4.3K skills · sorted by relevance
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
The English summary is being prepared. Showing the original description.
Implements SwiftUI Views from Figma designs using Figma MCP tools (figma:get_design_context, figma:get_screenshot, figma:get_variable_defs, figma:get_metadata). Splits large designs into appropriately-sized components, respects existing codebase conventions, and adds previews for each component. Use when implementing SwiftUI from Figma design URLs (e.g., figma.com/design/...), converting designs to code, or building iOS UI from Figma mockups. Do NOT call Figma MCP tools directly without reading this skill first.
The English summary is being prepared. Showing the original description.
Create custom steering documents for specialized project contexts
The English summary is being prepared. Showing the original description.
OpenViking long-term memory plugin guide. Once installed, the plugin automatically remembers important facts from conversations and recalls relevant context before responding.
The English summary is being prepared. Showing the original description.
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
The English summary is being prepared. Showing the original description.
Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
The English summary is being prepared. Showing the original description.
Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.
The English summary is being prepared. Showing the original description.
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
The English summary is being prepared. Showing the original description.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
The English summary is being prepared. Showing the original description.
Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.
The English summary is being prepared. Showing the original description.
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
The English summary is being prepared. Showing the original description.
Core context and guardrails for Openrind Desktop native app
The English summary is being prepared. Showing the original description.
Initialize or inspect project-local PWDEV QA context without overwriting existing state or installing tools.
The English summary is being prepared. Showing the original description.
Recommend context-appropriate QA tools while preserving observed availability, constraints, and safer alternatives.
The English summary is being prepared. Showing the original description.
Extrai o brand kit do Figma — tokens de cor, tipografia, grid, logo e componentes — e grava na seção 3 do contexto. Use quando o usuário disser "extrair a marca", "pegar os tokens", "quais as cores", "design system", "importar do Figma", "montar brand kit", ou quando a seção 3 estiver vazia. Lê do Figma; não inventa paleta.
The English summary is being prepared. Showing the original description.
Design bounded performance profiles with explicit load authorization, contextual samples, percentiles, and agreed thresholds.
The English summary is being prepared. Showing the original description.
Discover and approve feature requirements through focused interviewing and repository research. Use when the user has a feature idea, unclear scope, conflicting requirements, or needs Flow context artifacts before design.
The English summary is being prepared. Showing the original description.
Use when the user asks for the state of pwdev-feat plans — 'status do feat', 'quais planos estão pendentes', 'show feature status' — listing pending, complete, with-caveats, failed and resumable plans plus codebase-context health. Read-only. Do NOT use to execute (feat-exec) or query the audit trail (feat-audit).
The English summary is being prepared. Showing the original description.
Use when an existing skill must be refactored to cut context and ambiguity without losing behavior, safety or fallbacks — 'refatorar a skill', 'reduzir esta SKILL.md', 'revisar skill com métricas' — with before/after metrics, preserved invariants and three review rounds.
The English summary is being prepared. Showing the original description.
Copy para setor público e saúde — linguagem cidadã, acessibilidade, LGPD e comunicação de política pública. Use quando o contexto for prefeitura, secretaria, SUS, assistência social, transparência ou governo digital, ou quando o usuário citar DashSaúde, Integra Arapiraca, ODARA, e-SUS ou APS.
The English summary is being prepared. Showing the original description.
Pesquisa de Voz do Cliente (VOC) antes de escrever qualquer copy — coleta a linguagem literal do público em avaliações, fóruns, redes sociais, tickets de suporte e transcrições de vendas. Use quando o usuário disser "pesquisa de público", "voz do cliente", "VOC", "o que os clientes falam", "pesquisar concorrente", "analisar reviews", "levantar objeções", "não sei o que escrever", ou quando pedir copy sem que exista seção 6 preenchida em .claude/pwdev-copy-context.md. Produz frases verbatim, não paráfrases.
The English summary is being prepared. Showing the original description.
Define, documenta e aplica a voz da marca — formalidade, personalidade, vocabulário preferido, palavras proibidas e tratamento do leitor. Use quando o usuário disser "voz da marca", "tom de voz", "brand voice", "guia de estilo", "padronizar o tom", "não parece nossa marca", "manual de redação", ou quando precisar auditar se um texto está aderente. Extrai a voz de amostras reais em vez de inventar adjetivos, e grava o resultado na seção 5 de .claude/pwdev-copy-context.md para todas as demais skills consumirem.
The English summary is being prepared. Showing the original description.
Build Model Context Protocol (MCP) servers and tools that extend Claude's capabilities with custom functions, data sources, and integrations. Use when creating custom MCP servers, implementing tools for Claude, building integrations with external services, creating data source connectors, implementing custom functions, or extending Claude's capabilities with domain-specific tools.
The English summary is being prepared. Showing the original description.
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context.
The English summary is being prepared. Showing the original description.