Lightdash Development
claudecodexLightdash Development plugin for semantic layer modeling (dbt YAML, metrics, dimensions).
11 skills · 3 agents · 1 MCP server · hooks
Lightdash AgentOps plugin for building, managing, and autonomously tuning AI agents.
Plugin lightdash-agentops from marketplace dbt-heros in yu-iskw/dbt-heroes. Commands read from the repo's manifest — 18 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
debug-agent-threadsInspection of thread history, memory, and organization-wide agent activity.
manage-lightdash-agentsCRUD operations for Lightdash project agents.
run-lightdash-evalsOrchestrate evaluation runs and test case management for Lightdash agents.
agent-tunerAutonomous sub-agent for optimizing Lightdash AI agent performance through evaluation-driven tuning loops.
lightdash-toolsruns: npx -y @lightdash-tools/mcp
${CLAUDE_PLUGIN_ROOT}/hooks/safety.sh
${CLAUDE_PLUGIN_ROOT}/hooks/safety.sh
Lightdash Development plugin for semantic layer modeling (dbt YAML, metrics, dimensions).
11 skills · 3 agents · 1 MCP server · hooks
Lightdash Content Administration plugin for managing spaces, charts, and dashboards within a project.
8 skills · 1 agent · 1 MCP server · hooks
Lightdash Organization Administration plugin for managing users, groups, and organization settings.
6 skills · 1 agent · 1 MCP server · hooks
Lightdash Analysis plugin for data exploration and insight generation.
3 skills · 2 agents · 1 MCP server · hooks
Full product lifecycle plugin for Claude Code, Codex CLI, and OpenCode: define Vision/Mission/Core → generate workplan → execute with mandatory cross-provider reviewer agents → synthesize deliverables → maintain, with parallel task execution, crash recovery, and AgentOps metrics.
Operate AI agents and LLM features in production: prompt regression suites, model migration plans, context-engineering reviews, agent incident postmortems, and observability specs — plus the pm-ai evaluation and cost skills they build on.
8 skills
Agent 设计顾问与审查工具。基于 12-Factor AgentOps 最佳实践,用于探讨 Agent 架构设计方案,或审查现有 Agent/Skill/工作流的设计,发现问题并给出改进建议。触发词:审查我的 agent、帮我分析这个 skill、agent 设计、agent 优化、帮我 review 这个工作流。
42 skills
Copilot agent skills for running standardized evaluation workflows with AgentOps Toolkit and Microsoft Foundry agents.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.