Claude Skills by juanitourquiza

Audit code, components, or screenshots for WCAG 2.2 accessibility barriers across web and mobile projects.

Verify backend/API releases with tests, migrations, queues, integrations, and endpoint smoke checks.

Diagnose bugs, regressions, failing tests, or slow behavior by building a reproduction loop before code changes.

Review product copy, i18n, email, and landing text for clarity, approvals, and implementation-safe wording.

Review changed code before commit or PR with fast checks plus SOLID, security, performance, and test coverage audit.

Design or improve module seams, interfaces, testability, and codebase structure without changing product behavior.

Triage a bug or issue, collect required details, create a ClickUp ticket, and open a GitHub issue from templates.

Create a Draft GitHub PR or GitLab MR from git diff, commits, CODEOWNERS, and the ShipFrame PR template.

Create a ClickUp task from raw input by classifying it as US, BUG, IMP, TASK, or SPIKE and filling the template.

Collect concrete deploy or release proof before saying a publish, release, or deployment is complete.

Scan a UI project for theme, colors, typography, spacing, and component patterns, then generate DESIGN.md.

Audit design system docs in Markdown or Storybook and propose concrete documentation or Storybook improvements.

Set up design-system documentation by running design-expert, design-system-docs, and planning execution subtasks.

Build glossary, domain language, CONTEXT.md, or ADRs when designing or changing a project domain model.

Audit reports, handoffs, or replies and classify delivery claims by evidence strength.

Gather requirements for a new feature through structured questions and produce a ticket-ready specification.

Verify frontend releases with project-aware build, route smoke checks, assets, i18n, and version validation.

Generate or refresh a team-ready README by scanning stack, purpose, commands, and project conventions.

Compact the current conversation into a handoff document for another agent or future session.

Implement a scoped task end-to-end by reading context, planning files, changing code, verifying, committing, and preparing PR/MR.

Scan a new or unfamiliar repo and generate AGENTS.md with stack, commands, structure, and agent context.

Consult version-compatible external library documentation before changing code that depends on an API, SDK, framework, or provider.

Diagnose MCP connector failures by separating stored connection state from live upstream tool evidence.

Plan a ticket or task into ordered subtasks with context, acceptance criteria, out-of-scope, and done definition.

Run feature discovery and plan-expert together for a new feature, producing ticket and subtask structure.

Refresh project context from memory, WIKI/AGENTS files, git state, and repo conventions before work.

Read project-specific workflow rules before releases, deploys, onboarding, or custom repository conventions.

Orchestrate a generic release by loading project profile rules, running checks, and collecting deploy evidence.

Run explicit Verify commands from plans/checklists and report only passing proof.

Build a project-aware release checklist before merge, deploy, publication, or versioned release.

Research a docs/API/version question against primary sources and capture findings as a Markdown file in the repo.

Use red-green-refactor test-driven development for features, bug fixes, or integration-test-first work.

Convert documents into an interconnected LLM wiki using the Karpathy wiki pattern and project conventions.

Initialize a new project wiki vault with WIKI.md, index, conventions, sync config, and starter structure.

Answer questions from the active project wiki by reading the index and relevant wiki pages.

Sync the project wiki with source changes since origin/main, updating docs and the wiki operation log.