Best AI Agent & LLM Ops Skills for Claude Code

prompt-engineer

Popular

Free

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

Writes clear pull request descriptions by analyzing your branch diff. Covers what changed, why, how, and what to test. Works with GitHub, GitLab, and Bitbucket.

Give AI agents the ability to trace decision chains, reconstruct causal sequences, and reason over complex event timelines spanning months or years.

Deploy a hierarchical team of AI agents to perform 15-30 minute deep-dive research with parallel execution.

ai-productivity

Popular

Free

High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.

The "Skill for building Skills": Automate creating, testing, and optimisation of custom workflows.

Reduce Manus v5 credit consumption by 30-75% through intelligent task routing and autonomous strategy selection.

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.

Query Web3 and on-chain GraphQL endpoints using natural language via the Model Context Protocol.

Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.

Ultra-fast discovery and routing for large-scale AI agent skill libraries.

agent-handoff-orchestrator (for hermes agent / openclaw)

Free

Generate high-fidelity, structured handoff packets for seamless multi-agent collaboration and session persistence.

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

Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.

Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.

Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.

agent-workflow-controller

Free

Design and audit complex multi-agent workflows with rigorous ownership, evidence gates, and failure recovery policies.

Instantly diagnose any skill or prompt and get a clear, prioritized report on what’s wrong and how to fix it — across any agent.

Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.

RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

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

Autonomous research and task loop that builds on previous findings to solve complex objectives while you sleep.

Reliable, health-gated autonomous operations for agents in restricted or sandboxed terminal environments.

Builds the organizational memory schema your AI agent needs to answer why — capturing decision provenance, causal chains, and event context that embedding-based retrieval permanently discards.

AI Coding Prompt Refiner for Better Developer Results

Free

Transforms vague coding requests into precise, scoped, testable, AI-ready prompts for Cursor, Claude Code, Codex CLI, Replit, and other coding agents.

Eliminate hallucinations and errors using double-blind, multi-agent adversarial verification loops.

Audit AI agent memory files for privacy risk and bloat.

Design and evaluate production-grade observability systems using the 12-layer Full Stack Observatory reference model.

Comprehensive security auditing for AI agents, covering prompt injection, tool permissions, and data leakage risks.

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

Quickstart guide to connect your AI agent to the Agensi marketplace via Model Context Protocol (MCP).

Expert AI guidance for ISO-compliant cleanroom design, HVAC filtration setup, and controlled environment installation.

Battle-tested orchestration framework for running 3+ Claude Code agents in parallel. Covers task routing, denbun handoff protocol, exponential-backoff retry, rate-limit guards, structured JSON logging, and automated self-healing — patterns from real production deployments.

Turn erratic AI tool calls into a reliable, verified, and safe execution strategy.

Transform raw ideas into high-performance, structured prompts optimized for Grok’s reasoning and wit.

Real-time Gate.io and Bitget arbitrage scanner with cross-chain verification and net profit filtering.

Automatically detect, load, and stack the perfect skills combo for any user request.

Design, debug, and harden AI control loops with explicit contracts and automated verification harnesses.

Enterprise Automation Engineering Architect

$50

or 250 cr

Designs and upgrades business automation systems into modular, reliable, observable, secure, low-maintenance, enterprise-grade workflows.

Turn your AI agent into a coordinator that manages parallel subagents for complex coding and research tasks.

production-agent-architect

$6

or 30 cr

Architect, scaffold, and harden production-grade AI agents with battle-tested patterns and systematic evaluation.

Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.

Secure, guardrail-first Render deployments and service management via MCP with mandatory approval gates.

Safe, read-only discovery and gated deployment control for Vercel projects via MCP.

Architect high-fidelity, theologically-grounded AI personas and 'person-use' skills for ministry and biblical study.

Turn live Agensi marketplace signals and high-signal user data into actionable product development intelligence.

The security auditor for AI agents. Detect prompt injection, secret leaks, and unsafe tool access in SKILL.md files.

