Skills

• SkillUSD 2

  Dependency Licence Check

  Audits the licences across your dependency tree — including the transitive ones nobody chose on purpose — flags the obligations and conflicts that matter for how YOU ship, and leaves a policy so the next addition is checked at the door.

  Best for: Due diligence, enterprise deals and the questionnaire that asks about licences

• SkillUSD 2

  Code Style Guide

  Writes the code style guide your team will actually follow: derived from your codebase's existing best patterns, enforced by tooling wherever possible, with human judgement reserved for what tools cannot check.

  Best for: Teams relitigating the same style arguments in every review

• SkillUSD 2

  Dead Code Sweep

  Finds and removes the code that no longer runs — the unreferenced functions, the unreachable branches, the feature nobody can trigger — with the proof of deadness per item, because deleting the wrong thing is how legends start.

  Best for: Codebases where half the reading time is spent on code that never runs

• SkillUSD 2

  Git Hygiene Setup

  Establishes the version-control conventions that keep a repository navigable: branch naming, commit standards, merge strategy, protected branches — decided once, written down, and enforced where tooling allows.

  Best for: Repositories where every developer invented their own workflow

• SkillUSD 2

  Release Notes Draft

  Drafts the notes for one release from its actual changes: what landed, what it means for whom, the upgrade steps if any — in your product's voice, ready for the channel it ships in.

  Best for: The release going out Thursday that still has no notes

• SkillUSD 2

  Data Dictionary

  Builds the dictionary your data actually needs: every table and field with its real meaning, the values it takes in practice, who writes it and who relies on it — documented from the data itself, not from optimistic memory.

  Best for: Warehouses where every analyst re-derives what status=3 means

• SkillUSD 2

  Data Contract

  Writes the contract between a data producer and its consumers: the schema, the semantics, the freshness and quality promises, and what happens when changes come — so pipelines stop breaking by surprise.

  Best for: The pipeline that breaks every time the app team ships

• SkillUSD 2

  Pipeline Design Review

  Reviews a data pipeline's design before (or after) it bites: idempotency, failure recovery, late data, backfills, quality gates — the checklist that separates pipelines that survive reality from the ones that page you weekly.

  Best for: The pipeline design about to be built — reviewed while changes are cheap

• SkillUSD 2

  Data Validation Rules

  Writes the validation rules a dataset actually needs: derived from what the data means and how it breaks, placed at the right checkpoints, with severities that route — block, quarantine, or warn — instead of one giant red light.

  Best for: Datasets guarded today by hope and a not-null constraint

• SkillUSD 2

  SQL Review

  Reviews a query for the two things that matter: does it answer the question it claims to answer, and will it behave at real data sizes — catching the silent joins that double rows and the predicates that defeat every index.

  Best for: The query feeding a decision, checked before the decision

Also see the Agents.