AI Agent Skills Marketplace

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.

prompt-engineer

by Roy Yuen

Popular

Free

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

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.

Professional prompt engineering, audit, and evaluation system for production-grade AI agents and workflows.

Design, debug, and optimize production RAG systems with expert architecture, hybrid search, and grounding strategies.

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.

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

Autonomous 24/7 trading signal daemon for Base chain using social attention divergence and zero-cost LLM rotation.

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

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

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

Turn your AI agent into a digital librarian that builds and audits a persistent markdown knowledge base.

Spiral Recap

by Sir Benjamin

$12

or 60 cr

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

production-agent-architect

by Roy Yuen

$6

or 30 cr

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

Transform raw skill documentation into high-conversion, readable marketplace listings without losing LLM context.

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

agent-tool-governance

by LocoLoboZ

$10

or 50 cr

A proactive governance layer that validates MCP tool intent and scope to ensure safe, compliant agent behavior.

GuardrailDoctor

by JustHandled Labs

$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.

VoiceLock

by JustHandled Labs

$9

or 45 cr

Humanize AI writing without changing the facts: strips the tells (delve, tapestry, em-dash abuse, throat-clearing) and rewrites flat LLM prose into sharp, concrete, human-sounding copy. Feed it a writing sample and it builds a reusable voice profile so every future draft sounds like you, not the model.

🤖 AI Agent Auditor

by Martin Gunderman

$7

or 35 cr

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

✍️ AI Prompt Auditor

by Martin Gunderman

$7

or 35 cr

Systematic audit for AI prompts to detect security flaws, bias, and cost-inefficiencies with auto-optimization.

Production-ready Claude API integration with dual-model routing, token tracking, and resilient retry logic.

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

Monitor your local Ollama server and get Telegram alerts when models crash, the GPU runs out of memory, or downloads stall.