Explorar skills

Plan-vs-implementation deep audit using Agent Teams. Parses a plan file (or inline description), extracts requirements, and summons 4 Inspector Ashes to measure implementation completeness, quality across 11 dimensions, and gaps across 9 categories. Produces a VERDICT.md with requirement matrix, dimension scores, gap analysis, and actionable recommendations. Also use `--verify-tome <tome-path>` to

Gera automaticamente um changelog a partir de commits do Git, dados de sprint e documentos de design. Produz versões internas e voltadas para o jogador.

Explore as arquiteturas de sistema de estado e comportamento do Unity, incluindo FSM, FSM Hierárquico, Árvores de Comportamento e máquinas de estado baseadas em pilha. Isso abrange decisões de Animator-vs-código e testes de máquina de estado, com base no Unity 6.3 LTS.

Finds companies matching the ICP that are showing buying signals right now, then finds contacts at the best ones. Builds a scored prospect list for outreach. Triggers: /prospect, "find companies", "build a list", "find prospects". Reads: ./gtm/icp.md, ./gtm/signals.md, ./gtm/company.md. Writes: ./gtm/prospects.md. Standalone: yes.

Measure and improve how well your AI works. Use when AI gives wrong answers, accuracy is bad, responses are unreliable, you need to test AI quality, evaluate your AI, write metrics, benchmark performance, optimize prompts, improve results, or systematically make your AI better. Also used for spent hours tweaking prompts, trial and error prompt engineering is not working, quality plateaued early, s

Use when planning sprints, tracking delivery milestones, managing dependencies, identifying risks, writing status reports, running retrospectives, or coordinating cross-functional execution of a defined scope. Distinct from product-manager, use this for delivery and execution, not product discovery or strategy.

Use when you have already tried prompt-only optimization and want the next level — jointly tuning prompts and model weights for maximum quality. Common scenarios - you have maxed out prompt optimization and need the next level, combining instruction tuning with weight tuning for maximum quality, making a small model match a large model through joint optimization, or squeezing the last few percent

Gera documentos de design ou arquitetura a partir de implementações existentes. Trabalha de forma inversa a partir de código e protótipos para criar a documentação de planejamento ausente.

前端工程师角色技能。当需要根据产品需求、UI设计方案和架构约束实现具体前端功能时使用。关键词：前端开发、组件实现、状态管理、Vue 3、React、TypeScript、SCSS、页面布局、交互实现、API集成、路由、性能优化、代码规范、工程质量。

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Deepen an existing plan with Forge Gaze topic-aware enrichment. Summons specialized Ashes to enrich each section with expert perspectives. Can target a specific plan or auto-detect the most recent one.

Padrões de máquina de estados baseados em interface para estados de jogo Unity, controladores de personagem e fluxos de UI. Use ao implementar fluxo de jogo (menu -> jogabilidade -> fim de jogo), estados de personagem (ocioso -> correr -> pular -> cair), estados de comportamento de IA ou transições de tela de UI.