AI skill directory

This skill offers marketing tactics for SaaS and other software products, drawn from a catalog of tested approaches. It narrows the list by company stage, budget, and timeline, and points to ideas for quick leads, authority, product-led growth, or enterprise sales.

Brainstorms and shapes OKRs that connect outcomes to measurable key results.

Forces design brainstorming before creative/feature work so agents explore approaches instead of jumping to code.

Applies Anthropic's brand colors and fonts to documents and designs.

Generates brand-kit boards with logo systems, identity decks, and guideline visuals.

Drives a real browser to open pages, click flows, screenshot, and check console errors.

This skill makes a step-by-step learning plan for a topic you want to pick up over several sessions. It checks what you already know, orders topics from basics to applied work, and sets milestone projects with checkpoints. The plan includes practice assignments and a rubric for reviewing progress.

This skill finds and qualifies prospects, with separate paths for software companies, other business-to-business sellers, and neighborhood shops. It defines the ideal customer, gathers candidates, checks each one, and scores them. Results come back as a table, or as a CSV file once the list gets long. Compliance rules forbid mass scraping.

This skill guides building with Mastra, a TypeScript framework for building agents and workflows with tools, memory, and storage. It tells the agent to check current docs and APIs rather than rely on memory, and it helps with setup, frequent errors, version migrations, and the mastra api CLI.

This skill is the starting point for building on Neon, whose Postgres comes bundled with auth, file storage, serverless functions, and an AI gateway. It covers setting up the Neon CLI and MCP server, a branch-first workflow, finding the right docs page, and choosing narrower Neon skills.

This skill does competitive analysis in two ways. On demand, it lays out how to win a specific deal against a named rival. Across all deals, it pulls competitor mentions into win and loss patterns and keeps battlecards current, and it can run as a weekly digest.

This skill is a reference for building healthcare REST endpoints on FHIR R4, such as Patient, Observation, Encounter, and MedicationRequest. It covers mandatory fields, allowed enum values, HTTP responses and errors, and coding systems like LOINC, SNOMED, RxNorm, and ICD-10. SMART on FHIR authorization, Bundles, transactions, and paged search are included.

This skill builds and changes Obsidian Bases (.base) files, which show notes as a database. It sets up table or card views, filter rules, formula properties, and summary rows.

This skill helps you write spoken and text agents on the LiveKit Agents SDK and LiveKit Cloud. It focuses on keeping replies fast, keeping context small, and splitting one large agent into handoffs and tasks. It also covers fixes for agents that talk too much, repeat questions, or claim a booking that never saved.

Designs visual canvases and layouts as PNG/PDF artifacts with intentional composition and typography.

Applies the Caveman agent workflow—lean, evidence-first habits—for coding sessions.

Writes Conventional Commit messages reduced to their essential intent.

Reviews code with Caveman evidence-first standards—tight diffs, proofs, no fluff.

Builds ChatGPT Apps SDK applications combining MCP servers with app UI and tools.

Writes and runs SQL against chDB (in-process ClickHouse for Python) for local analytics.