Skills

Run WCAG accessibility audits on any URL using axe-core and produce structured JSON results or a polished PDF report. Use when checking a website for accessibility issues, WCAG compliance, or producing an a11y audit deliverable.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Answer date, time, and calendar questions using a local Python utility. Use when you need today's date, the day of the week, date arithmetic, the number of days between two dates, what day a date falls on, or any other calendar-related computation.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Render a competitive positioning PDF report from structured JSON — title page, 2×2 positioning map, comparison table, and gap analysis. Use when the agent has researched competitors and needs to produce a polished deliverable.

Pause execution for a specified number of seconds. Use when you need to wait between operations, rate-limit API calls, or give time for an async process to complete before checking its status.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Run GitHub CLI (gh) commands to manage repositories, issues, pull requests, releases, and more. Use when you need to interact with GitHub — create issues, search PRs, list repos, review workflows, etc. Requires a Personal Access Token.

Manage Google Calendar - view agenda, create/update/delete events, add attendees and Google Meet links, check free/busy availability, and manage multiple calendars. Use for any scheduling task: checking availability, booking meetings, updating events, or querying upcoming appointments.

Create, read, and edit Google Docs - insert and style text, build tables, manage headers/footers, work with named ranges, and export documents. Use for any Google Docs task: writing documents, formatting content, building templates, or extracting document text.

Manage Google Drive - list, search, upload, download, export, move, copy, trash files, and control sharing permissions. Also provides schema introspection for any Google Workspace API. Use for file management tasks: finding files, organizing folders, sharing documents, uploading/downloading content, or exploring API schemas.

Gmail - read, triage, bulk-act, compose, and send. Use for any Gmail task.

Build and manipulate Google Sheets from Python using pandas DataFrames. Create spreadsheets end-to-end: read/write data, apply formatting, add conditional formatting, charts, pivot tables, data validation, named ranges, and share files. Use when you need to build a sheet, dashboard, or report, or transform data into a spreadsheet — especially for business workflows (P&L, KPI dashboards, ops trackers, financial models, budget plans).

Create and edit Google Slides presentations - add slides, insert and style text, place images and shapes, duplicate presentations for templates, and perform bulk text/image replacement. Use for any Google Slides task: building decks, formatting presentations, filling templates, or reading slide content.

Manage Google Workspace via the gws CLI — create and read Google Docs, Slides presentations, manage Google Calendar events, work with Drive files, and send / reply / forward one-off Gmail messages. Use when you need to interact with Google Docs, Slides, Calendar, or Drive, or send a single email.

Publish blog posts and drafts to Hashnode via GraphQL API. Use when you need to publish content to Hashnode, create a blog post, push an article to a Hashnode blog, or manage Hashnode drafts. Requires a Personal Access Token, a Publication ID, and a Pro plan on the publication (Hashnode retired free API access in May 2026).

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Produce branded marketing PDFs (one-pagers and short multi-page sales sheets) from a brief plus either a brand URL to scrape or written brand instructions. Use when you need a print-quality PDF that reflects a company's actual branding.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Fetches current Octavus AI documentation over HTTP and answers questions from authoritative markdown. Use when you need information about Octavus (agent protocol, @octavus/server-sdk, @octavus/client-sdk, @octavus/react, REST API, examples, migration), or need Octavus docs that may have changed since model training data.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

PDF document toolkit for creating new PDFs, text extraction, table parsing, document assembly (merge/split), form population, and image rendering. Invoke when creating, processing, analyzing, or generating PDF files programmatically.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Build a formatted Excel prospecting brief from structured JSON - target accounts and contacts with styled headers. Use when sales research is done and the deliverable should be a shareable spreadsheet.

Generate QR codes from text, URLs, or data. Use when the user needs to create a QR code for any purpose - sharing links, contact information, WiFi credentials, or any text data that should be scannable.

Convert Markdown into paste-ready rich text for web editors and WYSIWYG fields. Use for blog posts, X Articles, CMS content, contenteditable inputs, or any workflow that needs Markdown copied as formatted text.

Manage Salesforce CRM data through the core REST API: run SOQL queries and SOSL searches; create, read, update, delete, and upsert any standard or custom object (Leads, Contacts, Accounts, Opportunities, Cases, Campaigns, Tasks, and custom __c objects); inspect object and field schemas; run Bulk API jobs for large data loads; and call arbitrary REST endpoints. Use for Salesforce CRM work: lead and contact management, account and opportunity updates, pipeline reporting, data extraction, bulk import/export, or any sObject CRUD. Requires Salesforce credentials (access token, username + password + security token, OAuth client credentials, or JWT bearer).

Take screenshots of web pages. Use when you need to capture a visual snapshot of a website, web application, or any URL. Supports full-page screenshots, device emulation, and custom viewport sizes.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Act in Slack as yourself - send and reply to messages, edit and delete them, add reactions, read channel and thread history, search messages, list and resolve channels and users, look people up by email, open DMs, and upload files. Use for any Slack task: posting updates, triaging a channel, DMing a teammate, searching past conversations, or sharing a file. Posts and actions appear as the authenticated person, not a bot. Requires a Slack user token (xoxp-).

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

Generate slide deck presentations using image generation with curated professional visual styles. Produces individual slide images and stitches them into a PDF. Use when asked to create presentations, pitch decks, slide decks, or any visual slide-based content.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Shorten long URLs into compact short links using the free spoo.me API. Use when the user wants to shorten a URL, create a short link, generate a tiny URL, or make a link shorter. Supports custom aliases, password protection, and click limits. No API key or signup required.

Inspect Vercel deployments, runtime logs, build logs, and projects via the Vercel REST API (read-only). Check Vercel logs, warnings, and errors; find failed, building, or canceled deployments; read build output for a failed build; filter runtime logs by level (error/warning) or HTTP status (500/5xx); and look up project or deployment details by id, name, branch, or commit. Use for Vercel observability and debugging: deployment failures, build errors, runtime 500s, and production/preview deploy status. Requires a Vercel access token.

Video and audio processing toolkit for TTS audio generation, combining images with audio, video concatenation, and media conversion. Use when creating videos from images and narration, stitching video chunks together, extracting audio, trimming clips, adding subtitles, or converting between media formats.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Query ZoomInfo B2B go-to-market intelligence through the Enterprise API: search the database of 100M+ companies and 300M+ professional contacts (free), enrich contact and company records with emails, phones, titles, firmographics, and technographics (consumes credits), pull intent signals, resolve lookup values, and check API usage and remaining credits. Use for prospecting, lead and account enrichment, building target/territory lists, or any ZoomInfo data task. Requires ZoomInfo Enterprise API credentials: recommended is a non-expiring client ID + private key (PKI); username + password or a short-lived JWT also work.