Menu
Skills in this repository
SkillsMP has collected 158 skills from Leo-Atienza/atlas-claude. Open a skill to review its source and details.
Leo-Atienza/atlas-claudeShowing 38 of 158 collected skills.
Manages Cursor/Codex session boundaries via checkpoints and handoffs. Use when resuming work, multitasking across repos, noticing repeated context resets, requesting a handoff bundle, splitting discovery from implementation phases, or after long idle gaps.
Runs a repeatable plan-execute-verify-review chain for repeatable multi-step workflows hitting build/test/review tooling. Trigger on ship this feature safely, guarded rollout, add tests review PR, multitask decomposition, deterministic delivery pipeline for…
Upgrades React Native apps to newer versions by applying rn-diff-purge template diffs, updating package.json dependencies, migrating native iOS and Android configuration, resolving CocoaPods and Gradle changes, and handling breaking API updates. Use when…
Vercel AI SDK 7 for Next.js 16 (v7 stable 2026-06-25) — generateText / generateObject / streamObject, Agent abstraction with tool loops (durable WorkflowAgent in v7), human-in-the-loop tool approval, useChat hook with structured tool UI. Provider-neutral…
Vitest — fast unit testing with Testing Library integration and test pyramid strategy
Manage the personal knowledge wiki (Obsidian vault at Documents/Wiki/) and per-project wikis. Five modes: ingest (compile source into wiki pages), query (search and retrieve knowledge), lint (health check), evolve (refine schema), scaffold (init project…
Auto-generate project-level CLAUDE.md from templates based on detected stack. Adapted from Ruflo's 30+ template system. Invoke from /new after project directory is set up.
Detect capability gaps and autonomously create skills, add free MCP servers, or organize agent teams. Trigger when: a task requires tools you don't have, a workflow pattern repeats 3+ times, a tool call fails because the capability is missing, or the user…
Automatically organize multi-agent teams for complex tasks. Scores task complexity across 5 dimensions, selects appropriate agents from the Flow ecosystem, coordinates parallel work, and synthesizes results. Use when: a task involves multiple independent…
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or…
Evaluate design from a UX perspective — visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique,…
Disciplined development cycle that enforces discovery, scoping, and design BEFORE any code gets written. Use when starting ANY new feature, project, or significant change. Invoke via /dev-cycle. Prevents scope creep through MoSCoW prioritization, appetite…
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…
Token-efficient code review using structural graph analysis and blast-radius computation. 8.2x average token reduction by reviewing only affected files instead of entire codebase. Use when: reviewing PRs, analyzing change impact, pre-merge checks, or user…
Compose and publish LinkedIn posts (text, articles, images) via the LinkedIn API. Use when user wants to draft, preview, or publish content to LinkedIn.
Google Nano Banana (Gemini Image) — AI image generation and editing via the Gemini API. Covers all models (2.5 Flash, 3.1 Flash, 3 Pro), text-to-image, image editing, multi-turn chat, grounding, reference images, thinking mode, batch processing, constraints,…
Complete browser automation and testing with Playwright. Four modes: CLI tool (playwright-cli commands for interactive browser control), JS script-based automation (write JS to /tmp, execute via run.js with dev server auto-detection), Python automation…
Run comprehensive WCAG 2.1 AA+ accessibility tests on a URL. Use when user wants to test accessibility, a11y compliance, screen reader support, or keyboard navigation.
Run the complete UI testing suite — all 15 test skills across functional testing and UX design quality. Use when user wants a comprehensive site audit, full test suite, or complete quality assessment.
Audit design system consistency across pages. Use when user wants to check visual consistency, design tokens, component reuse, color palette, typography, spacing, or cross-page uniformity.
Analyze conversion optimization, cognitive load, and trust signals. Use when user wants to audit conversion funnels, reduce friction, analyze cognitive load, check trust signals, or optimize CTAs.
Test cross-browser consistency across Chromium, Firefox, and WebKit. Use when user wants to verify browser compatibility, cross-browser layout, or browser-specific issues.
Test user flows, authentication, navigation, and SPA behavior. Use when user wants to test login flows, registration, browser history, pagination, search, CRUD operations, or routing.
Run comprehensive form validation and input testing on a URL. Use when user wants to test forms, input fields, validation, file uploads, or submit behavior.
Analyze attention patterns, visual hierarchy, and interaction prediction. Use when user wants to analyze UX layout, visual hierarchy, CTA placement, click target analysis, or attention scoring.
Test link integrity, navigation, and semantics. Use when user wants to check for broken links, test navigation, verify external links, or audit link behavior.
Run performance and Core Web Vitals testing on a URL. Use when user wants to test page speed, LCP, CLS, INP, load times, asset optimization, or runtime performance.
Run regression detection by comparing current page state against stored baselines. Use when user wants to detect regressions, compare before/after states, check for structural changes, or run baseline comparisons. Use --baseline flag to capture initial…
Run responsive design and visual adaptation tests across 4 viewports. Use when user wants to test responsive layout, mobile design, viewport behavior, dark mode, or print styles.
Run OWASP+ security vulnerability testing on a URL. Use when user wants to test security, find XSS, SQL injection, check headers, CSRF, authentication security, or data exposure.
Run SEO and meta data testing on a URL. Use when user wants to test SEO, meta tags, Open Graph, structured data, sitemap, robots.txt, or crawlability.
Test UI states and dynamic behavior including loading, empty, error, overlay, and animation states. Use when user wants to test modals, toasts, loading spinners, empty states, error handling, or animations.
Analyze micro-copy, CTA text, error messages, and content quality. Use when user wants to audit UX writing, button labels, error messages, form labels, or content clarity.
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes creating slide decks, pitch decks, or presentations; reading or extracting text from .pptx files; editing or updating existing presentations; combining or splitting…
Auto-generate project-level CLAUDE.md from templates based on detected stack. Adapted from Ruflo's 30+ template system. Invoke from /new after project directory is set up.
Complete UI/UX design system for web and mobile. Part A: UX Strategy — user flows, information architecture, Nielsen's heuristics, onboarding, empty states, error recovery, micro-copy, conversion optimization, UX audits. Part B: Design Intelligence — 50+…
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet from scratch or from other data sources; or…