CSS styles often drift across components and utility classes. This skill guides semantic class creation, Tailwind composition, dark mode coverage, tests, and refactoring.

Complex features often have several valid implementation paths. This skill runs independent agent implementations, reviews them, and helps select the strongest result.

Multi-agent projects often fail from unclear orchestration, weak boundaries, and unmanaged tool access. This skill provides architecture patterns, safety controls, and production checklists for coordinated agents.

Manual commit preparation can miss staged changes, message style, or sensitive files. This skill reviews git state and helps create clear conventional commits.

Code reviews can miss bugs, security flaws, and maintainability issues. This skill guides Claude, Codex, and Claude Code through structured review steps.

Telegram development spans bots, Mini Apps, webhooks, payments, and MTProto clients. This skill provides focused guides, templates, and best practices for Claude, Codex, and Claude Code.

Frontend teams often need accurate screenshots of styled components without a browser automation stack. This skill shows how to use snapDOM to export DOM elements as SVG, PNG, JPG, WebP, Canvas, or Blob outputs.

Prediction market apps need accurate API, trading, and live data guidance. This skill helps Claude, Codex, and Claude Code use Polymarket references for REST endpoints, CLOB workflows, and WebSocket streams.

Exchange APIs differ in symbols, order rules, and capabilities, which makes trading integrations difficult to implement correctly. This skill helps you use CCXT documentation to build, inspect, and troubleshoot those integrations.

Pull requests often lose context when titles, summaries, and tests are inconsistent. This skill guides Claude, Codex, and Claude Code to produce structured GitHub PR content.

Reviewing branch changes can be slow when commits, diffs, and status are scattered. This skill gathers Git context for PRs, reviews, and commit planning.

Finding the right test command and interpreting failures slows verification. This skill detects common test setups, runs the test command, reports failures, and guides focused fixes.

Implementation tasks need consistent edits, commits, and status reporting. This skill guides Claude, Codex, and Claude Code through investigation, code changes, git commits, and completion reports.

Preparing a pull request can miss branch checks, summary details, or test notes. This skill guides Claude, Codex, or Claude Code through a consistent GitHub PR workflow.

Large repositories slow down orientation and targeted searches. This skill helps Claude, Codex, and Claude Code locate files, symbols, and context quickly.

Turning requirements into safe code changes is time-consuming. This skill edits files, follows project conventions, and verifies behavior with checks when possible.

Complex features often fail when architecture decisions are unclear. This skill helps Claude, Codex, and Claude Code compare options, expose risks, and produce implementation plans.

API work often starts with vague prompts and uneven requirements. This skill gives Claude, Codex, and Claude Code a minimal API-focused starting point.

Building a useful Agent Skill requires clear triggers, structure, and safe supporting files. This skill guides Claude or Codex through discovery, design, creation, and handoff.

Code reviews can miss security, testing, and maintainability issues. This skill guides Claude, Codex, and Claude Code through structured review steps.