Loading...
Loading...
Found 1,313 Skills
Install and wire markstream-vue, markstream-react, markstream-vue2, or markstream-angular into an existing repository. Use when Codex needs to choose the right package, install the smallest peer-dependency set, fix CSS/reset order, decide between `content` and `nodes`, or add a minimal working renderer example.
DocuSeal development reference. Embed signing forms and template builder into web and mobile apps (JS/React/Vue/Angular, WebView, JWT, CSS theming). REST API with all endpoints, request/response schemas, code examples (cURL, CLI, Node.js, TypeScript, Python, Ruby, PHP, Go, C#, Java), and webhooks. Use when the user wants to integrate DocuSeal document signing or template management into their application.
Generate a comprehensive, structured learning guide for any technical topic or technology. Use this skill whenever a user wants to learn a new technology, programming language, framework, tool, or concept — even if they phrase it casually (e.g., "teach me Rust", "how do I get started with Kubernetes", "I want to learn React", "help me understand GraphQL", "give me a roadmap for learning Docker"). This skill covers concept identification and categorization, weekly study schedules, local dev setup, concept explanations with examples, exercises, popular libraries, project ideas, and resources. Trigger for any "how do I learn X", "roadmap for X", "getting started with X", "study plan for X", or "teach me X" request — even if they don't explicitly ask for a guide or roadmap.
Search and query the Grounded Docs MCP Server documentation index. Covers listing indexed libraries, searching documentation content, and resolving library versions. Use when you need to look up API references, find code examples, or check which documentation is available in the local index.
Audit automatique de conformité aux règles métier du domaine Hexagone (docs/domain/). Analyse le code d'un écran et les API appelées, matche contre les invariants, transitions et validations documentés, et produit un rapport structuré avec citations. Mode report-only — aucune modification automatique sur des règles métier en contexte santé.
Analyzes one or more sample articles to extract a writing style profile, then rewrites any target article in that exact style. Trigger when the user says: "Analyze the writing style of this article", "Rewrite in this style", "Clone someone's writing style", "Rewrite in XX's style", "style clone", "rewrite in this style", or pastes articles requesting style analysis/imitation.
Every Google Search Console feature you'd reach for, plus an offline SQLite cache that powers period compare, quick... Trigger phrases: `search console performance for example.com`, `quick wins for sc-domain:example.com`, `cannibalization audit on this site`, `compare last 28 days to prior period in GSC`, `why did traffic drop on this property`, `which pages are decaying`, `use google-search-console`, `run gsc`.
Mod development for Space Engineers version 1. Search mod code for examples and patterns.
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like "build a model", "package a model", "create a Cog model", "wrap a model", "containerize an AI model", "predict.py", "cog.yaml", "BasePredictor", or "Cog container", and when referencing cog.run, github.com/replicate/cog, or github.com/replicate/cog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.
Modo de explicação em camadas. Aplica SOMENTE na resposta imediatamente após a invocação — depois volta ao normal automaticamente. A resposta deve ser em manchete (1 frase, no máximo 2), no nível exato da granularidade da pergunta. Não listar itens individuais quando a pergunta foi sobre o conjunto. Não oferecer drill-down nem perguntar se quer detalhar — esperar o usuário pedir. Use SOMENTE quando o usuário invocar explicitamente com "/peel-talk", "peel-talk", "explica no peel-talk", "peel talk", "modo peel", ou variações. NÃO invocar automaticamente em outras tarefas.
Corrige e analisa escrita acadêmica em PDFs ou documentos de TCCs, dissertações, teses e artigos científicos com rigor de banca examinadora. Use esta skill SEMPRE que o usuário pedir para revisar, corrigir, analisar ou comentar um trabalho acadêmico, TCC, artigo, dissertação, monografia, relatório científico ou qualquer documento de escrita acadêmica. Também acione quando o usuário mencionar: "revisar meu TCC", "corrigir artigo", "feedback acadêmico", "análise do meu trabalho", "comentar PDF", "revisar escrita", "normas ABNT", ou pedir avaliação de estrutura, coerência, referências, metodologia ou linguagem formal. Realiza verificação ativa das fontes citadas via busca na web, detecta afirmações sem suporte bibliográfico, identifica inconsistências metodológicas e gera um PDF anotado com comentários técnicos detalhados e um relatório com nível de rigor de parecerista de periódico científico.
Design, test, and optimize prompts for LLM interactions. Cover prompt patterns (few-shot, chain-of-thought, ReAct), system prompt design, output formatting, prompt evaluation, and prompt optimization techniques. Triggers on "write prompt", "optimize prompt", "design system prompt", "few-shot examples", "chain of thought", "prompt evaluation", "LLM output formatting", "prompt testing", or "prompt patterns".