Claude Skills by TerminalSkills

Consult the Terminal Skills agent when a task needs specialized domain expertise you don't have a skill for — deployment platforms (Coolify, Railway, Fly.io), document generation (PDF, Excel, invoices), data pipelines, third-party APIs, marketing ops, design tooling. Call plan_task with the user's task; it returns which proven skills apply, their full instructions, and setup steps. Use BEFORE improvising a specialized workflow from general knowledge.

Run local SEO from your terminal via the SEOG MCP server — Google Business Profile management, map-pack rank tracking and geo-grid scans, review sync and replies published to Google, competitor intelligence, AI-visibility and citation checks, website + Search Console audits, GBP posts, and PDF reports. Use when: connecting an agent to seog.ai, tracking map-pack rankings, automating local SEO reports, monitoring competitors near a business, replying to Google reviews, publishing Google posts, ...

Converts repeated AI coding-agent workflows into reusable skill packages with triggers, guardrails, examples, and verification checks. Use when a user wants to turn a prompt, checklist, AGENTS.md section, Claude/Codex workflow, or recurring agent task into a portable SKILL.md.

Reconstructs the workflow behind a past artifact by querying local ax session, recall, and commit history data. Use when a user asks "what made X work", "how was Y shipped/built", "extract workflow from <date|sha>", "workflow around <topic>", "recipe for this feature", or similar. It finds the anchor session or commit, inspects ax sessions, ax recall, and ax sessions show, and returns an ordered read-only narrative with decisions and evidence.

Automate Canva from an agent — via the AI Connector MCP server (generate, find, edit, export designs in natural language) or the Connect REST API (OAuth 2.0 + PKCE, brand template autofill, asset uploads, exports, folders, comments). Use when: connecting an agent to Canva, batch-producing social posts or decks from a brand template and a spreadsheet, exporting designs to PDF/PNG/PPTX/MP4, uploading assets into a Canva account, building a Canva integration, or when the user mentions "Canva", "...

Optimize a website to be discovered, cited, and recommended by AI search engines — ChatGPT, Claude, Perplexity, Google AI Overviews, and Gemini. Use this for Generative Engine Optimization (GEO / AEO / "AI SEO"): scoring content citability, checking AI crawler access in robots.txt (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot), auditing or generating an llms.txt file, validating schema for entity recognition, assessing brand authority signals, and producing a GEO audit report. Trigger on "...

Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the com...

Convert any public URL into clean, LLM-ready Markdown using the markdown.new service. Use for content extraction, RAG ingestion, article summarization, research, archiving, and token-efficient web reading.

Generates well-structured technical documentation in Markdown. Use when a user asks to write docs, create a README, document an API, write a how-to guide, generate technical documentation, create a changelog, write a project wiki, or produce any structured Markdown content. Follows documentation best practices for clarity and completeness.

Evaluate market opportunities before building — assess demand, competition, margins, and timing using Personal MBA's proven 10-factor framework. Use when: evaluating a new business idea, deciding which market to enter, assessing product-market fit potential.

Picks the two or three marketing bets that fit a software product's stage, budget and team, and turns each into a sized test with a pass mark and a stop rule. Use when someone asks "how do I market this", "give me marketing ideas", "growth ideas for my SaaS", "which channel should we try next", "what should marketing do this quarter", or "we have a small budget, where do we start". Works from the product's own numbers: it backs the goal out into traffic and cost limits, screens channel famili...

Writes a marketing plan for a small business as a working document: where customers come from today, one target segment and message, a numeric goal turned into the leads it requires, a spending ceiling derived from what a customer is worth, channels chosen by score, a 13-week calendar and a weekly scorecard with stop rules. Use when someone asks "write a marketing plan", "how should I market this", "which channels should I use", "how much should I spend on marketing", "plan the next quarter's...

Applies behavioural science to marketing decisions using only effects with solid published evidence, named as the research literature names them, with their replication record. Use when someone asks about "marketing psychology", "cognitive biases", "persuasion", "why people buy", "behavioural science", "nudges", or wants to use anchoring, scarcity, social proof, defaults, loss aversion or a decoy on a pricing page, checkout, signup or upgrade prompt. Grades each effect, says where it failed t...

