Skills para agentes
Skills que ensinam agentes de programação a executar uma tarefa repetível, com sua origem e o que incluem.
4 recursos
A pesquisa roda no catálogo do KitLocal. Nada do que você digita aqui é enviado ao GitHub nem a outro serviço.
4 resultados
A guide for building high-quality MCP servers, in Python (FastMCP) or Node/TypeScript, so an LLM can use an external API through well-designed tools.
Selecionado + ao vivoAnthropic · Complete terms in LICENSE.txtAtualizado há 19 dias
mcpserverauthoringGuidance for making intentional visual design choices (direction, typography, polish) when building new UI or reshaping an existing one, so results do not look like templated defaults.
Selecionado + ao vivoAnthropic · Complete terms in LICENSE.txtAtualizado há 2 meses
designuifrontendGuides an agent through creating, editing and evaluating Agent Skills, including benchmarking a skill and tuning its description so it triggers reliably.
Selecionado + ao vivoAnthropicAtualizado há 7 meses
agent-skillsauthoringevalsA toolkit for testing local web applications with Playwright: verify frontend behavior, debug UI problems, capture screenshots and read browser logs.
Selecionado + ao vivoAnthropic · Complete terms in LICENSE.txtAtualizado há 7 meses
playwrighttestingbrowser
KitLocal · GitHub
Descubra skills individuais
Arquivos SKILL.md indexados de repositórios do GitHub configurados. As estrelas e as datas de atualização pertencem ao repositório, não a cada skill.
As estrelas pertencem ao repositório do GitHub, então as skills do mesmo repositório compartilham um único número.
Instantâneo: 15 de nov. de 2026, 05:54 · incluído
15 skills em 1 repositório
- 01brainstorming ↗
obra/superpowers · skills/brainstorming/SKILL.md · Observado em 15 de nov. de 2026
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
npx skills add obra/superpowers+14 de obra/superpowers
- diagnosing-superpowers ↗
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
- dispatching-parallel-agents ↗
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- executing-plans ↗
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
- finishing-a-development-branch ↗
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
- receiving-code-review ↗
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
- requesting-code-review ↗
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
- subagent-driven-development ↗
Use when executing implementation plans with independent tasks in the current session
- systematic-debugging ↗
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- test-driven-development ↗
Use when implementing any feature or bugfix, before writing implementation code
- using-git-worktrees ↗
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
- using-superpowers ↗
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
- verification-before-completion ↗
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
- writing-plans ↗
Use when you have a spec or requirements for a multi-step task, before touching code
- writing-skills ↗
Use when creating new skills, editing existing skills, or verifying skills work before deployment
★ 318 mil
- diagnosing-superpowers ↗
Repositórios de skills em alta por caso de uso
Pesquisa ao vivo no GitHub por repositórios com a tag agent-skills, ordenados por estrelas. Abre o GitHub Discover.
Agent Skills
Descubra skills para o seu agente de IA
Encontre instruções reutilizáveis para programar, pesquisar e fluxos de trabalho do dia a dia. Escolha um ranking, navegue por tarefa ou explore as skills selecionadas abaixo.
SKILLS.SH
Descubra skills populares
O Skills.sh classifica cada skill pela atividade de instalação.
Estes links abrem o ranking ao vivo no skills.sh.
SKILLSMP
Navegue por skills por caso de uso
Explore por tópico o diretório maior do SkillsMP e abra a fonte para ver os detalhes.
Revise as instruções da skill e quaisquer scripts antes de instalar. Um ranking ou listagem não é uma revisão de segurança.
GitHub · Stars
Principais repositórios de skills para agentes
Repositórios do GitHub com a tag agent-skills, ordenados por estrelas do repositório.
Sobre este catálogo
Instantâneo incluído · publicado 15 de nov. de 2026, 06:05 · Revisão do catálogo 5bc079fe355af2214bc0
Mostrando o instantâneo incluído no aplicativo (nenhuma fonte de conteúdo está configurada). Pode haver conteúdo mais recente na fonte.