AI & LLM Integration for Claude Code

Search, discover, and install AI agent skills from 7 registries with quality scoring and cross-platform support

Structured framework for session-based, agent-driven development with modular prompts and audit checkpoints

Collection of Baidu AI Cloud skills including media processing, stock tracking, task management, and more

Complete set of Twilio skills for Claude Code. Covers Setup, Planner, Product, and Guardrail skills across SMS, Voice, WhatsApp, identity verification, compliance, and 30+ products.

AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 19 specialized agents, 22 commands, 30 skills, and 1 hook, 1 MCP server.

Per-project persistent memory in AGD format. Skill + SessionStart hook + MCP server, all driven by the agd CLI.

Inter-agent messaging for Claude Code sessions on the same machine.

Reasoning methodology layer for AI agents — classifies problems, routes to reasoning protocols, and validates designs before execution

CLI design for AI agents — evaluate, design, and refactor CLIs so they reliably serve humans, AI agents, and orchestration systems simultaneously. Structured output, self-description, delegated auth, safety tiers, and a complete 8-phase interaction loop.

Email and messaging skills for agent-driven workflows. Integration tools for automated email processing.

Ai2 Asta MCP — Semantic Scholar academic graph over MCP (no Python). Intent-to-tool routing, safe fields defaults to avoid context blowups, citation traversal, author lookup, snippet evidence retrieval, and DOI/arXiv/PMID via externalIds.

Bilibili anime frame & character organizer — download a bangumi/UP video (or local file), extract scene-change keyframes, split scenery vs character crops (anime person detection), then either cluster everyone by CCIP identity or pull ONE character out via a reference folder (one-vs-rest, distance-prefixed matches). Agent-native JSON envelope CLI with --dry-run, --schema, stable exit codes; optional OCR+LaMa subtitle/watermark removal.

Text-to-speech skill providing voice synthesis capabilities for content generation.

AI image generation via Alibaba Bailian, ByteDance Volcano Ark & Tencent Hunyuan — 23 models, Chinese text excellence, rich terminal UI, smart config

Drive the Pi coding agent from Claude Code — model-agnostic, works with whatever provider pi is configured for (DeepSeek, OpenAI, Anthropic, Google, Ollama, LM Studio, or any OpenAI-compatible endpoint). /pi:review with structured findings, /pi:adversarial-review for design challenges, /pi:rescue with background job control (status/result/cancel), and an optional stop-time review gate. No OAuth (API key only). 1:1 fork of openai/codex-plugin-cc with the runtime swapped from Codex to Pi.

Multi-platform Chinese TTS text-to-speech — 8 China-friendly backends (Edge/Doubao/CosyVoice/Azure/Tencent/Baidu/MiniMax/Xunfei), agent-native CLI with JSON envelope, schema introspection, auto-detect TTY, distinct exit codes (0/1/2/3/4), structured errors (code/message/retryable/field/backend), --fields filtering, dry-run, JSON provider registry, filterable HTML comparison page, voice cloning, SSML, emotion, dialects.

Turns Fable 5 into a token-frugal orchestrator: Fable keeps judgment, tiered Opus/Sonnet/Haiku agents do the labor.

OCPP protocol reference (2.1, 2.0.1 & 1.6J) for AI-assisted EV charging development

Send messages from Claude Code to WhatsApp. Direct communication channel for notifications and updates.

Agent skills for the FlagOS multi-chip AI inference platform. Includes kernel generation and optimization, model migration, environment verification, vendor onboarding, and more.

Zero-cost session handoffs for long-running agent work. Initializer + Coding Agent relay protocol with pluggable planning, multi-agent, and review spokes.

Multi-platform UI/UX design plugin for AI coding agents. Routes product flow, platform idiom, originality, motion, assets, and tokens before implementation.

Persistent memory system for Claude Code - Go implementation with SQLite and ChromaDB

One shared, durable memory for your AI coding agents — local-first, zero-dependency. Decisions, lessons and status that persist across sessions, tools and projects.

Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required

MCP server for AI-assisted Grafana dashboard, datasource, alerting, and incident management

Publish and review AI work on Workplane — the working plane between AI and humans

Translates natural language intents into unsigned DeFi transaction payloads across 13 protocols. Deterministic, no signing, no private keys.

5-phase guided workflow for creating production-quality image generation prompts for Nano Banana (Google's AI image generator). Supports brand presets, iterative revision, and reference image management.

Custom skills and commands that integrate Hyperspell into your project.

Install and run agentchannels from Claude Code via /ach:init-slack and /ach:serve

Automatic long-term memory for Claude Code via Hindsight

Skills for developing with Nutrient SDKs: Web Viewer, Document Authoring, Mobile (iOS/Android/React Native/Flutter/MAUI), Server (Python/Java/Node.js/.NET), self-hosted Nutrient Document Engine, and Nutrient AI Assistant.

Interactive PTY sessions for AI agents: local shell, SSH, serial port, and persistent remote sessions.

AI agent stack for DayZ modding. After install, run /dayz-init for a guided setup wizard that takes you from empty repo to mod-loaded-in-DayZ. Ships specialist subagents and DayZ slash skills covering the full mod pipeline (preflight, scaffold, build PBO, launch test, types.xml, RAG indexers), plus the dayz-rag MCP server for semantic search over vanilla Enforce Script and the Bohemia community wiki.

Skills for building AI features: routing, classification, search, database Q&A, summarization, parsing, tool use, content generation, translation, recommendations, redaction, record matching, data cleaning, anomaly detection, notifications, image understanding, text rewriting, chatbots, agents, scoring, moderation, API serving, and skill discovery

Point-of-use AI governance: a once-per-day pre-flight greeting showing your AI reliance and what your agents can reach, before you start a session. Local-first.

Career direction analysis: interview + AI usage pattern mining to identify roles AI won't replace

Learning layer for AI-assisted development. Domain-agnostic solutions architect with FSRS-driven concept teaching, 407 seed concepts across 18 domains, and dynamic concept management.

Discipline layer (not a capability transplant): verification grounding, completion evidence gate, systematic investigation, early-stop prevention, and value output style packaged for Claude Code, CLI, and local LLM adapters. Performance claims are deferred to bench/RESULTS.md.