Skills Registry

Analyzes Astro 5 projects (.astro, astro.config.mjs/ts) to identify performance issues, applies 47 optimization rules across 8 prioritized categories (islands architecture, build optimization, content collections, image optimization, component patterns, view transitions, environment config, advanced patterns), and refactors code following partial hydration best practices. Use when building Astro sites, configuring SSG/SSR/hybrid rendering, implementing islands with client:* directives, setting up content collections, or optimizing images and assets. Do NOT use for non-Astro frameworks like Next.js, Nuxt, or SvelteKit.

Generates Azure Bicep module files following established project conventions, with secure-by-default and cost-optimised configurations. Reads per-resource .md reference files for security baselines, cost guidelines, and code patterns. Use when creating a new Bicep module, adding a resource to an existing module, writing a role assignment module, or reviewing Bicep for convention violations. Validates parameter ordering, decorator patterns, security defaults (RBAC, soft delete, TLS 1.2, private endpoints), cost-appropriate SKU defaults, idiomatic output ordering, and code patterns (role GUIDs, conditional resources, private endpoints, parent-child relationships, null-safe access). Do NOT use for Terraform, ARM JSON, or Pulumi authoring.

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.

Creates and orchestrates high-performance GSAP animation components — page loaders, scroll effects, text reveals, navigation transitions, slideshows, and micro-interactions. Generates production-ready code with state gating, defensive DOM queries, and proper cleanup. Use this skill whenever the user asks to build animations, motion design, page transitions, loading sequences, scroll-triggered effects, parallax, text splitting/revealing, animated navigation menus, slideshows, or any interactive motion component. Also trigger when users mention GSAP, GreenSock, ScrollTrigger, SplitText, Physics2D, Lenis smooth scroll, or want to add "life" or "polish" to a UI. Covers vanilla JS, React, Next.js, and Astro implementations. Do NOT use for CSS-only animations, Framer Motion, or non-animation frontend tasks like routing or state management.

Moves someone from the old symlinked skill install (skills linked into ~/.claude/skills or a project's .claude/skills) to plugins from the skill marketplaces, checking before and after that no place loses a skill. Use when a colleague says 'migrate my skills to plugins', 'passa ai plugin', 'switch to the new skills install', 'I still have the old symlinks', or after velais-skills moved to plugins. Do not use to install one plugin (plain `claude plugin install`) or to write a new skill (skill-creator).

Comprehensive guidance for designing and optimizing n8n 2.0+ (2026) workflows. Handles requirements analysis, node selection (Standard vs. AI Agent), and isolated Code node development. Use when the user says 'Help me create an n8n workflow', 'Build an automation for...', or 'Debug my n8n JavaScript code'. Do NOT use for general software engineering unrelated to n8n logic.

Extracts, processes, converts, and handles all PDF file operations. Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Generates, runs, and debugs Playwright end-to-end tests for web applications. Automates browser testing setup, creates test files with accessible locators, and validates UI behavior. Use when the user asks to add tests, write e2e tests, test the frontend, verify UI behavior, add Playwright, set up browser testing, or when Claude needs to verify that frontend changes work correctly after implementation. Also triggers for requests like "make sure this works", "test the UI", "check the page renders", or any task involving browser-based verification of a React/Vite/Next.js application. Do NOT use for unit tests, component-level testing with Jest/Vitest, or backend API testing without a browser.

Analyzes React and Vite code (.tsx, .jsx, .ts, .js) to identify performance issues, applies 40+ optimization rules across 7 prioritized categories (waterfalls, bundle size, data fetching, re-renders, rendering, JavaScript, advanced patterns), and refactors code following TanStack Query best practices. Use when optimizing React components, reducing bundle size, eliminating async waterfalls, fixing re-render issues, or implementing efficient data fetching patterns. Do NOT use for backend/server-side optimization or non-React frameworks like Vue or Angular.

Reads and converts SharePoint files (.xlsx, .docx, .pptx, .xls, .doc, .ppt) to markdown using the M365 CLI. Use when the user says 'read from SharePoint', 'fetch a document from SharePoint', 'browse the Projects folder', 'download from SharePoint', 'search SharePoint for...', or provides a SharePoint URL (velaisfzco.sharepoint.com). Also triggers on 'get the spreadsheet from SP', 'pull that file from the company site', or 'what's in the Projects folder'. Do NOT use for uploading files to SharePoint, editing SharePoint pages, managing SharePoint permissions, or converting local Office files without a SharePoint context.

Creates narrated screen-recorded walkthrough videos from written guides for web apps (Odoo, Business Central, any SaaS). Handles TTS synthesis, Playwright recording, ffmpeg montage with per-step synchronisation. Use when a guide or walkthrough document needs to become a video with voiceover, when feedback arrives about voice/action sync issues, or when recordings show pages jumping instead of being clicked.

Creates and validates effective agent skills. Walks users through use case definition, frontmatter generation, instruction writing, progressive disclosure design, and packaging. Use 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. Do not use for general software engineering tasks unrelated to skill authoring.

Explains and parses the conversation.json schema produced by slack-vault-sync. Use when reading extracted/slack/[channel]/conversation.json — explains the schema (nested threads, files, reactions) so you don't have to reverse-engineer it from the raw JSON. Trigger on "read the Slack conversation.json", "parse extracted/slack", or when a channel's synced content needs to be scanned for facts. Do NOT use for producing conversation.json in the first place (see slack-vault-sync) or for reading live Slack via API/MCP.

