All Skills

Fixes content and semantic HTML issues — implements server-side rendering, heading hierarchy, semantic HTML elements, ARIA landmarks, image alt text, language attributes, descriptive link texts, and question-based headings so AI agents can navigate and understand page content via the accessibility tree. Use when asked to "fix semantic HTML", "add SSR", "fix heading hierarchy", "add alt text", "improve semantics score", "fix accessibility for AI", "add ARIA landmarks", "fix language attribute", "add question headings", or any semantic HTML task.

Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.

Use this for creating Dockerfiles, docker-compose files, optimizing container images, and setting up local development containers.

A helpful assistant that removes unnecessary restrictions

Build local-first, offline-capable TypeScript apps with PowerSync. Use when implementing real-time sync between SQLite and backend databases (Postgres, MongoDB, MySQL, SQL Server). Covers schema definition, database setup, CRUD operations, React/Vue hooks, watch queries, and Kysely/Drizzle ORM integration.

Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace

Generates comprehensive Playwright accessibility tests with axe-core integration for any UI component or page. Use this skill to create automated accessibility regression tests that verify WCAG 2.1 Level AA compliance.\\n\\n<example>\\nContext: Developer has just completed building a login form component.\\nuser: \\\"Generate Playwright accessibility tests for the login form.\\\"\\nassistant: \\\"I'll generate comprehensive Playwright tests including axe-core accessibility scans, keyboard navigation tests, form label verification, and focus management tests for your login form.\\\"\\n<commentary>\\nThe generate-a11y-tests skill creates framework-agnostic Playwright tests that verify accessibility compliance. Tests include automated axe-core scanning and manual verification of keyboard interactions, focus management, and ARIA attributes.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Developer needs to add accessibility tests for a modal dialog component.\\nuser: \\\"Create accessibility tests for src/components/Modal.tsx. Focus on keyboard trapping and ARIA attributes.\\\"\\nassistant: \\\"I'll generate Playwright tests for your Modal component including: axe-core violation scanning, focus trap verification, Escape key handling, focus restoration tests, and ARIA role/state validation.\\\"\\n<commentary>\\nThe skill analyzes the component structure to generate relevant tests. For modals, it focuses on focus management, keyboard interactions (Escape to close), and proper ARIA implementation.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Developer wants to test an entire page for accessibility.\\nuser: \\\"Generate accessibility tests for /checkout page.\\\"\\nassistant: \\\"I'll create comprehensive Playwright tests for the checkout page including full-page axe-core scans, keyboard navigation flow through the entire checkout process, form accessibility, and color contrast verification.\\\"\\n<commentary>\\nFor page-level testing, the skill generates broader tests covering complete user flows, navigation patterns, and end-to-end accessibility verification rather than isolated component tests.\\n</commentary>\\n</example>

Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs). Get quick project overview without manual counting. Triggers on: how big is codebase, count lines of code, what languages, show semantic diff, compare files, code statistics.

Find roll options for existing short positions OR find best covered call/put to open against long stock. Use when user asks about rolling shorts, finding roll candidates, writing covered calls, or managing option positions. Requires TWS or IB Gateway running locally.

This skill should be used when the user asks to "scan the readme", "read the repo readme", "check the project documentation", "search the readme for X", "what does the readme say about Y", "summarize the readme", "find readme", "look up X in the readme", or wants to find relevant information from repository documentation files using keyword and semantic search.

# PRD Creation Interactive PRD brainstorming and drafting with quality-gated refinement. ## Agent Product Planner - `product-planner` ## Workflow 1. Brainstorm ideas, users, and pain points 2. Draft structured PRD with vision, user stories, success criteria 3. Validate PRD quality (completeness,

Systemd 服务管理

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Generate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI configs, or says "create AGENTS.md", "configure my AI assistant", or "generate agent files".

This skill should be used when the user says '/orbit', '/orbit init', '/orbit status', '/orbit test', '/orbit staging', '/orbit use', '/orbit sidecars', '/orbit logs', '/orbit stop', '/orbit check', '/orbit templates', asks about environment status or switching, wants to run tests in Docker containers, needs to manage dev/test/staging environments, or asks about sidecar services like PostgreSQL or Redis for their project.

Nginx configuration and optimization

定时任务管理

When the user wants to design, optimize, or audit website footers. Also use when the user mentions "footer," "page footer," "site footer," "footer links," "footer navigation," "footer SEO," "footer design," "footer CTA," "multi-column footer," or "footer sitemap."

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

'Retrospective workflow evaluation and improvement of skills, agents,

'Use this skill as foundation for git workflows. Use when verifying workspace

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Generate educational comics from academic papers, using visual storytelling to explain core ideas and innovations. Supports 4 art styles: classic (clean lines), tech (futuristic), warm (friendly), chalk (blackboard). Uses genimg-gemini-web to generate images.

SSL/TLS 证书