Agent skills for Claude Desktop

Automates comprehensive web application testing including visual, accessibility, and E2E checks using Playwright CLI.

Use when setting up or optimizing developer workflows in a monorepo, managing mise tasks, git hooks, CI/CD pipelines, database migrations…

Initiates a structured analysis of a problem using the DEV WORKFLOW PROCESS with specific contextual guidance.

Generate or refresh the workspace-root AGENTS.md and its CLAUDE.md redirect shim for a VS Code .code-workspace root.

Ship one iteration of issue work as a pull request — commit with a structured message, push the branch, and open a PR whose `Closes #N`…

Generate clear, PM-friendly release notes, changelogs, and session summaries from git commits, feature work, or the current development…

Automates documentation and code consistency checks to ensure technical manuals accurately reflect the current codebase.

Use when Codex is building or iterating on a web game (HTML/JS) and

Write a developer onboarding document for a service, codebase, or team.

Developer relations playbook builder — produces a DevRel program design covering community platform, contributor program tiers, ambassador…

Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on…

Set up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity.

Use when estimating time, effort, or complexity for features or projects - provides structured estimation workflows with breakdowns…

Audits infrastructure setup — database config, caching, performance, and scaling patterns.

Creates infrastructure.md and runbook.md (Docker-conditional).

Generate and optimize GitHub Actions CI/CD workflows.

Integrate one-shot x402 payments into a Node.js or browser application with @dexterai/x402/client.

Diagnose runtime infrastructure issues — cold starts, timeouts, scaling problems, network failures.

Diagnose why an authorized scraper that previously worked now fails, returns incomplete data, or diverges from browser behavior.

Diagnoses bias, anomalies, and strange results on a PostHog experiment.

UI branch of the diagnosing loop. Use when debugging any UI bug — wrong rendering, layout or scroll jumps, flicker, styling, interaction…