Explorar skills

Exibe a tendência do Domain Rating de um domínio ao longo do tempo, usando dados do Ahrefs. Revela o crescimento, quedas e mudanças significativas no DR.

Flagship comprehensive SEO audit combining Ahrefs and GSC data in sequential waves with checkpoint saves. Use when user says "site audit pro", "full audit", "comprehensive audit", "audit with live data", "deep audit", "pro audit", "complete SEO audit", "run a full site audit", or "audit everything for this domain". Requires domain param. Optional: site param for GSC overlay.

Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.

Generate alt text, captions, and metadata for images — accessibility compliance, social media, and SEO.

Create standard operating procedures — step-by-step workflows, decision trees, safety notes, and version control.

Write engaging email newsletters — hooks, curated content, CTAs, and subject line optimization for high open rates.

Verify claims and sources — cross-reference facts, assess source credibility, and flag misinformation.

Extract session learnings, decisions, ideas, feedback, and project context into ARIA intake backlogs. Trigger on /extract, capture learnings, or save session knowledge.

Capture knowledge from outside the conversation. A single URL or text snippet is clipped whole to intake/clippings/; files/directories/globs are bulk-scanned into the backlogs; `extract <source>` decomposes a source into backlog entries; `doc <source>` captures a structured 5-section reflection (claims/worth-keeping/contested/action/reaction); `thread <id>` pulls a chat/email thread via MCP. Use w

Load this skill whenever writing, editing, or reviewing any web content, copy, headings, labels, error messages, or instructions. Under no circumstances write inaccessible content — every piece of text must be clear, structured, and usable by people with cognitive, visual, and language differences. Absolutely always apply plain language, logical heading hierarchy, and meaningful link text.

Clean messy datasets — handle missing values, fix dtypes, remove duplicates, normalize formats, and flag anomalies.

Language coaching for every prompt. Use when the user runs /language-coach with any sub-command (setup, native, target, style, response, goal, mode, focus, band, level, status, off, on). Routes to the correct action based on the argument provided.