The library

analytics · Solo founder or analyst setting up analytics for the first time — provides tool recommendation by stage, event naming conventions, core metrics framework, and GA4 setup checklist to track decisions not dashboards.

tracking · Content marketer or analyst tracking article ROI via CTA clicks and funnel attribution — sets up user ID for cross-session tracking, event naming convention for consistency, and conversion marking for multi-touch attribution.

analyze-test · Validating A/B test results with statistical rigor before deciding to ship a variant.

analytics-insights · Reconstructing metrics from scratch after privacy regulation or preparing for board reporting

data-analysis · When you have structured business data and need decision-quality analysis that separates observation from interpretation.

attribution-modeling · When you need to move beyond last-touch attribution to understand which channels truly drive conversions.

analytics-tracking · Finding why metrics don't match between platforms (GA4 vs ad account) before rebuilding reporting

wf-swarm-score · Verifying adversarial score spreads and detecting hallucinating ants via 3-role consensus.

traffic · Growth leads doing monthly channel performance reviews and trying to understand where unattributed Direct traffic actually comes from.

google-search-console · SEO managers doing monthly monitoring of search visibility and title/meta optimization, who need to prioritize which pages to optimize first.

data-analysis-standard · Explaining unexpected metric movements before escalating to leadership; answers 'what changed, why, so what, now what' for any metric problem.

ai-traffic · Growth marketers trying to understand the new AI-driven referral channel and separate it from traditional organic/referral attribution.

write-query · Quickly drafting SQL exploratory queries without manual syntax lookup.

analyze-cohorts · Measuring product retention and engagement trends by user cohort to guide onboarding improvements and feature prioritization.

google-analytics · Identifying traffic bottlenecks and top-performing pages when you have GA4 set up and need programmatic reporting vs manual dashboard clicks

analytics-tracking · Startups building analytics infrastructure correctly from scratch or teams auditing data quality before strategic decisions.

sql-queries · Rapid SQL generation when analysts need queries without manual syntax work, especially for schema-heavy databases or multiple dialect support.

dividend-growth-pullback-screener · Long-term dividend growth investors who want to combine fundamental 12%+ dividend CAGR with technical entry timing (RSI pullback), keeping cost basis low by catching temporary weakness in quality names.

product-health-analysis · Weekly or monthly health check shared with leadership; forces discipline to separate metrics that matter from noise, and to answer 'so what' before recommending action.

research · Exploratory research with parallel hypothesis agents and cross-check synthesis.

ix-adversarial-llm-panel · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.

measure-performance · Perf fixes where file groups are disjoint and can edit in parallel without race conditions.

espeak-audit-all-langs · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.

espeak-audit-tts-vs-human · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.

investigate · Orchestrate multi-agent investigate across parallel branches and synthesis.

company-research · Automate company research reviews with structured output and validation.

build-dashboard · Creating executive dashboards that work completely offline with embedded data and no server dependencies.

attribution-model · Marketing teams trying to allocate budget based on actual channel contribution instead of last-click bias, where sales cycle complexity requires multi-touch view.

dashboard-builder · Founders who have data but no visibility into it, and need a single-file dashboard they can open in a browser and immediately see the state of their business without loading Mixpanel/Tableau/BI tool.

experiment-designer · Any decision backed by A/B test; forces pre-commitment to success criteria, prevents peeking and goalpost movement, separates statistical from practical significance.

campaign-analytics · Demand-gen and growth teams running multi-channel campaigns who need deterministic attribution without external API dependencies.

detect-platforms · workflow automation in specialized problem domain; check artifact name and description.

fieldatlas-deepread · Literature review requiring faithful extraction with verbatim evidence from long academic papers.

enrich-task-tags · Batch tagging homogeneous content (e.g., all AL benchmark tasks) against controlled vocabulary.

create-dashboard · Assembling a quick real-time monitoring dashboard that reads from an agent's database when one exists — not for complex multi-database UX or heavy interactivity.

comparison-analysis · Quick categorical comparison analysis when data is spread across Excel sheets and visual charts (bar + pie) help identify distribution patterns.

vocab-extract · Best for automating complex multi-phase vocab-extract processes at scale.

compound-extract · Mining reusable patterns from code changes while deduplicating existing knowledge.

attribution-report · Marketing leaders defending budget allocation to executives, where multi-touch comparison reveals that last-click dramatically undercredits awareness and consideration channels.

metrics-track · Social media teams who need weekly measurement before generating performance reports or adjusting content strategy.

model-arena-daily · Benchmarking multi-tier LLM responses against a canonical prompt with regression detection and cost-efficiency scoring.

fieldatlas-synth · Grounding research idea generation in corpus citations with novelty-checking and feasibility critique.

model-arena-daily · Daily intelligence on which Claude tier is best for each task type. Cost-disciplined by design: 3 generators + 1 judge =

grounding-audit · Parallel read-only audits against design claims with completeness criticism.

research-pulse-daily · Daily lightweight research pulse: 3 parallel domain scans + synthesis.

driver-menu-build · Interactive menu-driven workflows with dynamic branching.

multi-modal-sweep · Orchestrate multi-phase multi-modal-sweep tasks with structured verification and recovery.

indicator-why-believed · Orchestrate multi-phase indicator-why-believed tasks with structured verification and recovery.

paper-review-fanout · Parallel review and triage workflows across multiple criteria or models.

fieldatlas-validate · Environment or artifact verification with mechanical pass/fail detection against ground truth.