Provisions and manages channel resources for Conversation API projects, including WhatsApp accounts/senders/templates, RCS senders, KakaoTalk senders/templates, webhooks, and bundles. Use when the user asks to onboard channels, configure provisioning webhooks, manage templates, orchestrate multi-service bundles, or automate channel setup.

Monitors email deliverability via Mailgun Optimize (InboxReady) API. Use when the user wants to test inbox placement with seed lists, monitor IP or domain blocklists, track spam traps, check email health scores, review DMARC reports, or pull Google Postmaster or Microsoft SNDS data. Also use when emails are going to spam, sender reputation is dropping, inbox rate is declining, a domain needs warmup monitoring, an IP needs blocklist removal, or the user wants to set up email deliverability monitoring.

Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops — diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

Add OpenTelemetry observability (traces, logs, metrics) to a Python app with Liteverge. Use when the user asks to add observability, tracing, logging, or metrics to a FastAPI, Django, Flask, or similar Python backend — or to add custom spans, logs, and instrumentation to an already-instrumented app.

Add OpenTelemetry observability (traces, logs, metrics) to a Node.js/TypeScript app with Liteverge. Use when the user asks to add observability, tracing, logging, or metrics to an Express, Fastify, or similar Node.js backend — or to add custom spans, logs, and instrumentation to an already-instrumented app.

Add OpenTelemetry tracing to a browser/frontend app with Liteverge. Use when the user asks to add observability, tracing, or OpenTelemetry to a React, Next.js, Vue, Angular, or similar frontend app — or to add custom spans and instrumentation to an already-instrumented app.

Add OpenTelemetry observability (traces, metrics) to an AWS Lambda function with Liteverge. Use when the user asks to add tracing, observability, or metrics to a Lambda function — or to add custom spans and metrics to an already-instrumented Lambda. Logs are not included; use CloudWatch for logging.

Generate structured PR descriptions from diffs, add review checklists, risk assessments, and test coverage summaries. Use when the user says "write a PR description", "improve this PR", "summarize my changes", "PR review", "pull request", or asks to document a diff for reviewers.

List, find, and show Azure resources across subscriptions or resource groups. Handles prompts like "list the websites in my subscription", "list my web apps", "show my app services", "list virtual machines", "list my VMs", "show storage accounts", "find container apps", and "what resources do I have". USE FOR: list websites, list web apps, list app services, show websites in subscription, resource inventory, find resources by tag, tag analysis, orphaned resource discovery (not for cost analysis), unattached disks, count resources by type, cross-subscription lookup, and Azure Resource Graph queries. DO NOT USE FOR: deploying/changing resources (use azure-deploy), cost optimization (use azure-cost), or non-Azure clouds.

Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve agent instructions, optimize system prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Identify Azure cost savings from usage and spending data. USE FOR: optimize Azure costs, reduce Azure spending/expenses, analyze Azure costs, find cost savings, generate cost optimization report, identify orphaned resources to delete, rightsize VMs, reduce waste, optimize Redis costs, optimize storage costs, AKS cost analysis add-on, namespace cost, cost spike, anomaly, budget alert, AKS cost visibility. DO NOT USE FOR: deploying resources (use azure-deploy), general Azure diagnostics (use azure-diagnostics), security issues (use azure-security)

Extracts duplicated properties, methods, and logic from sibling Blazor components into a shared intermediate base class. Covers identification of duplicated surfaces, base class creation, member migration, and @inherits directive updates. Use when three or more components share copy-pasted Parameter declarations, consolidating shared helper methods, or refactoring component inheritance hierarchies.

Implements Hotwire patterns with Turbo Frames, Turbo Streams, and Stimulus controllers. Use when building interactive UIs, real-time updates, form handling, partial page updates, or when user mentions Turbo, Stimulus, or Hotwire.

Generates abstract invariants using domain abstraction — intervals, octagons, polyhedra, sign domains — to find invariants that concrete reasoning misses. Use when standard invariant inference fails, when the invariant involves relationships between multiple variables, or when verifying numerical code.

Extracts language-agnostic pseudocode from real code, stripping syntax noise and language-specific machinery while preserving the algorithmic structure. Use when documenting an algorithm for a paper or spec, when porting and wanting a neutral intermediate, or when explaining code to someone who doesn't know the source language.

Recommends the specific code change to remediate a detected vulnerability by dispatching on CWE to the matching Project CodeGuard rule's prescribed fix pattern. Use after a finding has been confirmed and located, when the user asks how to fix a vulnerability, or when generating remediation PRs.

Generates code comments that explain non-obvious intent, constraints, and tradeoffs — not what the code already says. Use when code is correct but opaque, when documenting for future maintainers, or when a function's why is harder to see than its what.

Sets up taint tracking by defining sources, sinks, and sanitizers from Project CodeGuard's input-validation taxonomy, then configures the target tool (CodeQL, Semgrep, custom instrumentation). Use when wiring taint analysis into CI, when the user asks for taint tracking, or when you need a source/sink catalog for a specific language.

Generates code test-first — writes a failing test from a requirement, then generates the minimal code to pass it, then refactors, in strict red-green-refactor cycles. Use when building new features where the spec is clear, when the design is uncertain and you want tests to drive it, or when you need high confidence in coverage from the start.

Generates metamorphic tests — tests that check relationships between multiple runs instead of checking exact outputs, useful when the correct output is unknown or expensive to compute. Use when there's no oracle, when testing ML/numerical/search code, or when the spec describes properties rather than values.