Skill of the Month: Award Winning Design by Aman Garg · View skill →
Skills for retrieval pipelines, evaluations, embeddings, MCP servers, and running language models in production. Measure and operate your AI stack instead of guessing.
287 live llm ops skills for Manus.
by loreto
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.
by loreto
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.
by Roy Yuen
Professional prompt engineering, audit, and evaluation system for production-grade AI agents and workflows.
by Roy Yuen
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
by loreto
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.
by loreto
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.
by Roy Yuen
Design, debug, and harden AI control loops with explicit contracts and automated verification harnesses.
by Roy Yuen
Architect, scaffold, and harden production-grade AI agents with battle-tested patterns and systematic evaluation.
by Roy Yuen
Design, debug, and optimize production RAG systems with expert architecture, hybrid search, and grounding strategies.
by Leo Li
Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.
by Roy Yuen
Turn raw agent traces and tool logs into professional production-readiness audits and remediation reports.
Bridge OpenCode to the Agensi marketplace to discover and install AI agent skills via MCP.
by Joeri Brons
Analyzes your agent conversation history to find and automate your most frequent recurring tasks.
by tudor
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.
by Roy Yuen
Audit your AI agent's evaluation coverage to identify missing release gates and production risks.
Install or audit the real upstream uBrowser MCP runtime, verify its exact 11-tool surface, and get a clear READY or REVIEW report.
Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.
Quickstart guide to connect your AI agent to the Agensi marketplace via Model Context Protocol (MCP).
A reusable rubric that grades every source by type, recency, authority, independence, and corroboration, then ranks them and resolves conflicts by evidence weight.
by LocoLoboZ
A proactive governance layer that validates MCP tool intent and scope to ensure safe, compliant agent behavior.
Analyzes AI agents for performance, reliability, security, and optimization opportunities.
Paste any AI output. Get the production-ready prompt that made it.
Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.
by Nex AI
Builds a Python FallbackProvider that chains Claude, Gemini, Qwen, and Ollama so your AI pipeline never fully stops.
Each skill on this page is a SKILL.md file built for llm ops work and confirmed to run in Manus. Install one into ~/.manus/skills/, start a new session, and Manus 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 Manus users actually keep. Free and paid skills compete on the same page, and every listing shows its security scan result before you download anything.
Learn how it works: AI agent skills explained and What is SKILL.md?.
These are the jobs creators are actually shipping skills for in this category. Each one encodes a full workflow, so Manus follows the same method every time instead of improvising from a one-line prompt.
Start with the outcome, not the label. Open the listing and read the SKILL.md preview: a good llm ops skill states exactly what it does, what it needs from you, and what it deliberately refuses to do. Vague descriptions usually mean vague output.
Then check three things: the install count and reviews (other Manus users voting with their setup), whether the creator ships updates, and whether the skill is universal SKILL.md or agent-specific. Free skills are a fine way to test a creator's style before buying their paid work.
Related categories for Manus: Agents & Orchestration, Data & Databases and APIs & Backend.
Every paid creator is verified before they can sell, so skills come from practitioners, not scraped prompt packs.
Each version is scanned for prompt injection, credential exfiltration and destructive commands before it goes live.
Some skills are free, but most are paid. Paid skills show the price upfront and include future updates from the creator.
Unzip into ~/.manus/skills/ and start a new session. No plugin store, no build step.
Questions, partnership ideas, or feedback on the platform? Tell us what's working and what isn't, we love to hear from you!
Founder & CEO of Agensi
Email UsBook a Callinfo@agensi.io
We typically respond within a few hours during business hours.