Coordinate specialized AI agent roles for complex planning, implementation, and verification workflows.

Custom Data RAG Chatbot Builder

$5

or 25 cr

Build a full-stack AI chatbot trained on your own documents across any industry — legal, healthcare, e-commerce, HR, finance, real estate, insurance, education, cybersecurity, government, and more.

Instantly diagnose and fix why your AI agent skills aren't triggering when they should.

Evidence-Grading Framework — Rank Source Quality Before Your Agent Writes

$18

or 90 cr

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

AGENTS.md & Agent-Config Quality Gate — Catch Ambiguous Rules, Conflicts & Missing Guardrails Before You Ship

$12

or 60 cr

An adversarial reviewer for AGENTS.md and agent instruction files. It flags ambiguous or contradictory rules, missing guardrails, vague tool and scope definitions, and untestable instructions, then returns a PASS / REVISE / BLOCK verdict — before the config drives your agent.

Bridge OpenCode to the Agensi marketplace to discover, install, and chain AI agent skills via MCP.

Diagnose and fix broken local LLM stacks, GPU issues, and stalled model downloads across Ollama, LM Studio, and more.

Turn Agensi marketplace signals and community requests into a prioritized roadmap of high-demand skill ideas.

Audit and fix your website's visibility for AI agents like ChatGPT, Claude, and Perplexity.

AI Eval & Test-Suite Quality Gate — Catch LLM Evals That Lie Before You Ship

$14

or 70 cr

An adversarial gate that audits an AI eval or test suite — LLM-judge rubrics, datasets, regression tests, metrics — for gameable criteria, data leakage, missing edge cases, and non-determinism, then returns one PASS/REVISE/FAIL verdict.

Contextual Understanding (SRT)

Free

Eliminate context drift and enhance depth with a multi-layered active reasoning framework for agents.

Optimization-Loop

$19

or 95 cr

Autonomous loop that iteratively modifies, evaluates, and selects the best version of any text resource — skills, prompts, or campaigns — using a modify-measure-keep/discard cycle.

Professional AI-powered redesign and beautification for PowerPoint and PDF slide decks.

🧠 AI Memory Optimizer

$7

or 35 cr

Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.

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

Establish a disciplined, issue-driven agentic operating model with automated tracking and strategic human-in-the-loop.

Transform brittle prompt chains into robust, artifact-driven DAG workflows with hard gates and explicit traces.

AI-Generated Code Review & Test-Coverage Gate — Catch Untested Paths, Silent Changes & Over-Confident Bugs Before You Merge

$15

or 75 cr

An adversarial reviewer for AI-written code changes. It pressure-tests a pull request or diff for untested branches, silent behavior changes, missing edge cases, over-confident code that only looks right, and weak tests, then returns a PASS / REVISE / BLOCK verdict before the change merges.

Maintain durable, lean, and consistent AI agent memory across sessions while preventing context bloat and data leaks.

Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.

Apply the 5-step engineering algorithm to ruthlessly delete, simplify, and accelerate any process or codebase.

Generate a production-ready 3D virtual office for AI agents using Next.js and React Three Fiber.

Adaptive GDPR, CCPA, security, and AI compliance audit with severity-graded findings and law citations

Investment analysis across stocks/funds/bonds/real-estate/crypto. Valuation methods, risk frameworks, portfolio construction.

Enterprise-grade project orchestration for breaking complex work into phases, dependencies, and agent workstreams.

Agent Skill Pricing & ROI Calculator

$50

or 250 cr

Calculates value-based pricing, ROI, buyer segmentation, and monetization strategy for AI agent skills across marketplace, B2B subscription, and enterprise sales models.

Convert a repeatable workflow into a reusable agent skill or staged skillchain candidate.

Specialized static security scanner for MCP servers and Python tool handlers to prevent injection and data leaks.

