AI Product Analyst — Claude Code-powered data analysis toolkit
Agent
Every agent .md file MUST begin with a CONTRACT block -- a YAML declaration inside an HTML comment that describes the agent's interface. The OR-3 DAG walker reads these contracts to build the execution graph.
Agent
Agent "INDEX" from ai-analyst-lab/ai-analyst, covering agent index, system variables (auto-resolved) and agents.
Agent
Agent "chart-maker" from ai-analyst-lab/ai-analyst, covering agent: chart maker, purpose, inputs, workflow and step 0.5: apply fix report (when {{fixreport}} is provided).
Agent
Agent "cohort-analysis" from ai-analyst-lab/ai-analyst, covering agent: cohort analysis, purpose, inputs, workflow and pre-flight checks.
Agent
Agent "comms-drafter" from ai-analyst-lab/ai-analyst, covering agent: comms drafter, purpose, inputs, workflow and step 1: read preferences.
Agent
Agent "data-explorer" from ai-analyst-lab/ai-analyst, covering agent: data explorer, purpose, inputs, workflow and step 0: check for existing schema.
Agent
Agent "deck-creator" from ai-analyst-lab/ai-analyst, covering agent: deck creator, purpose, inputs, non-negotiable defaults and theme selection (critical).
Agent
Agent "descriptive-analytics" from ai-analyst-lab/ai-analyst, covering agent: descriptive analytics, purpose, inputs, workflow and pre-flight checks.
Agent
Agent "experiment-designer" from ai-analyst-lab/ai-analyst, covering agent: experiment designer, purpose, inputs, workflow and step 1: assess feasibility.
Agent
Agent "hypothesis" from ai-analyst-lab/ai-analyst, covering agent: hypothesis forming, purpose, inputs, workflow and step 1: parse the question brief.
Agent
Agent "narrative-coherence-reviewer" from ai-analyst-lab/ai-analyst, covering agent: narrative coherence reviewer, purpose, inputs, workflow and step 1: headline coherence test.
Agent
Agent "opportunity-sizer" from ai-analyst-lab/ai-analyst, covering agent: opportunity sizer, purpose, inputs, workflow and step 1: define the impact model.
Agent
Agent "overtime-trend" from ai-analyst-lab/ai-analyst, covering agent: overtime / trend, purpose, inputs, workflow and pre-flight checks.
Agent
Track pipeline execution state for resume capability and progress reporting. Written to working/pipelinestate.json during /run-pipeline execution. Read by /resume-pipeline to determine restart point.
Agent
Human-readable summary generated after each pipeline phase completes. Written to working/pipelinesummary.md during execution, updated incrementally. Provides a quick status overview without needing to parse pipelinestate.json.
Agent
Agent "question-framing" from ai-analyst-lab/ai-analyst, covering agent: question framing, purpose, inputs, workflow and step 1: parse and summarize business context.
Agent
Agent "root-cause-investigator" from ai-analyst-lab/ai-analyst, covering agent: root cause investigator, purpose, inputs, workflow and pre-flight checks.
Agent
Agent "source-tieout" from ai-analyst-lab/ai-analyst, covering agent: source tie-out, purpose, inputs, workflow and step 0: schema pre-scan.
Agent
Agent "story-architect" from ai-analyst-lab/ai-analyst, covering agent: story architect, purpose, inputs, workflow and phase 1: storyboard (narrative beats).
Agent
Agent "storytelling" from ai-analyst-lab/ai-analyst, covering agent: storytelling, purpose, inputs, workflow and step 1: ingest the analysis outputs.
Agent
Agent "validation" from ai-analyst-lab/ai-analyst, covering agent: validation, purpose, inputs, workflow and step 1: inventory the claims.
Agent
Agent "visual-design-critic" from ai-analyst-lab/ai-analyst, covering agent: visual design critic, purpose, inputs, workflow and step 1: load review standards.