agent-reasoning
Skill0 starsChanged 51 days agoNo licenceView on GitHub
Guia de referência para escolher estratégias de raciocínio em agentes de IA. 16 estratégias em 4 famílias, com benchmarks e casos de uso. ATIVAR quando: construir ou otimizar agente, escolher estratégia de prompting. SUGERIR PROATIVAMENTE quando o utilizador estiver a treinar ou depurar um agente.
In this repository153 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-prompt-builderSkill
- aiactSkill
- ai-adoption-strategySkill
- ai-agent-patternsSkill
- ai-na-formacaoSkill
- ai-video-creatorSkill
- algorithmic-artSkill
- apprentice-cocreateSkill
- autoplanSkill
- b2b-outbound-automationSkill
- benchmark-modelsSkill
- benchmarkSkill
- brand-guidelinesSkill
- brandkitSkill
- browser-agentsSkill
- browseSkill
- industrial-brutalist-uiSkill
- canarySkill
- canvas-designSkill
- carefulSkill
- claude-apiSkill
- code-reviewSkill
- codexSkill
- co-intelligenceSkill
- context-engineeringSkill
- context-restoreSkill
- context-saveSkill
- csoSkill
- design-consultationSkill
- design-htmlSkill
- design-reviewSkill
- design-shotgunSkill
- devex-reviewSkill
- diagramSkill
- doc-coauthoringSkill
- document-generateSkill
- document-releaseSkill
- docxSkill
- embedded-captionsSkill
- enterprise-ai-agent-designerSkill
- essencialismoSkill
- faceless-explainerSkill
- faturixSkill
- fewer-permission-promptsSkill
- freezeSkill
- frontend-designSkill
- gem-builderSkill
- general-videoSkill
- graphic-overlaysSkill
- gstackSkill
- gstackSkill
- gstack-upgradeSkill
- guardSkill
- healthSkill
- hyperframes-animationSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-mediaSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.