🗂️ Model Inventory Auditor

$13

or 65 cr

Inventory every LLM model and provider your code depends on, the AI bill of materials, and flag the dependency risk. It lists each provider, model, and where it's used, then flags hardcoded model ids, single-provider dependency with no alternative, the same model referenced by different ids, model ids with no config or env indirection, and providers pinned in your manifests. Recognizes OpenAI, Anthropic, Google Gemini, and more from an editable list.

Deploy production-grade, AI-powered Telegram bots to Raspberry Pi with automated server hardening and scheduled jobs.

AGENTS.md and llms.txt Writer-Reviewer — Make Your Repo and Site Agent-Ready

$12

or 60 cr

Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.

Port your AI agent skills across Grok, Claude, Cursor, and Copilot using a professional two-layer architecture.

Deploy a self-hosted, private RAG system with pgvector, Ollama, and a Telegram interface for your personal notes.

Custom Enterprise Skill Discovery Consultant

$10.99

or 55 cr

Discovers and ranks internal enterprise processes that can become custom agent skills, with ROI estimates, governance needs, and pilot roadmaps.

Run a buyer-readiness check before publishing an AI agent skill package.

Production-grade 3-layer agent orchestration with dual-blind verification and automated model routing.

Generate structured architectural technical specifications and draft 'lastenboeken' from project descriptions.

HandoffPilot

$19

or 95 cr

Save a coding agent's full working state to a handoff file before it hits the context limit, then resume in a fresh session without re-explaining everything. Captures the active plan, git branch, uncommitted changes, decisions, blockers, and next steps, so Claude Code or Codex picks up exactly where it stopped instead of starting cold.

📝 Prompt Template Linter

$12

or 60 cr

Lint a prompt template for the issues that cause injection and flaky output. Flags untrusted variables interpolated straight into the instructions (the injection surface), placeholders that are never provided or never used, contradictory instructions, a missing output-format spec where the result is parsed, unbounded context interpolation, and leftover placeholders. It detects problems; it does not write prompts.

Canonical Next.js bridge for secure, real-time communication between browser UIs and local agent gateways.

agent-ready-cli

Free

Audit any website for AI agent-readability and protocol compliance using the Agent Ready CLI.

Transform business ideas into deployment-ready autonomous company blueprints for multi-agent frameworks.

agent-ready-api

Free

Score and optimize any website for AI agent-readability using the Agent Ready REST API.

RAG Architecture & Debugging

$9.99

or 50 cr

Design, diagnose, and optimize high-performance RAG systems with an engineering-first framework.

Structureert een veiligheidsrondgang op de werf in een concept-vaststellingenrapport: risicopunten per zone, ernst, verantwoordelijke en opvolging: naast (niet in plaats van) de veiligheidscoördinator.

High-reliability Dutch content engine with a Claude-Gemini-Qwen fallback chain and template safeties.

A universal, multi-role AI engineering team for autonomous planning, implementation, and rigorous code review.

skill-auditor

$5

or 25 cr

Audit, score, and improve your AI agent skills for higher quality, lower token costs, better reliability, and marketplace success. Get actionable recommendations for prompts, instructions, tool usage, error handling, and user experience.

Turn vague prompts into professional task specifications, optimized prompts, and verification test suites.

The TweetClaw

$7

or 35 cr

Professional X/Twitter automation for AI agents: Post, monitor, extract data, and manage engagement via 99 API endpoints.

Multi-Agent Orchestration Patterns Library

$12.99

or 65 cr

Every orchestration topology — sequential, parallel, hierarchical, map-reduce, critic-actor — selected and designed for your exact workflow. Full system design with agent roles, interfaces, routing logic, and error paths.

Master subagent orchestration in Grok Build CLI to parallelize complex coding tasks and maintain context focus.

Automated Belgian fiscal valuation of usufruct and bare ownership for notarial deeds and tax calculations.

Deploy a structured, long-term memory palace for AI agents on Raspberry Pi via MCP and ChromaDB.

Advanced Polymarket agent that trades the private market segment, specifically focussed on IPO timing, mispricings and cross-market arbitrage opportunities.

