The all-in-one AI plugin for Prompt Engineers, in one download

Skills for prompt engineers 8

• llm prompt optimizerTightens a working prompt and cuts tokens, like turning a 400-word support reply prompt into 120 words with the same accuracy.
• prompt builderBuilds a new prompt from your source material and tests each edit, like a policy-summary prompt checked against five real documents.
• agency senior prompt engineerRuns eval sets, measures RAG retrieval, checks agent tools, and designs structured output, like scoring 50 answers against a pass mark.
• agency ai securityReviews prompts and agents for jailbreaks, tool abuse, and poisoning, like mapping a chatbot attack path to MITRE ATLAS techniques.
• prompt injection defenseBlocks hidden instructions in user text or files, like stopping a resume PDF from telling your assistant to leak data.

Plus a start-here assistant, the prompt library and the app builder, and for members the daily brief.

Ready-made prompts 24

• Prompt Drafting Basics3 prompts, like Draft Your First Prompt Template
• Refining Prompt Wording3 prompts, like Simplify Wordy Prompts For Users
• Generating Prompt Variations3 prompts, like Generate Prompt Variation Sets
• Testing Prompt Responses3 prompts, like Simulate Model Responses Before Live Testing
• Edge Cases And Robustness3 prompts, like Generate Edge Case Inputs for Prompt Testing
• Evaluating Output Quality3 prompts, like Build A Model Output Scoring Rubric
• Documenting Prompt Guidelines2 prompts, like Draft Team Prompt Style Guide

Apps you can build with AI 3

• Prompt lifecycle workbench for AI teamsGives your team one reviewable record of every prompt change, so revisions stop living in chat threads and stray docs. Demo included.
• Prompt lifecycle testing and deployment workbenchCuts prompt regression risk by keeping versions and test results together, so a wording tweak cannot quietly break a live flow. Demo included.
• Source-linked language model workbenchKeeps prompts, context, and data under your control with sources linked, replacing a pile of disconnected tools. Demo included.

AI agents 12

In the download. An agent runs a whole recurring task for you, step by step, and asks you before anything important. Ask your AI: "Run the Prompt Injection Red-Team Agent". Each one also has a guided set-up with sample data on its page.

• Prompt Injection Red-Team AgentFind the ways your prompt can be attacked and fix them without hurting normal use
• Golden Test Set Maintenance AgentKeep the test set current so real failures become permanent tests
• Model Selection Bake-Off AgentChoose a model with evidence on quality, cost and speed for the real task
• Prompt Library Cleanup AgentLeave a smaller library where each purpose has one tested, owned prompt
• Refusal Boundary Test AgentSet the assistant's boundaries so valid requests are answered and disallowed ones are refused
• Prompt Test Harness AgentEvery prompt change measured against a full test set before it is adopted
• Prompt Variation Experiment AgentA better prompt found through a fair, logged comparison of variations
• Prompt Edge Case Robustness AgentA prompt that behaves correctly on messy and adversarial inputs, not just clean ones
• Output Quality Grading AgentConsistent, rubric-based quality scores for outputs at scale, with reliability checked
• Prompt Regression Monitoring AgentEarly notice when a production prompt degrades, with the likely cause
• Prompt Guideline Documentation Sync AgentKeep the team prompt guide in line with what tested prompts actually show works
• Prompt Output Consistency Tuning AgentRaise a prompt's output consistency to the agreed target without lowering quality

Connections (MCP servers) 12

A guide in the download. A connection lets your AI work in an app you already use. You add only the ones you use: ask your AI "Which apps can you connect to?" and follow the steps on each connection's page.

• Langfuse Prompts MCP serverLets your AI look up and fill in your Langfuse prompts right inside the chat.
• Promethic MCP serverYour AI can save, version and improve your prompts, and switch models and settings for each one. No install needed.
• Cloudflare Workers AI MCP serverLets your AI run chat, text embeddings and image generation through Cloudflare's AI service.
• OpenAI MCP serverAsk Claude to send a question to OpenAI models like gpt-4o or o1 and bring the answer back.
• AgentBase MCP serverLet your AI search and fetch ready-made instruction files from the AgentBase registry.
• System Prompts MCP serverLets your AI look up and use the system prompts behind tools like Cursor, Devin, and Claude.
• Opik MCP serverAsk your AI about your Opik traces, scores and prompts, and let it log results for you. Official. No install needed.
• Outsource MCP serverLet your AI ask other AI models to write text or make images for you.
• Claude Prompts MCP serverSave your best prompts once and reuse them, with checks and step-by-step chains your AI follows.
• AIStorageDepot MCP serverLet your AI search your shared team library of prompts, rules, skills and docs, and use them as slash commands.
• Gemini Bridge MCP serverLets your AI assistant ask Google's Gemini models questions and get answers back in the same chat.
• MCP Prompt EngineTurn your own reusable prompt templates into ready-made prompts your AI can pick up and use. No install needed.

Your Grok Bot team 12

• Llm Prompt OptimizerTransform weak prompts into precision-engineered instructions for any LLM.
• Prompt EngineeringDesign, test, and refine prompts for reliable LLM outputs.
• Llm EvaluationDesign and run systematic LLM evaluations with metrics, human review, and A/B testing.
• Context EngineeringCurates project context to maximize agent output quality and reduce hallucination.
• Prompt CachingAnalyzes LLM prompts and responses to recommend caching strategies that reduce costs and latency.
• Llm Structured OutputExtract typed, validated JSON from LLM responses using provider-specific structured output methods.
• Context Window ManagementManage LLM context windows by summarizing, trimming, and routing content to prevent token overflow.
• Research PromptTurn vague research needs into one precise deep-research prompt with context and output criteria.
• Prompt Engineering PatternsDesigns, optimizes, and validates prompts for production LLM applications.
• Context DegradationDiagnose and mitigate LLM context degradation patterns like lost-in-middle and poisoning.
• Llm Application Dev Prompt OptimizeCraft production-ready prompts with constitutional AI and chain-of-thought.
• Prompt BuilderEngineers and validates high-quality prompts through research, testing, and iterative improvement.