Browse The Marketplace

    New in LLM Ops

    990 skills found

    designing hybrid context layers

    $10

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    6
    165.0(1)

    prompt engineer

    Free

    Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.

    22
    5894.7(7)

    Serum Sound Design (serum mcp)

    Free

    Let your AI agent design real Xfer Serum 2 presets and themed preset banks from plain-language requests.

    1
    28

    Eval Dataset Builder: Test Your AI Before Users Do

    Free

    Builds evaluation datasets for prompts, chatbots, RAG and agents: coverage matrix, realistic, edge, adversarial and refusal cases, deterministic graders and LLM-judge rubrics, validated JSONL (duplicates, leaks, schema), frozen test split, harness config and baseline report.

    2
    115.0(1)

    ai output quality gate

    Free

    Independently audit AI outputs for accuracy, evidence, instruction compliance, and release readiness.

    3
    175.0(2)

    MCP Server Builder: Ship MCP Servers Agents Use Well

    Free

    Designs, builds, tests and connects production-ready MCP servers in TypeScript or Python. Task-oriented tools with LLM-friendly descriptions, strict schemas, safe auth, token-cheap outputs, Inspector + agent evals, and configs for Claude Code, Desktop, Cursor and VS Code.

    3
    105.0(1)

    agent eval builder

    Free

    Design weighted, multi-layer evaluation suites with golden cases, guardrails, and LLM-as-judge rubrics for AI agents.

    1
    2

    Token Optimizer — Save 90%+ Tokens in Claude Code & Cursor

    Free

    Cuts AI coding agent token consumption by 75–94%

    0
    264.0(1)

    Google Sheets Rube Playbook

    Free

    Deterministic Google Sheets automation through Rube MCP: read, append, upsert, filter, and format with verified read-backs, not guessed tool calls.

    1
    5

    MCP VirtualBox

    Free

    Give your AI agent direct control to manage, snapshot, and execute commands inside VirtualBox VMs via MCP.

    0
    2

    local llm selection

    Free

    Technical framework for choosing local LLMs, sizing quantization to VRAM, and weighing QLoRA vs RAG.

    1
    2

    Add MCP Server: Ask Claude About Your App

    Free

    Adds a read-only MCP server to an existing app, any stack, so its owner can ask Claude or ChatGPT about their own data. Reuses your report queries, enforces scope, adds API keys and OAuth 2.1, tested with the MCP Inspector.

    1
    1

    llms.txt Audit & Generator

    NewFree

    Audit any site for a missing, stale or malformed llms.txt — spec compliance, freshness and every link checked — then generate a compliant llms.txt from the live pages.

    1
    1

    AI Content Guard — Prompt Injection & Hidden Char Scanner

    NewFree

    Local, deterministic scanner that screens untrusted content — files, emails, docs, repos, AI configs — for prompt injection, invisible characters, encoded payloads and config backdoors before your agent reads it. Zero network. Redacted reports.

    1
    1

    agent environment check

    NewFree

    Diagnostic tool to verify file paths, directory writability, and state persistence for AI agent skills.

    1
    1

    git commit conventional changelog

    NewFree

    Automate Conventional Commit headers and grouped release notes from git history.

    1
    1

    MLOps and LLMOps

    NewFree

    Version, deploy, monitor and scale models. 10 ordered skills.

    1
    1