Research & Data

Builds a linked strategy choice cascade (winning aspiration, where to play, how to win, capabilities, management systems) so a direction is coherent and internally reinforcing, not a list of ideas.

Builds a zero-based budget for a cost center by requiring every line item to be justified from first principles rather than rolled forward from the prior year.

Decomposes cost changes into volume, rate, and mix effects to identify the true root cause of cost escalation or decline.

Reads industry structure with Porter's Five Forces and profiles rivals on capability and cost, giving a clear view of who you compete with and how attractive the industry really is.

Builds an answer-first plan by stating disprovable hypotheses and, for each, the "what would prove me wrong" test and the exact analysis that settles it, so the team tests instead of boiling the ocean.

Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs evidence. Not for external feature teardowns; use reverse-engineer.

Research bounded public source scopes, then return one independent ranked assessment.

Researches a competing product against your own and produces a ranked build-or-ignore verdict, plus optional comparison-page copy. Use when the user names a competitor or asks how their product stacks up against one. Trigger phrases include "vs us", "competitor", "what does X have", "should we copy", "competitive gap", "teardown", "are we behind". Produces a ranked verdict with effort estimates and an explicit not-worth-copying list.

Build batch and incremental data ingestion (extract-load) pipelines — full vs incremental extraction, change data capture (CDC), watermarks and high-water marks, API pagination and rate limits, and choosing managed EL tools (Fivetran, Airbyte) vs custom code. Use when ingesting data from databases, APIs, files, or SaaS into a warehouse/lake, or designing incremental extraction and CDC.

Build ML feature pipelines and feature stores — point-in-time-correct joins to avoid label leakage, offline/online parity, feature freshness and backfills, and materialization with tools like Feast. Use when engineering features for ML, preventing train/serve skew or data leakage, building a feature store, or backfilling historical features for training.

Design and operate Apache Iceberg tables — partitioning and hidden partitioning, partition/schema evolution, snapshots and time travel, compaction and small-file cleanup, and MERGE/upsert for lakehouse tables on Spark, Flink, Trino, or Snowflake. Use when creating or maintaining Iceberg tables, choosing partitioning, evolving schema/partitions, or fixing small-file and metadata bloat.

Systematically root-cause data pipeline failures and data incidents — job errors, wrong or missing data, duplicates, and freshness misses — by tracing lineage upstream, isolating the failing stage, reconciling against source, and planning a safe fix and backfill. Use when a pipeline fails, numbers look wrong, data is missing or duplicated, a dashboard is stale, or a stakeholder reports a data discrepancy.

Build well-structured dbt models — staging/intermediate/marts layers, ref() and source(), materializations, and incremental models with the right strategy. Use when creating or refactoring dbt models, choosing table vs view vs incremental, structuring a dbt project, or writing incremental logic.

Build Dagster pipelines using software-defined assets — asset dependencies, partitions, resources and IO managers, asset checks, and schedules/sensors. Use when creating Dagster assets or jobs, modeling data as assets, adding partitions or backfills, wiring resources/IO managers, or migrating from task-based orchestration to assets.

Set up server-side conversion tracking so purchases are reported accurately to Facebook, TikTok, Google and Bing despite iOS restrictions, ad blockers and cookie loss. Use when conversions are under-reported, when platform-reported purchases do not match real orders, when asked about Conversions API / Events API / offline conversions / CAPI, click id passthrough (fbclid, ttclid, gclid, msclkid), or when ad optimization has degraded after tracking changes.

Write production-grade Apache Airflow DAGs using the TaskFlow API — idempotent tasks, correct scheduling and catchup, retries/SLAs, connections/variables, and avoiding top-level code. Use when creating or reviewing Airflow DAGs, scheduling pipelines, wiring task dependencies, configuring retries/backfills, or fixing non-idempotent tasks.

Build reliable Apache Kafka consumers and producers — consumer groups and partition assignment, offset commit strategy, at-least-once vs exactly-once, idempotent/transactional producers, rebalancing, and dead-letter handling. Use when writing Kafka consumers/producers, configuring offset commits or consumer groups, tuning throughput, or handling rebalances and poison messages.

Define and enforce data contracts between producers and consumers — explicit schema, semantics, ownership, SLAs, and versioning — to prevent silent upstream changes from breaking downstream pipelines. Use when a producer schema change could break consumers, defining an interface between teams/services and the warehouse, or adding schema enforcement at ingestion.

Plan and run safe data backfills and replays — idempotent reprocessing of historical windows, partition-by-partition execution, isolating backfill compute from production, verifying results, and avoiding double-counting or changed history. Use when backfilling a new or fixed model, reprocessing after a bug, replaying events, or loading history for a new pipeline without corrupting existing data.

Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).

Scrape AI papers published by 28 big tech companies and AI labs in a given date window, with institutional attribution (lead vs. participating vs. intern). Use when the user asks "what did big tech publish recently", "what AI research has <company> put out", "run the paper radar", or wants to inventory recent arXiv output by company or topic. Also for fact-checking questions like "has <company> published anything on <topic>".

Find, verify and rank potential customers, first customers, early adopters, design partners, beta users or sales leads for a product using public pain, demand and timing signals. Use when the user supplies a product URL, repository, pitch or description and wants an ideal customer profile, a researched prospect shortlist, evidence-backed lead qualification, fit and timing scores, source-verified buying signals, repeated pain patterns, a CRM-ready lead export, source-based outreach drafts, or a shareable prospecting report. Every prospect must be traceable to a fetched, dated public source. Never sends outreach.

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes Agent, apply an author's frameworks while working, or build a reusable knowledge base from a file.

A CLI way to interact with autodoc.ru & armtek.ru to search & order spare parts for your car. Includes agent skill for tool usage