Top Agent Skills

Cloud Migration Architect

mermaid-to-ascii

Naming Strategist

codebase-to-mermaid

WordPress Performance Review

WordPress Plugin/Theme Senior Architect Review

Diagnose failures from runtime evidence before editing code.

Read, send, draft, delete, and organize Gmail emails

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe.

Matplotlib is Python's foundational visualization library for creating static, animated, and interactive plots.

Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

List, add, and update StyleSeed design tokens while keeping JSON sources, CSS variables, and dark-mode values in sync.

Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.

Generate reusable UI patterns such as card sections, grids, lists, forms, and chart wrappers using StyleSeed Toss primitives.

Use before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.

Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".

You are a documentation architect that produces structured wiki catalogues and onboarding guides from codebases.

Create care plans with assessments and interventions. TRIGGERS - Use when user needs help with care-plan related tasks.

Perform comprehensive SEO audits with technical, content, and link analysis. TRIGGERS - Use when user needs help with seo-audit related tasks.

Write case briefs with facts, issues, and holdings. TRIGGERS - Use when user needs help with case-brief related tasks.

Write ESG reports with metrics and disclosure. TRIGGERS - Use when user needs help with esg-report related tasks.

Create size guides with measurements and fit advice. TRIGGERS - Use when user needs help with size-guide related tasks.

Audit web applications for WCAG compliance. TRIGGERS - Use when user needs help with wcag-audit related tasks.

Write exam questions with difficulty progression. TRIGGERS - Use when user needs help with exam-writer related tasks.

Create lesson plans with objectives, activities, and assessments. TRIGGERS - Use when user needs help with lesson-plan related tasks.

Create process maps with steps, decisions, and handoffs. TRIGGERS - Use when user needs help with process-map related tasks.

Plan auction events with items and bidding. TRIGGERS - Use when user needs help with auction-plan related tasks.

Write cease and desist letters with legal basis. TRIGGERS - Use when user needs help with cease-desist related tasks.

Conduct energy audits with efficiency recommendations. TRIGGERS - Use when user needs help with energy-audit related tasks.

Design grading plans. TRIGGERS - Use when user needs help with grading-plan related tasks.

Design ICO strategies. TRIGGERS - Use when user needs help with ico-strategy related tasks.

Design NFT strategies with creation and marketplace. TRIGGERS - Use when user needs help with nft-strategy related tasks.

Write policy briefs with analysis and recommendations. TRIGGERS - Use when user needs help with policy-brief related tasks.

Create Request for Information templates for construction. TRIGGERS - Use when user needs help with rfi-template related tasks.

Use when aligning spliced RNA-seq reads to a reference genome, generating genome indices, or performing splice-aware alignment for transcriptome analysis.

Use when you need to navigate relationships between records in NCBI Entrez databases, find related articles, track citations, or link records across different databases such as PubMed to Protein.

Use when calculating thermodynamics of RNA-RNA interactions, including accessibility and binding energy predictions for RNA duplex formation.

Use when following local EDirect link relations such as PubMed `CITED`, `CITES`, or `PMCID` from an incoming UID stream or `ENTREZ_DIRECT` message.

Use when converting PubMed `DocumentSummary` XML into `Pubmed-entry` ASN.1 text, or into the intermediate XML form before final ASN.1 flattening.

Use when inferring maximum-likelihood phylogenies from aligned sequences, performing automated model selection, or assessing branch support with bootstrap or aLRT methods

Use when building, indexing, or querying local XML record archives from NCBI Entrez databases, creating inverted indices, or managing PubMed local caches.

Use when parsing, extracting, or converting XML data from NCBI Entrez or other bioinformatics sources into tab-delimited tables. Use for selecting specific elements, filtering records, and restructuring hierarchical XML into flat formats for downstream analysis.

Use when converting compatible BLAST annotation XML/ASN streams into a compact gene-markup-style table for downstream EDirect interval helpers.

Use when searching NCBI Entrez databases (pubmed, gene, protein, nuccore, snp, geoprofiles) with query strings and field qualifiers to retrieve record UIDs for downstream processing.

Use when working with GenBank format files and need to create reference indexers for sequence data retrieval or processing within the Entrez Direct toolkit.

Use when converting BLASTN mRNA alignment XML into segmented interval reports and strand-overlap summaries in EDirect pipelines.

Use when you need to inspect and summarize statistics for HMM (profile hidden Markov model) files from the HMMER suite.

Use when you need to apply aggregation functions (sum, mean, count, etc.) to values from overlapping intervals in one file and map them onto intervals from another file.

Use when evaluating the free energy (kcal/mol) of an RNA secondary structure, calculating co-folding energies for two RNA strands, or analyzing consensus structures from multiple sequence alignments.

Use when visualizing RNA secondary structures from dot-bracket notation or Stockholm alignments, generating structure diagrams, or creating annotated consensus structure plots.

Use when aligning long FASTQ reads to a reference genome with Subread's long-read aligner, optionally in RNA-seq mode.

Use when filtering a UID stream against a local postings index with a query expression in the `x*` local-archive toolchain.

Use when performing genome arithmetic on interval files (BED, BAM, BEDGRAPH), including intersection, merging, coverage, format conversion, or sequence extraction.

Use when collecting sorted UID lists from EDirect query sources such as PubMed queries, explicit IDs, WebEnv history state, or input files.

Write efficient C code with proper memory management, pointer

Gated PRD generation — interrogates problem, user, and metric before drafting; refuses to draft on unknowns. Usage: /prd <feature-or-problem>

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.