Advance

Architecture inconsistency detection via deterministic tools, research fallback, and AI heuristic

AI-generated code quality detection via AST, regex, and heuristic analysis

Backend technology stack evaluation — choose boring technology scaled by project context. Use when selecting languages, databases, async infra, or API styles for new or existing backends.

Competitive intelligence research methodology for source code and public information comparison

Improvement-discovery methodology for current-state, LBP, and external landscape analysis

Backlog reconciliation, bug priority assignment, and ROADMAP.md regeneration methodology

Codebase reconnaissance skill for mapping structure, hotspots, and risks

Bounded opportunity scouting for ADV discovery and design phases — identifies missed opportunities and leverage points using existing adv-researcher

Audit Advance instruction prose (AGENTS.md, project.md, ADV_INSTRUCTIONS.md, command/agent files) against executable anchors. Use when editing instructions, suspecting drift after a docs edit broke CI, or checking whether a protocol rule has any executable backing.

Two-plane post-change reflection methodology for archived ADV changes

ADV agent-callable tool contract checklist — keep schemas, command context packets, prompt instructions, specs, and tests aligned. Use when creating or modifying ADV sub-agents, command packets, report schemas, or agent-callable tools.

Frontend/design review methodology — 6-dimension checklist for component correctness, semantic HTML/accessibility, responsive behavior, visual polish, site-design consistency, and finer details

ADV worktree workflow — create, manage, triage, and clean up git worktrees with Temporal-coordinated state and per-worktree git isolation. Covers when to isolate, multi-session model, and merge-before-delete protocol.

Active ADV cleanup triage: stale, abandoned, duplicate, and ready-to-archive changes

Spec/implementation drift audit methodology for ADV capabilities

Conventional commits auto-release CI/CD pattern for public repositories. Auto-semver bump, CHANGELOG generation, binary builds, and GitHub releases on every trunk merge.

Socratic requirements clarification methodology for ADV proposal/discovery/design ambiguity

Stale proposal refresh methodology for single changes and stalest-batch ADV refactors

Structured comparison presentation protocol — format candidates, present side-by-side via question tool, capture preference. Use when facing concrete candidates where user intuition is needed.