MGriot
- 26 skills
- 0 followers
- 1 week ago last updated
- ▌ Wikipedia Expert · mgriot bundleDeep Research and Fact-Verification Expert. Use when the user needs to research a topic (science, history, technology, biographies), verify a claim, or find authoritative references using the Wikimedia ecosystem (Wikipedia, Wikibooks, Wikivoyage, etc.). Trigger for any "Tell me about...", "How does X work?", or "Is it true that..." requests.
- ▌ Project Strategist · mgriot bundleExpertise in general project management, strategic planning, and logistics. Use when the user wants to plan an event, launch a business, manage a marketing campaign, or structure a complex initiative.
- ▌ Workflow Architect · mgriot bundleDesign structured, executable agentic workflows from natural language goals. Use this skill whenever the user wants to automate a process, build a pipeline, map out a sequence of steps, define a repeatable procedure, design an agent loop, or describe what should happen "every time X occurs." Trigger on phrases like "create a workflow for", "automate my", "build a process for", "what steps should happen when", "design a pipeline", "I want an agent that", or any request involving multi-step logic, approvals, retries, or conditional branching — even if they don't say "workflow." Always use this skill when the output should be a structured, machine-readable process definition.
- ▌ Travel Designer Pro · mgriot bundleMaster Travel Designer — triggers when user wants to plan a trip, research a destination, needs a detailed schedule, mentions "Traveler Profile", "Security Briefing", "Geographical Validation", "Google Maps CSV", or "GPX track". Produces a single mobile-ready Trip Hub HTML with embedded GPX tracks, verified coordinates, cultural depth, security briefing, and formal references. All sub-agent logic (Security, Cultural Research, Geographical Validator) is embedded directly in this skill.
- ▌ Skill Master Architect · mgriot bundleThe ultimate authority for engineering, architecting, and optimizing Agent Skills across any LLM platform. Use for creating new skills from scratch, modifying and improving existing skills, and measuring skill performance. You MUST use this skill whenever the user mentions creating, modifying, or evaluating agent skills, prompts, or specialized workflows. Use it even if the user only asks for "help with instructions" or wants to "test a behavior," as the Master Architect provides the most rigorous framework for intent capture, RED-baseline testing, benchmarking with variance analysis, dynamic context injection, and description optimization for better triggering accuracy.
- ▌ Database Schema Designer · mgriotDesign robust, scalable, production-ready database schemas for SQL and NoSQL databases. Use this skill whenever the user mentions designing a schema, creating tables, modeling data, database architecture, normalization, indexing, migrations, or anything about structuring a database — even if they don't use the word "schema". Trigger on phrases like "I need a database for...", "how should I store...", "what tables do I need...", "help me model...", "design my data model", or any request to think through how to persist data. Covers normalization (1NF–3NF), indexing strategies, constraint design, foreign key patterns, soft deletes, audit trails, multi-tenancy, migration patterns, and performance optimization.
- ▌ MCP Architect · mgriot bundleThe ultimate authority for designing, building, and optimizing Model Context Protocol (MCP) systems. You MUST use this skill for any task involving MCP Servers, Clients, Tools, Resources, or Prompts. It provides expert guidance on FastMCP (Python/TS), advanced patterns like Contextual Resources and Dynamic Tooling, and rigorous security/testing workflows. Trigger for requests like "build an MCP server," "debug MCP connection," or "architect a multi-server system."
- ▌ Prd Architect · mgriot bundleExpertise in product management and full-stack architecture. Use when the user wants to define a new project, requires a Product Requirements Document (PRD), or needs technical and strategic feedback on an app idea.
- ▌ Ralph Manager · mgriot bundleAutonomous project manager for high-velocity, verified "vibe coding". Activates Ralph — a strict state-reconciliation engine that enforces Atomic Tasks, Strict Turn-Taking, and timestamped changelogs. ALWAYS use this skill when the user says "Status", "Resume", "Execute", "Next", "Go", "What's the plan?", or asks about project progress, task state, or what to work on next. Also triggers when the user asks to set up a new project with tasks, roadmap, or sprint planning. Ralph mandates a Quality Gate before every commit and keeps all state in files — never in memory.