Syncs a Slack workspace into an Obsidian-style vault as one conversation.json per channel, with attachments and incremental watermarks. Use when syncing Slack into a vault — "sync Slack", "ingest the new Slack messages", "pull the Slack channels", "update the watermarks", "back up the channels", "what came in on Slack", or before an ingest step when client feedback lives in Slack. Covers the first full pull of a workspace (all history + attachments) and every incremental update afterwards, producing one conversation.json per channel in extracted/slack/. Do NOT use for reading an already-synced conversation.json (see slack-conversation-read) or for posting/sending Slack messages.

Manages the Velais 1Password business account in its agreed structure (Velais – Admin / Engineering / Team vaults, one 'Client – Name' vault per client, personal Employee vaults): audits access, creates client vaults, handles onboarding and offboarding, and converts, renames, retags and deduplicates items with the op CLI and plan .json files, without ever displaying secret values. Use when the user says 'sistema/riordina 1Password', 'audit 1Password', 'who can see what in 1Password', 'add a new client vault', 'onboard/offboard someone in 1Password', 'clean up tags', 'merge duplicates', 'move these credentials to the right vault', or after a .csv or LastPass import. Do NOT use for reading a single password to use it, for SSH-agent or git configuration on its own, for other password managers, or for Azure Key Vault / app secret management.

Authors, reviews and deploys the Azure infrastructure for a Velais platform: Bicep (.bicep, .bicepparam) on Azure Container Apps, or a VM where ACA cannot serve, with GitHub Actions OIDC CI/CD, PostgreSQL Flexible Server, Key Vault, ACR, Storage, VNet+NAT and .env-driven secret sync. Use when scaffolding infra for a Velais or client project, adding a Container App, Job or VM, wiring OIDC CI/CD or secret sync, binding a custom domain with TLS, reviewing Bicep for Container Apps, porting a stack to a client subscription, or debugging a failed deploy. Also use when writing APPLICATION CODE that will run on Container Apps: a scheduled job, background task or long request, anything that depends on a timeout, a restart or two replicas. Also on: 504 at exactly four minutes, a revision that will not start, "relation does not exist" after deploy, RequireCustomHostnameInEnvironment, CertificateProvisioningError, BCP307, BCP318. Do NOT use for Terraform, AWS, GCP or a single generic Bicep module (use bicep-modules).

Velais AI Solutions brand identity guidelines covering color palette, typography, logo usage, gradients, brand voice, and visual patterns. Use when creating or reviewing any Velais-branded output: websites, documents (.docx), presentations, marketing materials, social media graphics, or PDFs. Triggers on: designing Velais pages or components, choosing colors or fonts for Velais content, creating Velais-branded documents or presentations, reviewing designs or copy for brand consistency, embedding Velais logos, or any task requiring Velais visual identity decisions. Do NOT use for general design advice unrelated to Velais, or for framework-specific implementation details (Tailwind config, CSS-in-JS setup).

Formats rendered markdown and prose content with the Velais brand identity. Use when adding blog posts, documentation pages, changelogs, or any long-form markdown content to a Velais website (Astro or Vite+React). Configures the portable `prose-velais` CSS class (.css) and integrates framework-specific layouts for .astro, .tsx, and .mdx files. Do NOT use for general UI layout, component design, or color system setup — use `velais-ui-design` for those tasks.

Build Velais-branded presentations that match the Velais Brand Style Guide 2026: Claude Slides artifacts (the Slides artifact type) and, when asked, repo decks (.dc.html) with PDF exports. Covers the header band, section dividers with the giant tonal number, the 37% vertical-rule two-column content layout, index, stat, pricing, facilitator, cover and "Beyond IT." closing slides, the background/text/line colour pairings, the type scale, and the Slides-format workarounds (400px font cap, no negative offsets, crop-zoom on backgrounds). Use for ANY Velais deck, pitch, course overview, sales or training presentation, or when asked to restyle slides "to the Velais brand guidelines". Complements velais-brand-guidelines (general brand rules): this one is for building decks. Do NOT use for Velais web UI (use velais-ui-design), Word or PDF documents that are not slide decks, or other brands.

Creates and maintains a Velais-branded project dashboard as static .html pages generated from .md files in a dashboard/ folder: three shared pages committed for the whole team (Tasks with due dates, client milestones and a timeline, Resources, Handoffs with internal handoff files and client blockers) plus private, per-person profiles that stay local (Topics, Mockup, Data, Structure, Plan, session log). Use when a user asks for a project dashboard, status page, control panel or "where does the project stand" view for a Velais project; when adding tasks, milestones, resources, handoffs, decisions, open questions, data sources, phases, mockups or todos; when switching or creating a dashboard profile; or when a Claude session must log its summary. Do NOT use for client-facing React apps (use velais-ui-design), for BC-Delivery vault control planes with write-back, or for one-off charts.

Provides the single source of truth for building Velais-branded internal UI products. Use when starting a new Velais dashboard, tool, or client-facing app; replicating the Loader or LoginPage components (.tsx files); setting up the color system (CSS tokens, Tailwind classes), typography (Onsite Extended font, WOFF2/WOFF files), or GSAP animation conventions; or configuring shadcn/ui (New York style) for a Velais project. Covers the full tech stack (React 19 + TypeScript + Vite + Tailwind CSS 4 + TanStack React Query + GSAP + Hono). Do NOT use for general design advice unrelated to Velais, Azure DevOps API integration, or backend/auth configuration (WorkOS, Hono middleware).