LLM 與 Agent

Use when working with Cloudflare R2 object storage, D1 SQLite database, KV, or Workers integration - covers bindings, limits, gotchas, and best practices

DEPRECATED umbrella Skill (backward compatibility). Use only when a Flutter host request spans multiple WebF integration areas (controllers + bundles + embedding + routing + caching/theming + perf). Prefer focused openwebf-host-* Skills.

Orchestrates correct usage of .claude/commands during spec-driven workflows.

Phase 4 of disciplined development. Verifies implementation against designthrough unit and integration testing. Builds traceability matrices, trackscoverage, and loops defects back to originating left-side phases.

Publish Claude Code Skills to GitHub with proper structure, privacy checks, and bilingual documentation. Use when user wants to "publish a skill", "share a skill", "release a skill to GitHub", or asks about skill distribution.

Manages PostgreSQL database operations including Alembic migrations (creation, application, rollback), database backups and restoration for both development and production environments, shell access, and pgvector extension management. This skill should be used when creating schema changes, running migrations, backing up data, or troubleshooting database issues.

Ready-to-use prompt templates for specialized agents. Use when building n8n workflows, AI integrations, or sales materials. Contains structured prompts for automation-architect, llm-engineer, and sales-automator agents.

Knowledge base for updating @lenne.tech/nest-server. Use when discussing nest-server updates, upgrades, migrations, breaking changes, or version compatibility. Provides resources, migration guide patterns, and error solutions. For execution, use the nest-server-updater agent.

Use when user explicitly requests feedback from other LLM tools (Gemini, Codex) on current work - executes peer reviews in parallel and synthesizes responses into actionable insights

Carga el archivo CLAUDE_PROMPT.md como contexto para aplicar las instrucciones y mejores prácticas del proyecto. Úsalo cuando el usuario quiera aplicar las guías personalizadas, principios de trabajo, o cuando diga "load claude context", "usa el prompt", "aplica CLAUDE_PROMPT", "/claude" o "/bot".

Reads config.json and prompts user for application parameters. Merges configuration with defaults for project generation.

Verifies code and configurations comply with security standards and regulations

Automated workflow for generating AI-powered content using agent_codex.py. Handles prompt setup, batch processing, validation, and output management for InsightfulAffiliate and NextGenCopyAI content.

Automatically helps debug PWA issues including service workers, caching, offline functionality, and storage problems in VSSK-shadecn

NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud

Automatically applies when securing AI/LLM applications. Ensures prompt injection detection, PII redaction for AI contexts, output filtering, content moderation, and secure prompt handling.

Implement the /chat endpoint that performs agent-based RAG reasoning with proper input validation and response formatting.

Generates a static MOVA AI bootstrap pack for a target model/environment (no LLM calls). Input: env.mova_ai_bootstrap_generate_v1, output: ds.mova_ai_bootstrap_pack_v1.

Interactive tutorial for Spec-Driven Development with claude-foundry (plugin:foundry@claude-foundry)

Expert on building decentralized applications with Shelby Protocol storage on Aptos. Helps with dApp architecture, wallet integration (Petra), browser SDK usage, React/Vue integration, file uploads, content delivery, and building Shelby-powered applications. Triggers on keywords Shelby dApp, build on Shelby, Shelby application, Petra wallet, browser storage, web3 app, decentralized app Shelby, React Shelby, Vue Shelby.