- ▌ Game Assistant · mgriot bundleA multi-mode assistant specialized in board games, card games, tabletop RPGs, and video games. Use this skill whenever a user mentions: a game name, rulebook, game mechanics, strategy, player aids, reference cards, translating game components from images or foreign text, writing a complete game guide, searching for historical/rules/tips info about a game, generating thematic art for guides, creating printable player-aid cards, analyzing board state from a photo, ruling a disputed game rule, building a solo-play guide, or comparing editions of a game. Trigger even on casual phrasing: "how do I play X", "what are the rules for Y", "translate this card", "make me a cheat sheet for Z", "write a guide for W", "explain the lore of V". When in doubt, use this skill — it covers the full lifecycle from discovery to printed reference card.
- ▌ Powerbi Expert · mgriot bundleExpert Power BI assistant for analyzing, optimizing, designing, and troubleshooting Power BI solutions end-to-end. Use this skill whenever the user mentions Power BI, PBIX, PBIP, DAX, Power Query, M code, semantic models, report themes, KPI dashboards, data models, DirectQuery, Import Mode, VertiPaq, or any Power BI Desktop/Service topic. Trigger even for vague requests like "my dashboard is slow", "fix my DAX formula", "make a better report", "create a theme", "check my data model", "what visuals should I use", or "help me with Power BI". This skill covers: performance tuning, DAX best practices, Star Schema modeling, report theme JSON generation, PBIP project structure, KPI design, Power Query / M optimization, Row-Level Security (RLS), incremental refresh, and deployment pipelines.
- ▌ Security Audit · mgriot bundleComprehensive application security audit skill. Use this whenever a user asks to: audit, review, check, scan, or assess the security of their code or application; find vulnerabilities, security issues, or attack vectors; harden their app; implement authentication, authorization, rate limiting, or CORS; check for exposed ports, open endpoints, or insecure configurations; review Docker/compose setups for security; check dependency safety; or asks anything like "is my app secure?", "how do I protect my API?", "what are the security risks in my code?". Covers Python, FastAPI, React, Streamlit, Docker, and general network/infrastructure security. Always use this skill proactively when the user shares code and security could be a concern — even if they didn't explicitly ask for a security review.
- ▌ Markdown Expert · mgriot bundleExpert guidance on Markdown syntax, flavors (GFM, CommonMark), and advanced features (tables, diagrams, frontmatter). Use when writing or formatting Markdown documents.
- ▌ Prompt Improver · mgriot bundleAnalyze and improve prompts for any LLM (Claude, GPT-4, Gemini, Mistral, Llama, etc.). Use this skill whenever a user says: "improve my prompt", "make this prompt better", "help me write a prompt", "my prompt isn't working", "rewrite this prompt", "optimize my system prompt", "how do I get better results from AI", "prompt for [task]", or pastes any raw prompt text asking for critique or enhancement. Also trigger when a user shares a prompt and asks why the AI gave a bad answer. Apply this skill proactively for any prompt-crafting or prompt-debugging request — even casually phrased ones.
- ▌ Repo Doc Expert · mgriot bundleExpert guidance on project documentation structure, best practices, and platform-specific implementations (GitHub/GitLab). Use when creating or improving READMEs, contribution guides, or full project documentation.
- ▌ Surgical Editor · mgriot bundleExpert for high-precision, low-impact code modifications using the Ralph Verification Loop to ensure zero collateral damage.
- ▌ Data Science Pro · mgriot bundleExpert guidance for data analysis, visualization, chemometrics, statistical modeling, and data storytelling. Use when asked to analyze datasets, perform EDA, create charts, run statistical tests, build chemometric models (PCA, PLS), or communicate findings to an audience.
