Check version bump, changelog, compare range, package metadata, validation commands, publish steps, and rollback plan before cutting a release.
Inspect and test web UIs using screenshots, browser automation, accessibility snapshots, and console/network signals with structured visual evidence collection.
Use when migrating APIs, libraries, or patterns across a large codebase. Ensures safe, step-by-step progress rather than risky mega-commits.
Check existing repo capability, external libraries, MCP options, and maintenance risk before writing custom code. Decide adopt/wrap/build with explicit criteria.
Inspect GitHub PR checks, fetch actionable failure logs, summarize the breakage, and propose a local fix plan before changing code.
Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
Use when completing a task or running out of context limit. Ensures the next session or human engineer has exactly what they need to resume work instantly.
Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
Diagnose local agent and project setup problems — missing commands, broken MCP configs, stale generated assets, bad paths, invalid catalog entries, and missing env vars.
Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
Use to audit and remove unused or redundant third-party dependencies from package manifests.
Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming…
Fix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.
Use when an MCP server is about to be enabled, added to agent config, or upgraded -- a staged server config is a candidate for activation, a third-party server is proposed from a…
Evaluate metric and semantic model changes for BI/reporting breakage and business meaning drift.
Use to collapse over-engineered abstractions, remove unnecessary layers, or consolidate redundant logic.
Relay questions and tasks to a local Claude CLI using one-shot subprocesses per ask.
Use to diagnose tests that pass and fail intermittently without code changes.
Ensure that new complex models actually outperform simple, naive baselines.
Turn vague implementation requests into testable requirements before coding.
Process-first advisor routing with artifact capture
Audit the methodology used to split data into train, validation, and test sets.
Identify and prevent target leakage in ML preprocessing pipelines.
Multi-model orchestration — route to two external advisors, then synthesize
Use when code needs restructuring without changing observable behavior.
Verify that API endpoints match their OpenAPI/Swagger specifications.
Extract a learned skill from the current conversation manually