AI Agents & LLM Ops Skills for VS Code

    Skills for orchestrating multi-agent systems, building MCP servers, evaluating LLM outputs, and shipping production-grade prompt and retrieval pipelines.

    734 live ai agents & llm ops skills for VS Code.

    Prompt to Skill Converter with Grok (v1.4.1)

    by Markus Isaksson

    Free

    Transform repetitive, messy prompts into structured, reusable SKILL.md files for your AI agents.

    2
    235.0(1)

    ai coding checklist

    by Julian

    Free

    A 5-gate pre-flight audit to ensure your AI agent has the context, scope, and safety boundaries needed to code successfully.

    2
    15

    PromptDecoder Pro — AI Output to Prompt Converter

    by Brandon DeVries

    Free

    Paste any AI output. Get the production-ready prompt that made it.

    1
    12

    marm init

    by Ryan lyell

    Free

    The intelligent installer for MARM, providing cross-agent persistent memory and shared context via MCP.

    2
    95.0(2)

    Multi Agent Workflow Orchestration Architect

    by Shandra

    Free

    Designs controlled multi-agent workflows with clear roles, contracts, validation gates, approval steps, memory boundaries, audit trails, error handling, and fallback behavior.

    4
    3

    GoldBean — x402 Micropaid MCP Server

    by GoldBean

    Free

    120+ paid AI tool endpoints. Pay per use via x402 micropayments on Base (USDC). No API keys, no subscriptions.

    2
    3

    Agent Failure Recovery Protocol

    by PubsProToolkit

    Free

    A structured recovery framework to stop agent loops, handle malformed output, and manage autonomous error escalation.

    1
    2

    Agent Coordination Protocol

    by PubsProToolkit

    Free

    A structured protocol for AI agents to orchestrate sub-agents with role contracts and disciplined handoffs.

    1
    2

    nex webhook handler pattern

    by Nex AI

    Free

    Generate production-grade, idempotent FastAPI webhook handlers with signature verification and audit logging.

    6
    1

    More Concise AI Writing

    by Aman Garg

    $5

    AI output is full of padding, repeated information, and filler phrases. This skill cuts all of that while keeping the specifics and nuance that actually matter.

    3
    1

    Ironclad — Senior Software Developer

    by OnwireFlow

    $9.99

    Makes your coding agent work like a senior developer: exact money with no rounding errors, configurable rules, real audit trails, honest testing and review. Any stack, any country.

    2
    1

    Evidence Grading Framework

    by PubsProToolkit

    Free

    A reusable rubric that grades every source by type, recency, authority, independence, and corroboration, then ranks them and resolves conflicts by evidence weight.

    2
    1

    AI Feature Eval Writer

    by PubsProToolkit

    Free

    Design and write the eval suite for your LLM-powered feature — the metrics that match your failure modes, a golden dataset plan with starter cases, anchored rubrics, LLM-as-judge prompts with the known bias mitigations, and pass/fail gates wired for CI.

    1
    1

    nex site trust ext

    by Nex AI

    Free

    Ship a complete Manifest V3 website trust and safety checker extension with no build step required.

    5
    0

    nex reply ai ext

    by Nex AI

    Free

    Deploy a complete Manifest V3 Chrome extension for AI-powered replies in Gmail, Outlook, LinkedIn, and X.

    5
    0

    AI Design System Prompt Architect for Web UI

    by Shandra

    $7.99

    Creates complete AI-ready prompt systems and implementation-aware specifications for coherent web UI design systems, including brand direction, design principles, colors, typography, spacing, grids, tokens, components, interaction states, dashboards, landing pages, responsive behavior, accessibility, Figma guidance, frontend guidance, governance, testing, and quality control.

    3
    0

    Triadic Semantic Mapper

    by Sir Benjamin

    $60

    Eliminate circular reasoning and semantic drift by anchoring AI concepts in relational Subject-State-Object triads.

    3
    0

    Delegate AI Subtasks

    by Aman Garg

    $5

    Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.

    3
    0

    design product experiences

    by Carl Badenhorst

    $6.99

    Design, audit, and implement accessible product experiences with system consistency and Figma-to-code reconciliation.

    2
    0

    build with lovable

    by Carl Badenhorst

    $19

    Architect, build, and test Lovable applications with structured workflows and four-layer quality verification.

    2
    0

    Prompt Stress Test: Find Where It Breaks

    by Vladisav Jovanovic

    Free

    Give this skill a system prompt, agent prompt, workflow instruction, or structured-output prompt and let it find the cases most likely to break it. Stress-test ambiguity, missing context, contradiction, scope drift, schema pressure, correction uptake, tool failure, and authority boundaries before deployment.

    2
    0

    Backend Languages Pack

    by mochalatte

    $5

    Language-specific defense audits and rewrites for Go, Python, and TypeScript backends.

    2
    0

    Mini Game Product Architect

    by antara chindarkar

    Free

    Engineer differentiated, production-ready mini-game blueprints for HTML5 and mobile games using fantasy-first design, unique mechanics, scalable content systems, and professional game-product validation.

    2
    0

    PromptBase Template Builder Super Power

    by nowrich

    $5

    Builds and audits reusable prompt templates with typed variables, platform conventions, and hallucination guardrails.

    2
    0

    Why ai agents & llm ops skills work in VS Code

    Each skill on this page is a SKILL.md file built for ai agents & llm ops work and confirmed to run in VS Code. Install one into .vscode/skills/ in your workspace, start a new session, and VS Code follows the workflow the creator encoded instead of improvising from a short prompt.

    Listings are ranked by installs, upvotes and reviews, so what surfaces first is what other VS Code users actually keep. Free and paid skills compete on the same page, and every listing shows its security scan result before you download anything.

    Frequently asked questions