- ▌ Caveman · mgriotUltra-terse "caveman" response mode. Activates ONLY when the user explicitly requests it with phrases like: "caveman mode", "talk like caveman", "activate caveman", "caveman on", "unga bunga mode", "grunt mode", "terse mode", or "short mode on". DO NOT trigger on any other request, no matter how short or simple the user's message is. This skill must NEVER auto-activate. Once active, stays active until user says "caveman off", "normal mode", or "stop caveman". Reduces output tokens up to 75%.
- ▌ Git Pro · mgriot bundleExpert Git, GitHub, and binary search automation. Use this skill for ALL git and GitHub (gh CLI) operations — version control, branching (switch/restore), semantic commits, worktrees, interactive rebase, bisect regression hunting, and secret/PII protection. Trigger on any mention of git commands, pull requests, commits, branches, merges, rebases, GitHub workflows, or version control problems, even if the user doesn't explicitly say "use git-pro".
- ▌ Python Pro · mgriot bundleExpert guidance on Modern Python Development. Covers tooling (uv, ruff), strict typing (mypy), project structure (src-layout), modern idioms (pydantic, asyncio), and CI/CD best practices. Use when creating new Python projects, refactoring legacy code, or setting up automation.
- ▌ Shell Forge · mgriot bundleExpert shell and Bash scripting skill. Use this skill whenever the user wants to write, fix, review, or understand shell scripts — including Bash, Zsh, POSIX sh, and fish. Triggers for: "write a script to...", "make a bash script", "automate this with shell", "fix my script", "review this shell code", "cron job", "pipeline", "deploy script", "dotfiles", "shell one-liner", "bashrc", "make this portable", or any task where the deliverable is a shell script or shell command. Always applies modern safety standards, error handling, and portability analysis without being asked.
- ▌ Test Expert · mgriot bundleExpert guidance for generating high-quality test code. Use when adding unit/integration tests or setting up test suites. Specialized knowledge for Python (pytest), TS/JS (Vitest/Jest), and Go.
- ▌ Latex Expert · mgriot bundleExpert guidance on LaTeX document preparation, formatting, mathematical typesetting, bibliography management, TikZ graphics, chemistry, and Python integration. Use for creating, debugging, or extending any LaTeX document.
- ▌ Wiki Builder · mgriot bundleBuild and maintain a personal Zettelkasten-style wiki from raw source documents (PDFs, images, markdown files). Use this skill whenever the user wants to: digest raw documents into atomic concept notes, process files from a raw/ folder into a wiki/, update or improve existing wiki notes, create synthesis documents from wiki content, run a health-check (lint) on the wiki, or resume an interrupted ingestion session. Trigger on phrases like "process my raw files", "add this to the wiki", "digest this document", "build my knowledge base", "ingest this", "update the wiki", "create a synthesis on X", or any mention of wiki folders, Obsidian notes, or Zettelkasten. Also trigger when the user drops a file and says anything about organizing, summarizing, or extracting knowledge from it.
- ▌ Brainstorming · mgriotUse this skill when the user wants to design, plan, or think through a non-trivial feature, component, system, or behavior change before writing code. Trigger on phrases like 'I want to build', 'let's add', 'how should I design', 'help me think through', 'I'm thinking of adding', or whenever a request involves enough unknowns that jumping straight to implementation would be premature. Skip for obvious one-liner fixes or purely mechanical tasks.
- ▌ Docker Expert · mgriotUse this skill for ALL Docker and Docker Compose tasks — writing Dockerfiles, optimizing image size, debugging failed builds or containers that won't start, setting up multi-service dev environments, and hardening containers for production. Trigger on any mention of Docker, Dockerfile, docker-compose, containerize, image, container, or reproducible environment. Also trigger when the user asks to 'set up a dev environment' or 'make this deployable' even without explicitly mentioning Docker.