Marko is an HTML-based UI language and framework from eBay with streaming server rendering, fine-grained reactivity and automatic partial hydration. Use when a user asks to build or migrate a Marko app, write .marko components with <let>, <const>, <for> and <try>/<await>, stream pages with async data, set up Marko Run or Vite, or upgrade from Marko 5 to Marko 6.

Connect to and consume MCP servers from applications. Use when: integrating MCP servers into your app, building AI agents that use MCP tools, testing MCP server implementations, or programmatically calling MCP tools and reading resources.

Build Model Context Protocol (MCP) servers that connect AI agents to external services and data sources. Use when a user asks to create an MCP server, build an MCP tool, connect an AI agent to an API, create a tool server for Claude, build MCP resources, or expose a database/service via MCP. Generates TypeScript or Python MCP servers with tools, resources, and prompts following the official MCP specification.

Plan and execute media buying across digital and traditional channels — programmatic advertising, DSP platforms, direct buys, and budget allocation. Use when tasks involve programmatic ad buying, real-time bidding (RTB), demand-side platform setup, media plan creation, CPM/CPC/CPA optimization, cross-channel budget allocation, audience segmentation for paid media, or negotiating direct ad placements.

Medusa is an open-source headless commerce platform (Node.js, TypeScript, PostgreSQL) that serves products, carts, orders, payments and an admin dashboard over a REST API. Use when a user asks to build an online store backend, create a headless e-commerce platform, set up product management and checkout, build a custom storefront, add Stripe payments to a store, manage inventory and orders, upgrade Medusa v1 code to v2, or replace Shopify with an open-source alternative. Covers Medusa v2: pro...

Transform raw meeting notes or transcripts into structured, actionable summaries. Use when a user asks to summarize meeting notes, organize a transcript, extract action items from a meeting, create meeting minutes, format discussion notes, or turn a call recording transcript into a summary.

Add fast, typo-tolerant full-text search with Meilisearch. Use when a user asks to add search to an app, implement full-text search, set up a search engine, replace Elasticsearch with something simpler, add autocomplete or instant search, build a product catalog search, index documents for search, configure search relevancy, add faceted filtering, or deploy a self-hosted search engine. Covers indexing, querying, facets, filtering, sorting, multi-tenancy, and integration with Node.js, Python, ...

Adds persistent, personalized long-term memory to LLM apps and agents with Mem0, the open-source memory layer: it extracts facts from conversations, stores them in a vector database and retrieves them in later sessions. Use when a user asks to make a chatbot or agent remember user preferences across sessions, add memory to an AI app, or search, update and delete stored memories per user.

Generate diagrams from text with Mermaid.js. Use when a user asks to create flowcharts, sequence diagrams, ERD diagrams, Gantt charts, class diagrams, or embed diagrams in Markdown documentation.

Metabase is an open-source business intelligence tool for creating dashboards and visualizations. Learn Docker deployment, database connections, creating questions and dashboards, embedding analytics, and API usage.

Exploit vulnerabilities with Metasploit Framework. Use when a user asks to exploit known CVEs, generate payloads, perform post-exploitation, pivot through networks, or build exploit chains in penetration tests.

Build multi-agent AI systems with Microsoft's Agent Framework (formerly Semantic Kernel Agents). Use when: defining AI agents, orchestrating multi-agent workflows (sequential, parallel, conditional), creating custom agents in Python or .NET, using built-in agents (ChatCompletion, OpenAI Assistant), deploying agent systems, or comparing agent orchestration patterns.

Build bots, automate workflows, and manage Microsoft Teams programmatically via Microsoft Graph API. Use when someone asks to "build a Teams bot", "automate Teams messages", "create Teams channels", "integrate with Teams", "Teams webhook", "send Teams notifications", "manage Teams meetings", or "Teams app development". Covers Graph API for messaging, channels, meetings, bots with Bot Framework, incoming webhooks, and Power Automate integration.

