qlik-agents

Designs complete data architecture including app architecture strategy, star schema, ETL pipeline with layer boundaries, QVD layer strategy, cross-layer field mapping, and source architecture consumption patterns. Invoke when the project specification is approved and source profiling is complete. Use after Phase 1 gate passes and Phase 2 source profiling is available.

Generates complete project documentation from all pipeline artifacts. Produces nine documents (README, data dictionary, technical specification, expression catalog, visualization guide, deployment runbook, user guide, change log, dependency tracker). Invoke after all Critical QA findings are resolved (Phase 7 gate passed). Ensures technical accuracy, audience calibration, and cross-document consistency.

Authors all Qlik Sense expressions including master measures, master dimensions, calculated dimensions, set analysis expressions, variable expressions, and complex aggregations. Produces expression catalog reference and runnable expression-variables.qvs file. Invoke after Phase 4 scripts complete. Resume when viz-architect reports expression gaps or execution validation reveals expression issues.

Project manager for the Qlik development pipeline. Coordinates seven specialized subagents across nine phases (platform context, requirements, source profiling, data architecture, script development, expressions, visualization, QA, documentation). Manages quality gates, execution validation, rework loops, and dependency tracking. Use this agent to run a complete Qlik Sense development project or resume an in-progress pipeline.

Reviews all Qlik development artifacts against best practices, naming conventions, script quality, expression correctness, security, and cross-artifact consistency. Performs data quality validation when available. Invoked multiple times during pipeline for lightweight (Phase 3), script (Phase 4), expression (Phase 5), and comprehensive (Phase 7) reviews. Resume to verify fixes.

Post-load data quality validation patterns for Qlik development. Provides query templates for null rate analysis, referential integrity checks, value distribution analysis, row count validation, orphaned record detection, sparse field identification, and duplicate detection. Usable by the qa-reviewer when MCP or post-load data access is available. Also provides patterns for embedding validation checks directly into load scripts. Load when performing data quality validation or writing diagnostic scripts.

Captures existing platform patterns for brownfield Qlik projects. Provides structured templates for documenting existing app inventory, shared subroutine catalogs, naming convention maps, data connection standards, QVD storage conventions, and organizational coding standards. Used by requirements-analyst during Phase 0 context ingestion and by script-developer during Phase 4 for platform compatibility. Load when ingesting platform context or writing scripts that must integrate with existing platform conventions.

Capability registry for the Qlik Cloud MCP server. Maps MCP tools to pipeline phases, provides MCP detection patterns, documents behavioral gotchas not covered by tool definitions, and defines multi-step workflows for expression validation, reference app analysis, visualization scaffolding, and data quality checks. Load whenever an agent needs to interact with a live Qlik Cloud tenant. The tool definitions themselves document parameters, response structures, and basic usage -- this skill covers framework integration, sequencing, and pitfalls discovered through live testing.

Star schema patterns, key resolution strategies, synthetic key prevention, QVD layer design, multi-app architecture patterns, source architecture consumption strategies, and associative engine behavior for Qlik Sense data modeling. Load when designing or reviewing data models.

Deployment procedures for Qlik Sense Cloud and client-managed environments. Covers app import, data connection setup, task scheduling, security configuration, environment promotion (dev/test/prod), QVD storage setup, and post-deployment validation. Invoke manually with /qlik-deploy when preparing deployment artifacts or writing operational runbooks.

1 hook across 1 event