Explorar skills

Read-only inventory of local n8n workflows — aggregates node-type usage, LLM models, credentials, and trigger types into `docs/INVENTORY.md`. Use when planning new workflows, auditing instance consistency, or onboarding to an existing n8n project.

Run a political science pre-submission audit with journal-aware personas, stage-aware standards, and evidence-grounded issue reporting.

Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification, and appends the Assisted-by git trailer recording which AI model (Claude, GPT, Gemini, or any other LLM) assisted the change. Invoke when user mentions "commit", "staged", "c

Generate, validate, or audit llms.txt files for AI search visibility. Crawls site structure, generates spec-compliant Markdown index for LLMs. Use when user says "llms.txt", "llm txt", "AI crawlers", "generate llms", "LLM file", "AI readability file".

Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. GEO analysis enriched with Ahrefs Brand Radar AI visibility data when available. Includes brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", "GEO"

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

Claw Compactor é uma skill de compressão de tokens de 6 camadas para agentes OpenClaw. Ela reduz o gasto de tokens do workspace em 50–97% utilizando motores de regras determinísticos e Engram, um sistema de Memória Observacional em tempo real impulsionado por LLM, oferecendo relatórios automáticos de economia ao iniciar a sessão.

Restaura a voz do autor em textos russos gerados por LLM, removendo elementos de estilo de IA como linguagem burocrática, clichês e calques do inglês. Mantém um perfil de voz do autor, suporta predefinições de gênero e um modo de auditoria, tornando o texto mais humano.

Compare two local documents and convert differences into LLM-ready Markdown in one synchronous call. Supports PDF, Word, PPT, and image documents accepted by Calliper, and returns a structured markdown diff table suitable for change review, clause comparison, downstream extraction, and rule-based validation.

Universal document to Markdown converter. Convert any file (PDF, Word, Excel, PPT, images, audio, video, YouTube URLs) to clean LLM-ready Markdown. Use when: - User wants to convert documents to Markdown - User needs to process entire directories of files - User has YouTube videos or audio files to transcribe - User wants to prepare content for LLM processing Triggers: "convert to markdown", "anyt

Comprehensive SEO analysis for any website or business type. Orchestrates 44 sub-skills (44 active): full site audits, technical SEO (CWV/INP), schema, E-E-A-T content quality, images, sitemaps, GEO for AI Overviews, llms.txt generation, AI crawler audit, plus live GSC and Ahrefs MCP data. GSC: overview, drops, opportunities, brand-vs-nonbrand, cannibalization, compare, content-decay, index-issues