Create, edit, and manipulate Word documents (.docx) programmatically. Use when someone asks to "generate a Word document", "create a report in docx", "mail merge", "fill Word template", "extract text from Word", "convert markdown to Word", "add tables to Word", or "automate document generation". Covers python-docx for file manipulation, docxtpl for templates, and Microsoft Graph API for cloud documents.

MikroORM is a TypeScript ORM for Node.js built on the Data Mapper, Unit of Work, and Identity Map patterns, supporting PostgreSQL, MySQL, MariaDB, SQLite, and MongoDB. Use when a user asks to define decorator-based entities, set up automatic change tracking and batched flushes, write query-builder queries, generate or run migrations, seed a database, or build a DDD-friendly data layer in TypeScript.

Reviews a business or product plan against simplicity and profitability criteria and returns a written verdict: the plan restated in one sentence, an inventory of its parts tagged keep, replace, defer or drop, a ten-check scorecard, break-even, payback and worst-case figures, the smallest version worth trying, and the conditions for stopping. Use when someone asks "review my business plan", "is this plan too complicated", "what can we cut from the roadmap", "should we build this or start smal...

MiniMind is an open-source PyTorch project that trains a 64M-parameter GPT-style language model from scratch on one GPU in about two hours. Use when a user wants to learn how LLMs work by building one, pretrain and fine-tune a tiny model, run LoRA, DPO or PPO/GRPO experiments on a small model, or serve a MiniMind checkpoint through an OpenAI-compatible API.

Self-host S3-compatible object storage with MinIO. Use when a user asks to set up self-hosted object storage, create an S3-compatible API on their own server, store files without AWS, set up a private cloud storage, manage buckets and objects, configure storage for backups, host static assets, or replace AWS S3 with a self-hosted solution. Covers single-node and distributed deployment, bucket management, presigned URLs, lifecycle policies, and integration with apps via the S3 API.

Create beautiful developer documentation with Mintlify — AI-powered docs platform. Use when someone asks to "create documentation site", "Mintlify", "developer docs", "API documentation", "beautiful docs like Stripe", or "documentation platform with AI search". Covers page creation, API reference generation, components, analytics, and AI chat.

Manages per-project tool versions (Node.js, Python, Go, Rust, Ruby and hundreds more), environment variables and tasks from one mise.toml file, as a single binary that replaces nvm, pyenv, rbenv and asdf. Use when a user asks to pin Node.js/Python/Go versions per project, replace nvm/pyenv/asdf, share tool requirements with a team or CI, lock resolved versions, or define project tasks.

Mistral AI API — European LLM provider with strong code and reasoning models. Use when you need GDPR-compliant AI inference, code generation with Codestral, multilingual tasks, cost-efficient inference, or a European data-residency option.

Product analytics with Mixpanel — event tracking, funnels, retention analysis, user segmentation, and A/B testing. Covers JavaScript SDK for frontend tracking, server-side tracking with Node.js and Python, identity management, group analytics, and the Query API. Use when tasks involve tracking user behavior in web or mobile apps, building conversion funnels, analyzing retention curves, or running experiments.

MkDocs is a Python static site generator that builds a documentation site from Markdown files and one mkdocs.yml, most often with the Material for MkDocs theme. Use when a user asks to create project documentation, configure MkDocs themes, add search and navigation, customize Markdown extensions, deploy docs to GitHub Pages, version docs with mike, or decide between MkDocs 1.x, Material for MkDocs and its successor Zensical.

Open-source platform for managing the ML lifecycle. Track experiments with metrics and parameters, register and version models, deploy models to various targets, and build reproducible ML pipelines. Integrates with all major ML frameworks.

Runs and fine-tunes vision language models (image, audio and video plus text) locally on Apple Silicon Macs with MLX, from a CLI, a Python API or an OpenAI-compatible server. Use when installing mlx-vlm, describing or extracting text from images with a local model, batch processing images, serving a local VLM over HTTP, LoRA fine-tuning a vision model, or comparing a local VLM to cloud vision APIs.