An autonomous agent that scouts real-world demand signals to find and rank high-leverage revenue opportunities.

Generate a JSON-backed, agent-callable task CLI with recurrence and prefix-ID matching.

Elite Cloudflare Agent

$7

or 35 cr

Build stateful AI agents with persistent memory, SQLite, and cron scheduling on Cloudflare's global edge network.

Extract structured, evidence-backed AI persona profiles from historical chat logs, emails, and documents.

🩺 llms.txt Doctor

$9

or 45 cr

Generate an llms.txt for your site and validate an existing one against the spec. The generator turns your sitemap.xml or docs folder into a clean, sectioned llms.txt with one-line descriptions. The validator flags a missing H1 title, a missing summary blockquote, malformed link entries, links with no description, relative URLs that should be absolute, and a referenced llms-full.txt that is not present.

Monitor any website for price drops, stock changes, and content updates. Sends clean Telegram alerts with smart change detection.

Prompt-Injection & Agent-Security Gate — Block Hidden Instructions Before Your Agent Acts

$14

or 70 cr

An adversarial security gate that audits untrusted content — web pages, tool outputs, documents, emails — for embedded instructions, exfiltration, and authority spoofing, then returns a SAFE/REVIEW/BLOCK verdict.

A production-ready Python integration for Gemini using a unified AIProvider interface for easy model swapping.

Agent Spend Guardrails

$19

or 95 cr

Define spending rules for your AI agent — caps, category whitelists, approval thresholds — and audit what it bought or almost bought, with an approve/hold/block verdict per transaction.

🛡️ Model Resilience Linter

$12

or 60 cr

Find the LLM integration code that will not survive a provider being pulled or going down. Flags single-provider lock-in with no alternative, calls with no failover branch, missing timeouts, retries with no limit or backoff, no degraded-mode default, and hardcoded endpoints with no alternate. This is about the model going away, not the model declining.

Subagent Workflow Patterns To Boost Output Quality

$9

or 45 cr

Deploy 6 battle-tested multi-agent orchestration patterns to eliminate agent laziness and boost output quality.

a2a-agent-interoperability-launch-pack

$7

or 35 cr

Turn multi-agent intake into client-ready A2A readiness reports, task contracts, and orchestration topologies.

ai-agent-production-hardening-kit

$12.99

or 65 cr

Transform fragile AI prototypes into resilient, enterprise-ready production agents with professional hardening tools.

Optimize task execution by intelligently dispatching work to parallel subagents with ready-to-paste prompts.

Agent Loop - Autoresearch Optimizer

$5

or 25 cr

An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.

Audit AI/LLM spend across OpenAI, Anthropic, AWS Bedrock, Azure. Find waste, project runway, FinOps report. Free scripts.

Intelligently audit your repo and workflow to recommend, install, or create custom AI agent skills.

No Code App Idea Builder Agent

$9.99

or 50 cr

Creates practical no-code app ideas, MVP briefs, and AI-ready prompts for tools like Bolt.new, Lovable, Cursor, Replit, and single-file web app builders.

Unit & Integration Test Generator — Write Tests That Actually Catch Bugs (Edge Cases, Error Paths, Mocks)

$12

or 60 cr

Generate a real test suite for any function, module, or file — meaningful edge cases, error paths, boundary conditions, and proper mocks, not happy-path stubs. Detects your project's framework and conventions, plans the cases deliberately before writing, and hands back runnable tests plus a summary of what's covered. Built to write the tests that actually catch bugs.

Diagnose RAG bottlenecks with precision metrics (Recall, MRR, nDCG) to identify retrieval or ranking failures.

Audit your AI agent's evaluation coverage to identify missing release gates and production risks.

🤖 AI Agent Auditor

$7

or 35 cr

Analyzes AI agents for performance, reliability, security, and optimization opportunities.

