Showing 5101–5130 of 10205 skills
Cria prompts JSON estruturados para geração de imagens de alta qualidade com estética luxuosa e cinematográfica. Use esta skill sempre que o usuário quiser gerar um prompt de imagem, criar uma foto de produto, montar um prompt para IA de imagem, fotografar produto virtualmente, criar imagem de comida, bebida, cosmético, joia, moda ou qualquer item visual. Também deve ser ativada quando o usuário mencionar: "prompt para imagem", "gerar imagem de produto", "foto de produto com IA", "prompt para Midjourney/DALL-E/Flux", "fotografar produto", ou pedir para "montar um prompt JSON de imagem".
stribus/pygerengastos
Agente Researcher do time Code New Project Agents. A partir de `ideation.md`, aprofunda o público-alvo em 1 a 3 personas estruturadas com jornadas. Use quando o usuário digitar "/reversa-researcher", "reversa-researcher" ou quando invocado pelo orquestrador `/reversa-new`. Produz `_reversa_sdd/personas.md`.
stribus/pygerengastos
Cria selos visuais generativos seeded usando p5.js, gerando HTML standalone com canvas de arte algorítmica reprodutível. Use esta skill sempre que o usuário pedir um selo, identidade visual de projeto, hero generativo, capa única reprodutível, ou artwork derivado de um hash. Deve ser ativada quando o usuário mencionar termos como "selo", "selo generativo", "identidade visual do projeto", "hero capa", "artwork seeded", "Art Blocks style", "p5.js generativo", "capa reprodutível", "selo de documentação" ou pedir um elemento decorativo único e reprodutível derivado de uma string. Funciona com qualquer string como seed (hash do soul.md, nome do projeto, ID arbitrário). Sempre gera HTML standalone com p5.js via CDN.
stribus/pygerengastos
Exchange messages with live Claude Code sessions through a local Unix socket relay tied to the current Codex thread. Use for explicit cross-session coordination, not general Claude product questions.
stokaro/codex-claude-peer
CLI best practices for LlamaFarm. Covers Cobra, Bubbletea, Lipgloss patterns for Go CLI development.
llama-farm/llamafarm
Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.
llama-farm/llamafarm
Configuration module patterns for LlamaFarm. Covers Pydantic v2 models, JSONSchema generation, YAML processing, and validation.
llama-farm/llamafarm
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
llama-farm/llamafarm
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
llama-farm/llamafarm
Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".
llama-farm/llamafarm
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.
llama-farm/llamafarm
Server-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns.
llama-farm/llamafarm
Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.
llama-farm/llamafarm
Recreate a short reference video (usually an AI-generated clip) as a real, explorable Unreal Engine 5 scene, built 100% procedurally inside Unreal, then match its camera and lighting and make it playable. Adapts gokaygokay's video-to-shader method (breakdown, build, compare at matched times, repair) to a game engine, driven through Unreal's official MCP plugin. Use when asked to turn a video or clip into an Unreal level, scene or playable game slice.
mattvideoproductions/MVP-Prompts
多编排者/长期 agent 身份之间的异步信箱总线——发信、收信、回信、归档、名册注册。每个身份一个 inbox,一封信只有一个去处(收件人 inbox),收信只查自己信箱。触发:给另一个编排者/CTO/agent 写信或提议、查我的信箱、跨编排者协调、看有哪些注册身份。不用于人类电子邮件(gmail/给真人同事或客户写信)或普通消息转发。可选伴随 cto-orchestration 使用(多编排者场景)。Use when writing to / reading mail from another orchestrator agent, coordinating across orchestrators, or managing the agent roster; NOT for human email.
martin1847/evolab
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory
fabioc-aloha/Alex_Skill_Mall
Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.
fabioc-aloha/Alex_Skill_Mall
This skill should be used when the user asks to convert an academic paper in LaTeX from one format (e.g., Springer, IPOL) to another format (e.g., MDPI, IEEE, Nature). It automates extraction, injection, fixing formatting, and compiling.
fabioc-aloha/Alex_Skill_Mall
Generate and verify integrity manifests for AI agent plugins and tools -- detect tampering, enforce version pinning, and establish supply chain provenance (the SLSA/Sigstore gap for agent ecosystems).
fabioc-aloha/Alex_Skill_Mall
Patterns for agent self-improvement through iterative evaluation and refinement -- generate, evaluate, critique, refine loops that move beyond single-shot generation.
fabioc-aloha/Alex_Skill_Mall
This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration.
fabioc-aloha/Alex_Skill_Mall
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
fabioc-aloha/Alex_Skill_Mall
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
fabioc-aloha/Alex_Skill_Mall
Safely consume an MCP server someone else wrote — evaluate it before installing, register it correctly, scope its credentials, and diagnose it when it misbehaves.
fabioc-aloha/Alex_Skill_Mall
Verwenden, wenn zu einem Thema oder einer Person ein strukturiertes Recherche-Briefing als Markdown-Dossier erstellt werden soll (z. B. 'Recherche-Dossier anlegen', 'Briefing zu Thema X erstellen', 'Dossier über Person Y', /dossier-briefing). Erzeugt ein strukturiertes Briefing-Dokument mit Kernfakten, Quellenbelegen und offenen Fragen. NICHT verwenden für akute Entscheidungsverdichtung (dafür decision-shot) oder formale Forschungsprotokolle (dafür research/research-agent).
ellmos-ai/skills
Use when the user wants to send the same prompt to several LLMs and compare the answers - sequentially (stopwatch, clean per-lane timing) or in parallel (true race), with optional repetitions per model, judged by the starting model across quality, correctness, completeness, instruction fidelity and latency (time is only one dimension). Triggers on /compare-race, 'model race', 'vergleiche modelle', 'gleicher prompt an mehrere modelle'.
ellmos-ai/skills
Tiefe Pflegerunde für ein veröffentlichtes GitHub-Repository (Stufe 2): enthält den vollständigen surface-after-care-Durchlauf und ergänzt ihn um drei teure Schritte — rechtliche Ersteinschätzung über die Law-Checker mit Wiedervorlage nach einem Jahr (Gutachten bleibt gitignored im Repo), Querverweise zu verwandten Repos über ALLE Organisationen hinweg sowie das Nachziehen aller Sprachen auf App-Ebene, nicht nur in der Doku. Nutze diesen Skill bei "full after care", "deep after care", "tiefe Repo-Pflege", "große Runde", "Repo grundlegend durchgehen", wenn ein Repo länger nicht geprüft wurde, vor größeren Releases oder wenn rechtliche Relevanz, Querverweise oder Mehrsprachigkeit ausdrücklich Thema sind. Für die günstige, oft wiederholte Runde stattdessen surface-after-care; für die Erstveröffentlichung github-repo-care.
ellmos-ai/skills
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
urmzd/dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the `dotfiles` CLI; use manage-machine.
urmzd/dotfiles
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel work, or coordinating subagents across panes.
urmzd/dotfiles