Claude Skills by agentskillexchange

Lets agents operate Google NotebookLM/Gemini Notebook through a Python API, CLI, skill, MCP server, or REST server to create notebooks, add sources, ask cited questions, generate artifacts, and download exports.

Use NotebookLM through MCP or a local REST API to run cited Q&A, generate Studio artifacts, and manage high-volume research batches.

Assess a public HTTP(S) page before building browser automation, extraction, or an integration. Use this skill to collect bounded structural evidence, readiness signals, risk flags, acceptance tests, and remediation priorities without sending credentials or accessing private targets.

5-phase repeatable structure for autonomous agent sessions: context-load, tiered work-selection, coordination claim, execute, and persist-learning. Prevents duplicate work across concurrent sessions and ensures every run produces durable artifacts. Runtime-agnostic — Claude Code, gptme, Codex, or any persistent-workspace agent.

Finds and compares 184,900 swimming spots worldwide (beaches, lakes, bathing places) with live water temperature, wind, UV and wave signals, local guides and source-backed activity providers, via the public BeachFinder MCP server.

Use MemoryBench to run repeatable conversational memory and RAG benchmarks across providers, datasets, judge models, checkpoints, and structured reports.

Run Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.

Use CC Safety Net when coding-agent CLIs need pre-execution hooks that block destructive commands, secret access, and unsafe file operations before tools run.

Use ZCF to initialize, update, and standardize Claude Code or Codex environments with prompts, workflows, MCP services, API settings, and backups.

Transcribes one explicitly authorized Brazilian Portuguese or Spanish audio or video file through the metered BRAINIALL API, then creates speaker-labelled JSON, SRT, and WebVTT with word timestamps and no automatic retry.

Runs an existing coding agent behind Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat, or HTTP so teams can invoke real agent sessions from chat without rebuilding the agent stack.

Let operators control local Claude Code, Codex, Cursor, Gemini CLI, and other coding agents from Slack, Discord, Telegram, Feishu/Lark, DingTalk, LINE, and WeChat Work.

Expose browser-use web automation through an MCP server so Cursor or another MCP client can operate websites with browser state returned to the agent.

Turn an existing coding agent into a supervised local work assistant that connects to workplace tools, reusable skills, workflows, and scheduled loops.

Use RocketRide to compose, run, observe, and deploy portable AI pipelines from an IDE or CLI across model providers, vector stores, and agent nodes.

Scaffold, run, inspect, and evaluate model-agnostic agents that connect to MCP servers, skills, shell tools, and workflow packs.

Scaffold, build, and run MCP servers from a predictable Python project layout with tools, prompts, resources, auth, and OpenTelemetry hooks.

Use Yao when an operator needs to package an AI agent workflow, hooks, MCP tools, memory scopes, and a reviewable web or chat interface into one deployable runtime.

Ingest documents into Morphik, expose retrieval over AI-app knowledge, and tune document search quality before handing context to agents or RAG workflows.

Compose coding-agent primitives in Rust, including tool execution, LLM streaming, sub-agent orchestration, memory, and MCP support, as an embeddable application workflow.

Use Bisheng to assemble, evaluate, and publish enterprise RAG and agent workflows across internal data, models, and business users.

Use JetBrains Koog to define typed, fault-tolerant AI agents that run inside JVM, Kotlin, backend, mobile, or browser contexts.

Use LlamaAgents to define async Python workflow steps, coordinate document-centric agent pipelines, and expose those workflows as services, clients, or deployable agent apps.

Use MCP Go to implement typed Model Context Protocol servers in Go that expose tools, resources, prompts, and transport handlers to agent clients.

Index private text into graph-backed retrieval structures, tune prompts, and query the resulting knowledge graph for RAG workflows.

Convert a bounded document set into a Neo4j knowledge graph, inspect extracted nodes and relationships, and use it for graph-backed RAG.

Use Faiss to create and query local vector indexes for agent retrieval and RAG workflows before adding heavier managed vector infrastructure.

Use LlamaCloud Services to parse, index, and manage document knowledge pipelines that feed LlamaIndex retrieval and agent workflows.

Store raw multimodal data, embeddings, and vector-search indexes in Deep Lake so agents can retrieve grounded context for RAG and analysis workflows.

Turn a repository or wiki into an interactive knowledge graph that agents and humans can search, explore, and query before implementation work.

Use deepdoctection when an agent workflow needs a local Python pipeline for document layout analysis, OCR, table recognition, and page-level extraction before LLM ingestion.

Build and maintain a repository-local context graph so coding agents can orient inside large codebases without rediscovering the same structure every session.

Use Memvid when an agent needs local, portable long-term memory and retrieval without running a vector database or full RAG service.

Use Strands Agents to assemble model-agnostic Python or TypeScript agent harnesses with tools, MCP, guardrails, tracing, streaming, and provider swaps.

Model Go-native agent systems with graph workflows, tool calls, memory, MCP, A2A, evaluation, and OpenTelemetry observability.

Give Claude Code a routed skill pack for designing, validating, debugging, and deploying n8n workflows through n8n-mcp.

Use TiDB when an agent needs one transactional SQL store that can also hold embeddings and serve vector retrieval for RAG, memory, or app-context workflows.

Use Vocode to compose transcription, LLM, speech synthesis, and telephony components into reviewable real-time voice-agent workflows.

Use Pipecat to define realtime voice and multimodal agent pipelines with transports, model providers, tools, and turn-taking tests.

Run a self-hosted Kotaemon document QA workflow so agents can index private files, ask grounded questions, and return cited answers.

Rewrite Chinese-first chat, status, docs, and public-writing drafts to remove AI-like phrasing while preserving facts, commands, numbers, terms, and responsibility.

Safely audits and removes Git worktrees linked to closed GitHub or GitLab issues with a mandatory scan-confirm-execute protocol and deterministic local validation.

Ask multiple model and CLI-backed coding agents the same question from Claude Code, then compare individual answers and a synthesized recommendation.

Use Xero MCP Server to give approved MCP clients controlled access to Xero accounting data, reports, invoices, contacts, and related business records.

Expose databases, files, code indexes, workflows, and policy-aware GraphQL through GraphJin's MCP and agent endpoints for governed discovery and action.

Use OpenRAG's built-in MCP endpoint so agents can ingest documents, search a knowledge base, create filters, and run RAG-backed chat against a deployed OpenRAG instance.

Use the built-in JetBrains MCP server to let Codex, Claude Desktop, Cursor, VS Code, and other MCP clients inspect and operate an open IntelliJ-based project.

Use ClaudeR to expose an active RStudio session to MCP-capable coding and research agents for R execution, plots, manuscript audits, and multi-agent analysis.

Force LLM outputs into typed schemas, enums, JSON-like structures, and routing records during generation instead of repairing malformed text afterward.

Use BlenderMCP when an MCP-capable agent needs to inspect, create, and modify Blender scenes through a controlled Blender bridge.