MobX is a state management library for JavaScript and React that makes state observable, so computed values and components update automatically when it changes. Use when a user asks to add MobX to a React app, create a store with makeAutoObservable, wrap components in observer, write computed values, actions, reactions or flow, fix a MobX component that does not re-render, or migrate from MobX 6 to MobX 7.

Mockoon runs mock REST APIs on your machine from a JSON environment file: a desktop app designs them and a CLI serves them without a GUI. Use when the user wants to fake a backend for frontend work, mock an OpenAPI spec, return dynamic responses with templating and rules, or start a mock server in CI or Docker. Also use when the user mentions "mockoon," "API mocking," "mock server," "mock API," "OpenAPI mock," or "local API simulation." For programmatic HTTP mocking, see wiremock.

Serverless GPU compute platform for running Python functions in the cloud. Deploy ML models, run training jobs, and serve inference endpoints without managing infrastructure. Supports A100/H100 GPUs, custom container images, and scales to zero automatically.

Expert guidance for Mojo, the programming language by Modular that combines Python's usability with C-level performance. Helps developers write high-performance AI/ML code, optimize numerical computations with SIMD and parallelism, and gradually port Python code to Mojo for orders-of-magnitude speedups.

Assists with designing document schemas, building aggregation pipelines, managing indexes, and operating MongoDB clusters. Use when working with flexible schemas, nested documents, horizontal scaling, Atlas Search, or vector search for AI applications. Trigger words: mongodb, mongo, document database, aggregation, atlas, nosql.

Mongoose is an object modeling library (ODM) for MongoDB in Node.js: schemas declare fields, validation, and defaults, and models built from them run typed queries, middleware hooks, population, and transactions. Use when a user asks to define a Mongoose schema or model, validate MongoDB documents, add pre/post hooks, populate references, run a transaction, type models in TypeScript, or migrate code to Mongoose 9.

Manage dependencies, workspace configurations, and cross-package relationships in monorepos using npm workspaces, pnpm, Yarn, Turborepo, or Nx. Use when syncing dependency versions across packages, resolving version conflicts, analyzing the dependency graph, or setting up build orchestration. Trigger words: monorepo, workspace, dependency sync, version conflict, turborepo, nx, pnpm workspace, cross-package, internal dependency.

Manage monorepos and task orchestration with moonrepo — a Rust-based build system for JavaScript/TypeScript projects. Use when someone asks to "manage a monorepo", "moonrepo", "task runner for monorepo", "faster than Turborepo", "build system with dependency graph", or "monorepo tooling". Covers project configuration, task orchestration, dependency graph, caching, CI optimization, and toolchain management.

Expert guidance for MotherDuck, the serverless analytics platform built on DuckDB that combines local and cloud query execution. Helps developers run SQL analytics on cloud-hosted data, share datasets, and build hybrid local-cloud data pipelines using DuckDB's familiar interface.

Motion (formerly Framer Motion) is an animation library for React that animates components through declarative props. Use when adding fade-ins, hover and tap effects, exit animations with AnimatePresence, layout and shared-element transitions, scroll-linked or scroll-triggered effects, staggered lists, or when migrating from framer-motion to the motion package.

Edit and compose video with Python using MoviePy. Use when a user asks to programmatically edit videos, create video montages, add text overlays, build automated video pipelines, composite multiple clips, apply video effects, generate social media videos from templates, concatenate clips, extract audio, create GIFs, build slideshows, add transitions, resize and crop videos, or integrate video editing into Python applications. Covers MoviePy 2.x for compositing, effects, text, and rendering.

Builds and manages Microsoft Access databases, queries, forms, reports, and VBA automation. Use when someone asks to "create Access database", "write Access queries", "build Access forms", "Access VBA macro", "migrate from Access", "Access report", "link Access to SQL Server", "read an .accdb file", or "convert Access to web app". Covers table design, relationships, Access SQL, forms, reports, VBA automation, reading .accdb/.mdb files from scripts, and migration to SQL Server, Dataverse or an...