Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task, reviews once per phase, loads phases just-in-time to minimize context usage
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent, handles retries and timeouts, manages review-fix loop until zero issues
Xcode build system guidance for xcodebuild operations. Use when building iOS projects, running tests, analyzing build failures, or configuring schemes. Covers build/clean/test operations, interpreting xcodebuild output, and troubleshooting common build errors.
Deploy containerized applications to AWS ECS/Fargate. Use when deploying containers to AWS, managing ECS services, or setting up Fargate tasks. Covers task definitions and ECR.
Creating components (inline/docker). Dynamic ports, retry policies, PTY patterns, IsolatedContainerVolume.
Use when beginning implementation from a design plan - orchestrates branch creation, detailed planning, and hands off to execution with all necessary context
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Implement observability solutions. Use when setting up monitoring, logging, or tracing. Covers OpenTelemetry, metrics, and alerting.
Initialize epic directory, brief, and tracker entry. Use to begin a new epic.
Use this skill when performing any Docker-related tasks including building images, running containers, managing containers, viewing logs, and working with Docker Compose
Creates a git worktree for parallel feature development. Use after planning to prepare an isolated development environment with all necessary environment files.
Create a PR and automatically cleanup the worktree. Keeps local and remote branches intact.
Compare Bicep templates against a live Azure environment by querying Azure directly and parsing the Bicep template. Presents categorized change results (Create, Modify, Delete, No Change) without deploying anything. Does NOT use ARM what-if.
Generate deployment-ready Bicep templates and PowerShell scripts from an approved Draw.io Azure architecture diagram. Parses the diagram, generates a user-editable .bicepparam file with descriptive comments, validates against Azure constraints, and outputs modular Bicep with deployment scripts.
Check a Bicep template against the Azure Policy assignments in the target Azure environment to determine whether the resources would be compliant before deployment. Uses the checkPolicyRestrictions REST API for fast server-side evaluation, with a legacy CLI fallback. Produces a per-resource compliance report with remediation guidance.
Reverse-engineer a live Azure scope (resource group or filtered subscription) into deployment-ready Bicep templates. Discovers resources via Azure MCP, extracts full configurations, generates modular Bicep with parameter files, and documents out-of-scope dependencies that require separate changes.
Build or update the lance-context MCP server and Claude Code example that uses lance-context as a memory/knowledge store.
Guidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity.
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.
