context-aware-vision-grounded-kb-agent

Structured first-pass debugging for test failures, runtime errors, and unexpected behavior. USE FOR: test failure, assertion error, ImportError, traceback, debug failing test, fix broken test, diagnose error, runtime exception, mock error, config error. DO NOT USE FOR: complex multi-system design issues (escalate to @planner for re-planning).

Create, update, refactor, explain, or review Microsoft Agent Framework solutions. Use when working with the KB Agent (src/agent/) or any Microsoft Agent Framework code.

Patterns for adding governance, safety, and trust controls to AI agent systems using Microsoft Foundry and Azure API Management (APIM) AI Gateway. Use when: - Adding rate limiting, content safety, or jailbreak detection to agent traffic - Configuring APIM policies for token limits, throttling, or semantic caching - Leveraging Foundry tracing, evaluations, and agent monitoring - Implementing department-scoped access via JWT claims - Deciding what to handle at the platform layer vs. thin application code

Validates service boundary compliance in the KB Agent project. Use when working on cross-service imports, restructuring modules, or reviewing code that crosses service boundaries.

Performs comprehensive preflight validation of Bicep deployments to Azure. Use when: - Before deploying infrastructure to Azure - Reviewing or preparing Bicep files - Previewing what changes a deployment will make (what-if) - Verifying permissions are sufficient for deployment - Before running `azd -C infra/azure up`, `azd -C infra/azure provision`, or `az deployment` commands

Reviews Bicep modules, azure.yaml, and infrastructure changes for the KB Agent project. Checks naming, RBAC, module wiring, and doc sync. Use when working on infra/ or reviewing infrastructure PRs.

Manages epic and story lifecycle for the KB Agent project. Reads epic files, verifies acceptance criteria, updates story status, and checks Definition of Done. Use when completing stories, starting new work, or auditing epic status.

Evaluation-driven development for Python LLM applications using the Microsoft Evaluations SDK (`azure-ai-evaluation`) and Microsoft Foundry. Use when: - Setting up evals, QA, or testing for the KB Agent or any LLM-calling code - Running local evaluations with LLM-as-judge evaluators backed by Foundry models - Publishing evaluation results to Microsoft Foundry for tracking and comparison - Building golden datasets for regression testing - Investigating LLM response quality failures - Benchmarking prompt changes

Design and optimize GitHub Actions workflows with security-first practices, efficient resource usage, and reliable automation. Use when creating or reviewing CI/CD workflows, action pinning, OIDC auth, and supply-chain security.

Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%. Use when: - Measuring test coverage for a module - Finding untested code paths - Improving coverage for a specific service

Guides safe refactoring operations across the KB Agent service-based architecture. Use when restructuring code, extracting modules, or moving files across services.

Guide for configuring and managing GitHub secret scanning, push protection, custom patterns, and alert remediation. Use when: - Enabling or configuring secret scanning for a repository - Setting up push protection to block secrets before push - Defining custom secret patterns with regular expressions - Resolving a blocked push from the command line - Triaging or remediating secret scanning alerts

Security analysis for Azure-hosted Python services. Checks for managed identity, secret exposure, input validation, RBAC, and OWASP-style vulnerabilities. Use when reviewing endpoints, auth code, infra changes, or any user-input handling.

Cloud design patterns for distributed systems architecture covering 42 industry-standard patterns across reliability, performance, messaging, security, and deployment categories. Use when designing, reviewing, or implementing distributed system architectures.

Generate a map of all files relevant to a task before making changes. Use when planning multi-file modifications, cross-service changes, or any work that touches multiple modules.

Prompt and workflow for generating conventional commit messages. Use when: - Committing changes with standardized messages - Following the Conventional Commits specification - Generating commit messages from staged changes

Comprehensive Azure Cosmos DB NoSQL data modeling expert. Use when: - Designing or reviewing Cosmos DB container schemas and partition strategies - Analyzing access patterns and aggregate boundaries - Optimizing RU costs, indexing policies, or query performance - Evaluating multi-document vs single-document aggregates - Working on the project's Cosmos DB containers (agent-sessions, conversations, etc.)

Create, update, and manage GitHub issues using MCP tools. Use when: - Creating bug reports, feature requests, or task issues - Updating existing issues (labels, assignees, state) - Searching or filtering issues - Managing issue types, sub-issues, or dependencies

Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation. Use when conducting spikes documented in docs/spikes/ or docs/research/.