebSockets, and generate pytest strategies—all using 2025 patterns and official docs.

Run fully autonomous AI coding sessions that generate step-by-step plans, execute tasks with self-critique and best practices, enforce file policies to prevent clutter, block risky commands via safety guards, manage tmux for isolated testing, and export refined plans.

Provides AI agents to prepare startup fundraising materials: score pitch decks against investor criteria, validate financial models for unit economics and runway, simulate VC investment committee simulations, and build TAM/SAM/SOM market sizing

Automate full dev lifecycle: summarize branches and uncommitted work, generate conventional commits, create/triage GitHub PRs, polish code per guidelines, safely upgrade deps with pnpm/uv, extract action items from transcripts/Slack into Linear tickets, and produce handoff docs.

Extract text and structured data from single or batch PDFs to Markdown or TXT via CLI, using 9 backends with automatic fallback and OCR for scanned documents.

Manage Bauplan data lakehouses end-to-end: safely ingest S3 data via Write-Audit-Publish with quality gates and atomic merges, explore schemas/tables/profiles using Python SDK, create SQL/Python transformation pipelines, generate Polars-based quality expectations, assess data fitness for business questions, and debug failed jobs with pinned snapshots and Git fixes.

Automate end-to-end Linear workflows from CLI: triage issues into prioritized tickets, create git branches with ticket IDs, commit/push changes, and open linked GitHub PRs; manage projects, milestones, documents, and cross-repo coordination.

Automate ASDA grocery shopping entirely from the terminal by searching products, managing your basket with add/remove/view actions, authenticating your account, booking delivery slots, and placing orders.

Run an autonomous optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time, and more.

Automate document processing workflows with Nutrient DWS API via Python client and uv CLI scripts. Convert, merge, split PDFs; run OCR; extract text, tables, key-value pairs; apply watermarks, redactions, signatures; optimize, protect, reorder pages; chain into custom multi-step pipelines.

Run four-layer tests on Claude Code plugin skills to validate structure, check trigger accuracy, simulate multi-turn sessions, and compare skill outputs using Python scripts and Bash commands.

Navigate and analyze codebases semantically with tree-sitter: search symbols by regex, trace call sites and usages, explore class APIs and structures, grep files and contents, scan git commit history, query configs via jq or XPath, and switch workspaces—all locally without LSP setup.

Collect real human opinions—surveys, preference comparisons, ratings, and rankings—directly from within Claude Code to integrate human feedback into your workflows.

Securely install, scan, audit, and monitor packages across 14 ecosystems (npm, yarn, pnpm, bun, pip, uv, poetry, cargo, go, gem, composer, nuget, hex, pub) with CVE detection via OSV.dev, auto-fixes, severity triage, dependency audits, and continuous email alerts using INFYNON CLI and agent.

Perform thorough reviews of Python tests in code or projects using a standard checklist that evaluates isolation, mocks, execution time, flakiness, and naming clarity to uphold high testing standards.

Persistent three-screen side panel (main, status, ambient) that runs alongside Claude Code with automatic session checkpointing, context prompts, and lesson extraction

Persist decisions, specs, and architectural constraints across Claude Code sessions as a context companion. Bootstrap canonical OpenSpec by interactively setting product details, discovering codebase modules via Bash, and mining historical sessions into a module registry. Initialize sessions suggesting recent git changes, load or reconcile prior specs, with hooks automating on edits and session events.

Extract timestamped transcripts from YouTube videos using a simple CLI command. Input any video URL to download formatted text files for content analysis, documentation, or review workflows, bypassing manual transcription entirely.

Scaffold opinionated Django projects with one-file-per-model organization, Ninja APIs via domain-grouped routers and Pydantic schemas, Unfold admin with HTMX and Tailwind, pytest tests using factory_boy, Dynaconf config, uv deps, and Docker setup. Delegate code reviews to the agent to enforce patterns after changes.

Fetch WeChat Official Account article data via JZL API to track today's publishing status by name, biz, or URL; retrieve paginated historical lists; and convert short-to-long links with biz extraction. Unlock operations workflows for competitor analysis, market tracking, social media monitoring, and content marketing productivity.

Sync and lazy-load remote skill catalogs from DeepVista, with OAuth authentication and session lifecycle hooks for context capture and cleanup.

Reformat markitdown-generated Excel Markdown files into clean, readable multi-sheet documents via analyze-transform-merge pipeline. Convert .xlsx files or directories directly to validated reformed.md outputs, cleaning NaNs, unnamed columns, empty rows/columns, and ensuring table integrity with parallel sheet processing.

Build and audit production-grade Python packages with best practices for project structure, tooling (pyproject.toml, Ruff, mypy), testing (pytest, CI matrices), CI/CD (GitHub Actions, trusted publishing), documentation (MkDocs, Diataxis), API design (sync/async, pluggy), packaging (wheels, sdists, cibuildwheel), versioning (SemVer, changelogs), security (Sigstore, Dependabot), and developer experience (one-command setup, Makefile).

Scan AI agent code and runtime sessions for OWASP LLM Top 10 vulnerabilities via static and dynamic analysis, apply contextual fixes to issues like prompt injection and data leaks, generate markdown compliance reports with SOC2 mapping, correlate findings with evidence, and gate deployments until critical issues resolve.

Map your repo structure to detect naming clashes and doc gaps, track cross-session goals and learnings, build evolving narratives from git history, and auto-generate READMEs—persisting tribal knowledge for fast code exploration.

Run adaptive autonomous SDLC workflows that orchestrate agent teams to implement Python features via enforced TDD/BDD cycles with pytest-bdd scaffolding, git worktree isolation for parallel tasks, Beads CLI for dependency-tracked issue management, ruff/mypy/pytest verification pipelines, documentation updates, PR creation, and automated merges.

Develop STM32 firmware with AI agents that generate HAL peripheral init code, debug HardFaults and bus issues, search full documentation, optimize low-power modes, configure bootloaders and security, analyze safety compliance, and review hardware designs.

Install and configure gcallm CLI to add Google Calendar events using natural language from text, files, clipboard, or screenshots directly in Claude Code. Query schedules, list calendars, and manage via integrated MCP server.

Consult Google Gemini 3 Pro for debugging, code review, architecture advice, and image generation (diagrams, infographics) directly from Claude.

Generate images from text prompts, edit existing images, and compose collages using Google GenAI via the Zenmux API, specifying aspect ratios from 1:1 to 21:9 and resolutions from 1K to 4K, all through a Python CLI managed with uv.

Run a local MCP server to generate videos with OpenAI Sora, images, and audio using multimodal APIs. Access integrated prompting guides, tool references, model selection tips, and best practices for effective media workflows requiring OPENAI_API_KEY and media file paths.

Write idiomatic MLX code for machine learning on Apple Silicon, implementing arrays, neural networks, training loops, lazy evaluation, unified memory, Metal GPU acceleration, and PyTorch migrations.