Explorar skills

Use to write content in a specific brand voice. Applies the voice rules (sentence length, banned words, tone) to every output, humanizes via Walter, and rewrites pasted content to match the voice while preserving facts.

When addressing slow application endpoints, high database CPU usage, or standardizing data access patterns.

Verify code works at runtime through build verification (mandatory), LSP diagnostics, ad-hoc verification for projects without frameworks, E2E and smoke tests, and visual verification (screenshot-analyze-verify for UI changes). Skip whitelist strictly enforced (markdown-only, config-only, dependency-bump-only with evidence); all other skips require Proactive-Autonomy escalation. Use after quality

When designing how a system recovers from and reports failures.

Use to write technical documentation. Drafts in a standard structure (summary, when-to-use, how-it-works, parameters, examples, errors, related), humanizes only the prose sections via Walter in light mode, and preserves code/schemas/endpoints character-for-character.

When configuring automated build, test, and deployment workflows for a repository.

When designing and implementing web interfaces to ensure they are usable by everyone.

Use when producing location-specific SEO content at scale. Generates unique humanized pages per city, preserves '[service] in [city]' patterns, and flags overly similar pages that risk Google's duplicate location filter.

When building or refactoring React UI components to ensure reusability and maintainability.

When creating or extending an HTTP API for client consumption.

When deciding where and how to store data in a modern web application.

Illuminates what the answer never addressed — dimensions, stakeholders, and failure categories invisible from the activation path.