designing hybrid context layers
by loreto
$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)
Best LLM Ops Skills for Claude Code
Skills for retrieval pipelines, evaluations, embeddings, MCP servers, and running language models in production. Measure and operate your AI stack instead of guessing.
43 skills · page 1 of 2
diagnosing rag failure modes
by loreto
$10
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.
5
5
rag architect
by Roy Yuen
$5
Design, debug, and optimize production RAG systems with expert architecture, hybrid search, and grounding strategies.
2
0
prompt engineer
by Roy Yuen
Free
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
11
3345.0(1)
Agent Operator Utility Pack
by GTDataworks
Free
Five compact operator skills for artifact intake, zip preflight, test planning, session handoff, and MCP tool-candidate inspection.
2
1
rag failure diagnostics
by Kaymue
Free
Diagnose broken RAG systems. 8 failure categories: chunking, embeddings, retrieval, reranking, hallucination. Recall@k measurement.
2
3
Custom Data RAG Chatbot Builder
by tudor
$5
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.
5
0
Token Optimizer — Save 90%+ Tokens in Claude Code & Cursor
by Arun Dass
Free
Cuts AI coding agent token consumption by 75–94%
2
3
MCP Server Builder
Free
Scaffold a secure, spec-compliant MCP server from a description of the tools you want to expose. Sets up the official SDK (TypeScript or Python/FastMCP), defines tools/resources/prompts with strict JSON Schema, wires the right transport (stdio or Streamable HTTP), adds OAuth 2.1 for remote, and hardens against the MCP-specific footguns — prompt injection via tool output, token passthrough, over-broad scopes, command/path/SSRF injection, leaked secrets — before it ships. Returns a runnable skeleton plus a security checklist. Built by someone who's shipped production MCP servers.
1
1
Touchdesigner Mcp Driver
by Edric Vale
$5
Drive a running TouchDesigner instance through the twozero MCP bridge: create operators, wire nodes, animate parameters, run render passes, and query state back
10
0
AI Feature Eval Writer
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
Agent Context Budget Doctor
Free
Diagnose and fix context-window problems in your agent setup. Inventories everything that loads — memory files, skills, MCP tool definitions, hooks — estimates where the budget goes, maps your symptoms to causes, and prescribes concrete trims, restructures, and session habits, rewriting the files where that's the fix.
1
1
🧠 AI Memory Optimizer
$7
Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.
2
1
rag eval
by Ifásola
$5
Diagnose RAG bottlenecks with precision metrics (Recall, MRR, nDCG) to identify retrieval or ranking failures.
2
0
RAG Failure Diagnostics & Architect
$7
Produces a diagnosis of why a RAG system gives confident-but-wrong answers, or picks between vector search, knowledge graph, and structured/temporal retrieval. Use when the user says "why is our RAG hallucinating", "diagnose this failing query", "should we use a knowledge graph", "pick a retrieval architecture", or "design our memory layer". Do not use when the request is building a RAG system from zero.
1
0
Agent Tool Trace: Debug Receipts
by GTDataworks
$7
Capture tool-trace receipts, label failures, and emit replay prompts so you can debug an agent run after it finishes.
2
0
RAG Architecture & Debugging
$9.99
RAG system design and retrieval debugging (retrieval-augmented generation) - architecture decisions, hybrid search strategy, and a readiness checklist. Use when the user says my RAG app returns irrelevant chunks, the model makes things up, debug our retrieval accuracy, fix RAG hallucinations, design our RAG system, or choose a vector database.
1
0
RAG System Designer
$9.99
Every RAG tutorial shows the same pipeline; almost none of it survives contact with your actual corpus
1
0
MCP Client Evidence Gate for Codex and Qwen
by GTDataworks
$7/mo
Compatibility evidence for MCP servers against Codex CLI and Qwen: discovery receipts, report.md, and receipt.json.
1
0
Ultimate Local RAG Pipeline
$19
Deploy a local, private RAG pipeline using Supabase, n8n, and Ollama in minutes.
1
0
🔐 MCP OAuth & Authorization Contract Preflight
$19
Preflight redacted MCP 2026-07-28 OAuth evidence for issuer discovery, registration, PKCE, scopes, token audience, refresh behavior, and role-specific gaps.
2
0
ai workflow failure finder
by Md Tamim
$8
A systematic diagnostic framework for debugging AI pipelines, prompt drift, RAG failures, and agent orchestrations.
2
0
RAG Knowledge Base Auditor
by PromptWagon
$9.99
Reviews document sets, source quality, chunking logic, metadata, retrieval coverage, citation traceability, answer grounding, source gaps, stale content, duplicate content, and failure patterns for RAG knowledge-base chatbots. Helps AI, product, support, governance, and engineering teams diagnose common and costly RAG quality problems before deployment or after incidents.
1
0