AI Automation QA & UAT Pack

$5

or 25 cr

A QA lead for AI automations and agent systems — turns a delivery into acceptance criteria, UAT scripts, a non-determinism test plan, a failure-mode matrix, and a client-ready sign-off pack, or audits an existing automation for the gaps that cause silent production failures.

Intelligently delegate tasks to Claude, Codex, or Gemini based on cost, model strengths, and rate limits.

llms.txt Generator — Create a Spec-Compliant llms.txt & llms-full.txt for Your Site or Repo

$12

or 60 cr

Generate a spec-compliant llms.txt (and optional llms-full.txt) for your site or repo so AI agents and crawlers can navigate it. Curates the pages that matter, writes the exact llmstxt.org structure — single H1, blockquote summary, and link sections in the precise format agents parse — then validates the format and tells you where to put it. The honest version: a low-cost, machine-readable surface for the agentic web, not an overhyped SEO trick.

Generate a production-ready Python client for Alibaba Qwen models with text, vision, and reasoning tag filtering.

Evidence Integrity Gate — Stop AI From Shipping Unsupported Claims in High-Stakes Content

$34

or 170 cr

Runs an ordered evidence-integrity gate over any AI draft — grade sources, ground claims, verify technical assertions, stress-test — then returns one PASS/REVISE/FAIL ship decision.

Build production multi-agent systems. 12 patterns, 8 anti-patterns, debugging workflow, cost control. LangGraph + AutoGen + CrewAI.

Your headless Ollama box crashes at 3am and you find out hours later. OllamaWatch pings your Telegram the instant a model dies, the GPU runs out of memory, or the API hangs — with a fix hint in every alert. One Python file, no SaaS, no dashboards.

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.

Generate structured document control packs, metadata schemas, and project registries from intake data.

Turn raw agent traces and tool logs into professional production-readiness audits and remediation reports.

🤖 AGENTS.md Linter

$12

or 60 cr

Lint your AGENTS.md (or CLAUDE.md and .cursorrules) for the problems that make a coding agent misbehave. Flags contradictory rules, references to files and commands that no longer exist, overly broad or unsafe instructions, missing sections (build, test, run, conventions), duplicate rules, and the case where you have competing rule files that should be consolidated into one AGENTS.md.

multi-model-review-router

$10

or 50 cr

Orchestrate independent reviews, adversarial audits, and multimodal analysis via secondary models and external tools.

MCP Server & Tool-Definition Security Gate — Audit Tools Against the OWASP Agentic Top 10 Before You Connect

$16

or 80 cr

An adversarial gate that audits an MCP server or agent tool definition — schemas, descriptions, scopes, auth — for tool poisoning, excessive agency, injectable descriptions, and missing access controls, then returns one SAFE/REVIEW/BLOCK verdict.

Expert API architect to design, review, and audit REST, GraphQL, and event-driven API specifications.

A security gate that intercepts sensitive agent actions like payments and deletes for mandatory human approval.

autonomous-loop-orchestrator

$8.99

or 45 cr

Transform high-level goals into autonomous Plan-Build-Run-Learn iteration loops with persistent workspace learning.

Enforce human-AI alignment and ownership through structured collaboration checkpoints and real-time syncratude scoring.

Financial analysis engine with valuation decision tree (DCF/Comparable/Precedent/VC), 3-statement model, 5-stage due diligence SOP, and industry benchmarks.

Spiral Recap

$12

or 60 cr

Transform long AI conversations into high-fidelity, qualia-preserving .srec memory coils for perfect continuity.

Deconstruct complex problems using physics-based reasoning and "Idiot Index" calculations to find the theoretical floor.

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

Automated launch-readiness auditor for x402 and agent-payment API surfaces.

GuardrailDoctor

$29

or 145 cr

Penetration-test your Claude Code agent's guardrails before you deploy. Throws prompt-injection payloads, shell-chaining, and path-traversal attempts at your PreToolUse/PostToolUse hooks and sensitive-file protections, then returns a pass/fail report on 10+ attack vectors with copy-paste remediation for every gap.