Build and debug code-first Azure AI Search indexing for Foundry agents: load local files, chunk text, generate embeddings through the Foundry project endpoint, create vector and semantic indexes, upload idempotently, and inspect the live service. Use for RAG ingestion, reindexing, schema mismatches, empty indexes, and…
Inner development loop: mandatory logging setup, startup preflight, text-only DevUI run/debug from entities/, trace correlation, and diagnosing a silent agent. Load for DevUI, logging, telemetry, or when an agent produces no answer. NOT for local microphone/speaker VoiceLive loops - load voicelive-realtime instead.
Building the local MAF reasoning agent against a Microsoft Foundry project endpoint: agent factories, function tools, skills, sessions, middleware, and Azure AI Search retrieval. Load for work under src/agents, src/tools, or src/retrieval. NOT for chunking, embedding, populating, or inspecting a Search index - load…
Splitting one agent into several and orchestrating them: declarative kind: Workflow documents that reference agent files, code-first orchestration builders, executors, and choosing between agent-as-tool, sequential, concurrent, handoff, group chat, magentic, and a graph WorkflowBuilder. Load when a second agent…
Repo layout, fixed MAF-bridge topology, two-resource default with optional alternate VoiceLive overrides, and conformance checklist. Load when scaffolding, placing code/config, or reviewing this Foundry + Azure AI Search voice seed before it ships.
Create, edit, validate, and preview Mermaid diagrams using the Mermaid Chart VS Code extension. Covers the validate-then-preview workflow, the LM tools (mermaid-diagram-validator, mermaid-diagram-preview, get-syntax-docs-mermaid), the mermaidChart. commands, @mermaid-chart slash commands, and the Mermaid Chart cloud…
Audit a skill pack for duplication, routing drift, description collisions, broken references, and always-on context cost. Produces a findings report and a prioritised fix list. Load when adding a skill to an existing pack, when the agent loads the wrong skill or two overlapping ones, when a fact has been restated in…
Azure AI VoiceLive SDK (1.2.0, async-only): a guided interview that confirms managed-model vs Foundry-hosted BYOM before writing config, the managed model catalogue, local microphone/speaker prototypes, connect(), RequestSession, turn detection, barge-in, audio formats, voices, interim responses, and tools. Load for…
★not rated 2 1mo agoA101 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: