Explorar skills

新项目"对话式迭代设计"工作流初始化。按复杂度三档（轻量/中等/复杂）建立协作脚手架——CLAUDE.md 协作契约、DesignNotes/ 讨论记录、可选 MkDocs 站点、可选参考项目管理与架构约束体系。触发词："初始化项目"、"新项目"、"project kickoff"、"project design kickoff"、"开始新项目"、"项目初始化"、"design kickoff"。

Oracle APEX 24.2 foca no desenvolvimento e em um dicionário de metadados, ativável em Dynamic Actions, Interactive Report, Interactive Grid, Classic Report, Page Process, AJAX Callback, Validations, Authorization Schemes, paginação, LOV, APEX_APPLICATION_*, APEX_APPLICATION_PAGE_*, APEX_WORKSPACE_*, APEX_APPL_*, Workflows, Tasks, configurações de IA, ACL, JSON Sources e APEX_ACTIVITY_LOG.

Previews the MorningStar task plan for a PRD without writing any code or making commits. Fetches the Notion PRD, analyzes the current codebase, and prints the proposed task list with files, acceptance criteria, and an estimated cost. Use when the user says any of "preview", "dry run", "what would this build", "show me the plan", "estimate cost", "morningstar dry-run", or wants to validate a PRD be

Camada de compatibilidade para a skill de delegação assíncrona legada do Qwen, da claude-ccb-skills. Utilize apenas quando o usuário delegar explicitamente ao Qwen.

Verify real brand mentions in AI engine answers. Runs a curated set of category intent queries against ChatGPT, Claude, Perplexity, and Google AI Overviews (or their WebSearch proxies) and reports whether the brand appears in answers, whether the description is correct, and whether the sentiment is positive/neutral/negative. This is the only Pillar 5 ground truth — everything else is signal proxyi

Docs-aware grilling: interrogates the user's plan one question at a time AND maintains the domain glossary (CONTEXT.md) and architecture decision records (docs/adr/) inline as decisions crystallise. Used to stress-test a plan against the project's language and documented decisions; for a plain interview that writes no files, use grill. Activates when the user writes "grill-docs", "grill with docs"

Use ao auditar habilidades e comandos do Claude para garantir a qualidade. Suporta os modos Quick Scan (apenas habilidades alteradas) e Full Stocktake com avaliação sequencial em lote por subagente.

Token de sessão da awp-wallet; apenas a awp-wallet legada (<v0.17) precisa disso.

AI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creativ

Use when the user describes work to be tracked and the work kind isn't obvious. Infers whether it's a task, story, bug, spec, epic, or incident from the language used, then routes to the right entry point (`/ticket`, `/spec`, or direct boardmaster call) with the correct `kind` pre-set.

Motor de simulação multiagente de IA para previsão de cenários e ensaio de decisões. Simula dinâmicas sociais com personas de incentivos e vieses distintos, ideal para analisar resultados de campanhas, impactos de políticas e cenários de crise.

Use when reviewing source files, diffs, commits, pull requests, or bugfixes for correctness issues, regressions, security problems, performance risks, edge cases, or missing tests across any language or framework.