Plugin registry

OpenLit telemetry for Claude Code: sessions, tool calls, edit decisions, and cost rollups.

Skills for the Cloudflare developer platform: Workers, Durable Objects, Agents SDK, MCP servers, Wrangler CLI, and web performance

Feature creation, selection, and transformation tools

Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI

AI Agent Skills for production-ready Go projects

Automated data preprocessing and cleaning pipelines

Set up ML experiment tracking

Agent Skills for optimizing web projects against Google Lighthouse, Core Web Vitals, WCAG 2.2, and modern SEO — performance, accessibility, SEO, and best practices.

Create data visualizations and plots

Deep learning optimization techniques

Ranked PR review list with dependency trees and filtered line counts.

Run your work like an AI agency, from a single Notion board. Agents discuss, plan, and execute tasks in parallel with dependency ordering and model routing.

Generate professional Statements of Work for AI projects

Interactive rebase workflow.

Engineering + Product + Operations + Legal + Design + Data Science + Security Operations + Developer Experience + Infrastructure Specialist + AI Operations team — 100 agents as Claude Code specialists. Infrastructure, DevOps, backend, security, ML/AI, mobile, UX, analytics, growth, revenue, content, PR, customer success, finance, people, operations, support, contracts, compliance, IP, governance, regulatory, color systems, typography, motion, accessibility, design tokens, forecasting, feature engineering, model training, drift monitoring, vector search, LLM fine-tuning, pen testing, detection engineering, incident response, zero trust, API docs, SDK design, developer onboarding, Kubernetes, Terraform, FinOps, service mesh, edge computing, caching, queuing, multi-cloud, chaos engineering, model deployment, LLM evaluation, AI observability, guardrails, prompt engineering, embeddings, ranking, and more.

Create Make.com (Integromat) scenarios with AI assistance - visual automation design

Walk through PR changes from the user's perspective.

Point it at a GitHub issue and get back a reviewed pull request. Hyperflow turns one AI coding session into a structured engineering pipeline: plan sharpens and decomposes the work, dispatch fans out parallel workers, and a domain specialist reviews every step — nothing ships unreviewed. 18 skills, 22 specialist reviewer and investigator agents, adaptive depth so a 5-line fix never triggers a deep run, and persistent per-project memory that lives in your repo and never leaves it. Runs on whatever model your session already uses — zero config, no API keys, no daemon. Works across Claude Code, Codex App/CLI, OpenCode, Grok, Antigravity, and Cursor.

Describe your app in plain English — Shipwright builds, tests, and deploys it autonomously via a 9-phase pipeline.

Compare local vs remote branch to detect rebase/merge mistakes.

Calculate and present ROI for AI automation projects

Detect anomalies and outliers in data

Run bin/claude-review --print and automatically fix all reported issues, committing each fix individually.

Run clustering algorithms on datasets

Build classification models

Amend a commit further back in history with fixup and auto-rebase.

Computer vision image processing and analysis

AI ethics and fairness validation

Git bisect to find the first bad commit by running a test command.

Design complex n8n workflows with AI assistance - loops, branching, error handling

Generate custom discovery questionnaires for AI agency prospects

120 marketing skills and 8 commands on one shared contract, arranged as a four-layer marketing operating system — Strategy (brand narrative), Channels (SEO/GEO, organic social, email, paid ads, influencer), Orchestration (product launch), and a shared Protocol layer of truth registries and memory. SEO/GEO (keyword research, content creation, technical audits, schema markup, programmatic/parasite/local SEO, site architecture, AI-traffic, monitoring), influencer marketing (audience insight, discovery, campaign planning, outreach, amplification, ROI tracking), paid ads across the ROAS loop, email marketing across the SEND loop, product launch across the RAMP loop, organic social across the ECHO loop (channel portfolio, voice dossiers, platform norm cards, calendars, platform-native creative, advocacy, social-quality audit, inbox/crisis ops, listening/SOV/dark-social measurement), and brand narrative & messaging across the TALE loop (message/positioning-truth tracing, durable message house, brand voice + naming canon, story bank, surface cascade, pitch narrative, enablement, proof packaging, the NQS gate, message testing, resonance and drift monitoring), plus a shared protocol layer (entity/creator/offer-claim/consent/launch/channel/narrative truth registries, project memory) serving all seven. Frameworks: CORE-EEAT, CITE, C3, ROAS, SEND, RAMP, ECHO, TALE.

Create multi-step Zapier Zaps with filters, paths, and formatters

Build AutoML pipelines

AI guide for game development with JEngine Unity hot-update framework

Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)

Automatic semantic memory for Claude Code — remembers what you worked on across sessions

Display Claude agent status in tmux window names via workmux

PostgreSQL documentation and best practices through semantic search and curated skills, including TimescaleDB and Tiger Cloud ecosystem tools.

Turn complex codebases into clear, navigable architecture diagrams

Extract subtitles/transcripts from YouTube videos via CLI or browser automation

Leverage OpenAI Codex (GPT-5/GPT-5.1) for non-interactive automation mode and hands-off task execution

Cloud-backed persistent memory powered by Deeplake — read, write, and share memory across Claude Code sessions and agents

Interactive feature development workflow from idea to implementation (Requirements → Design → Tasks → Execute)

Generate or edit images using Google Gemini API via nanobanana

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.

Claude Code settings and skills for spec-driven development workflows

GitHub Spec-Kit integration for constitution-based spec-driven development (7-phase workflow)