Browse The Skill Store

prompt engineer

by Roy Yuen

Free

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

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.

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.

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

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.

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

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

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

production agent architect

by Roy Yuen

$6

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

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.

A professional systematic framework for AI agents to analyze, resolve, and verify complex git merge conflicts.

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

Automate the packaging, versioning, and distribution strategy for AI agents, CLIs, and marketplace skills.

Professional audit trails, decision tracking, and human-in-the-loop safety for autonomous AI agent teams.

Force your AI agent to minimize token usage (-70% token usage across multiple scenarios), batch commands, and eliminate conversational filler for faster, cheaper ops.

Enterprise SOP Automation Architect

by Shandra

$50

Converts internal SOPs, policies, checklists, and process notes into structured AI-agent workflows with decision trees, escalation rules, QA checkpoints, and audit-ready outputs.

🤖 AGENTS.md Linter

by JustHandled Labs

$12

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.

Deployment Failure Forensics

by Shandra

$9.99

Professional DevOps diagnostics for AI agents to solve failed deployments, Docker crashes, and CI/CD pipeline errors.

🤖 AI Agent Auditor

by Martin Gunderman

$7

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

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

agent tool governance

by LocoLoboZ

$10

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

weekly cowork system auditor

by LocoLoboZ

$7

A structured governance auditor to optimize AI project instructions, clean up context, and manage workspace health.

📝 Prompt Template Linter

by JustHandled Labs

$12

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.