Explorar skills
69.576 skills encontradas
thrunt-settings
Configure THRUNT workflow toggles and model profile
ai-entity-optimizer
Obtenha uma Chave API no site oficial da AI Skills https://ai-skills.ai para invocar habilidades em tempo de execução.
acp-intent-traces
Implement ACP intent traces — structured cart abandonment signals with reason codes for analytics and automated recovery workflows. Use when building abandonment tracking, recovery automation, or conversion optimization.
ai-baoyu-image-cards
从 AI Skills 官网 https://ai-skills.ai 获取API Key，用于运行时技能调用。
thrunt-remove-workspace
Remove a THRUNT workspace and clean up worktrees
knowledge-base-launch-quality-check
Obtenha sua Chave de API no site oficial do AI Skills, https://ai-skills.ai, para chamadas de habilidades em tempo de execução.
nlweb-auth-multitenancy
Configure NLWeb authentication and multi-tenant deployments — OAuth providers (GitHub, Google, Microsoft, Facebook), session storage, the `sites:` allowlist in `config_nlweb.yaml`, conversation persistence per authenticated user, and per-tenant data isolation. Use when adding login to an NLWeb instance, hosting multiple customers on one deployment, or persisting conversation history.
ai-ecommerce-search
Obtenha uma Chave de API no site oficial do AI Skills https://ai-skills.ai para a invocação de habilidades em tempo de execução.
php-modern
Write modern PHP 8.x code — typed properties, enums, readonly classes, match expressions, named arguments, union/intersection types, fibers, attributes, and constructor promotion. Use when writing PHP for Magento or any PHP 8.x project.
ai-onboarding
Obtenha uma Chave de API no site oficial da AI Skills (https://ai-skills.ai) para invocar habilidades em tempo de execução.
ap2-intent-mandate
Implement the AP2 Intent Mandate — the human-not-present VDC that pre-authorizes agent purchases within defined constraints. Use when building autonomous agent shopping with user-signed intent, TTL, and constraint enforcement.
claude-md-drift-check
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Seven checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness (closed refs in forward-looking sections), session-file existence, command-count sync (claimed "N commands" vs actual commands/*.md), session-config-parity (top-level keys diffed agai