claude-plugins

Perform initial analysis of a codebase - detect tech stack, directory structure, and completeness. Gear 1 of the 6-gear reverse engineering pipeline. Automatically detects programming languages, frameworks, architecture patterns, and generates analysis-report.md.

Generates a complete architecture document from reverse-engineering documents and user-specified constraints. Asks 3-5 high-level questions about tech stack, cloud provider, scale, and hard constraints, then produces architecture.md with Mermaid diagrams, service boundaries, ADRs, and infrastructure recommendations. Works standalone or as part of the BMAD Auto-Pilot workflow.

Generate 4 BMAD planning artifacts (PRD, Architecture, Epics, UX Design) from Gear 2 reverse-engineering docs. Three modes: YOLO (automatic), Guided (targeted questions), Interactive (section-by-section review).

Resolves [NEEDS CLARIFICATION] markers in specifications through interactive Q&A. Asks focused questions about missing features, UX details, and business rules, then updates spec files with complete, unambiguous requirements. Step 5 of 6 in the reverse engineering process.

Transforms 11 reverse-engineering documents from Gear 2 into GitHub Spec Kit specifications with three thoroughness levels (specs-only, specs+plans, specs+plans+tasks). Creates .specify/ directory with constitution, feature specs, implementation plans, and task breakdowns. Gear 3 of 6 in reverse engineering pipeline. Triggered by: 'create specs from reverse engineering docs', 'generate spec kit from documentation', 'run gear 3', 'transform docs into spec kit'.

Orchestrates all 6 StackShift gears sequentially without manual intervention. Supports 7 execution paths including GitHub Spec Kit, BMAD Auto-Pilot, BMAD Method, Architecture Only, Portable Extraction, and Widget Migration.

Ecosystem discovery from a single starting repo. Scans for integration signals (npm packages, docker compose, env vars, API calls, CI/CD triggers, workspace configs, message queues, infrastructure refs), searches GitHub for related repos, scans the local filesystem, then presents an ecosystem map with confidence scoring and a Mermaid dependency graph. Hands off confirmed repos to /stackshift.batch or /stackshift.reimagine.

Performs route-aware gap analysis. In brownfield mode, compares specifications against existing implementation using AST analysis and /speckit.analyze. In greenfield mode, validates specification completeness and prompts for target technology stack selection. Step 4 of 6 in the reverse engineering process.

Use GitHub Spec Kit commands to systematically build missing features from specifications in specs/. Validates against acceptance criteria and achieves 100% spec completion. Step 6 of 6 in the reverse engineering process.

Analyzes integration surfaces across multi-system ecosystems. From starting-point repos and config directories, discovers connected systems, profiles each one, maps cross-system capabilities, tiers functionality (T1/T2/T3/PRUNE), and generates a layered implementation plan (L0-L3) with dependency-ordered epics.

Traces a specific business logic flow across multiple repositories from user-provided starting points. Explores only prompt-relevant code, discovers repos the user missed, traces the algorithm end-to-end, and produces tech-agnostic BMAD specs with reference IDs (BR/DC/EC/ERR/FLOW).

Activated when a brownfield project completes Gear 6 with modernize flag enabled. Upgrades all dependencies to latest stable versions, fixes breaking changes with spec guidance, synchronizes specifications, and validates coverage. Scoped to Node.js/TypeScript projects only.

Extract tech-agnostic portable component specs from StackShift reverse-engineering docs. Generates abstract epics and component specifications for ANY BMAD project. Bridges StackShift code analysis with reusable, platform-independent component specifications.

Translates portable component specs into targeted BMAD epics for a specific target project by mapping abstract personas, domain language, and data contracts against the target's PRD and Architecture. Activated when the user has completed portable-extract and wants to import business logic into a target project.

Detects code changes since reverse-engineering docs were last generated and surgically updates only the affected documentation files. Triggered by "refresh the docs", "update reverse-engineering docs", or "sync docs with latest code".

Synthesizes reverse-engineering docs from 2+ repositories into a unified capability map, identifies duplication and gaps, facilitates brainstorming to reimagine the system, and generates new specifications. Trigger phrases - reimagine these services, consolidate these repos, synthesize a new vision, redesign from multiple repos.

Performs deep codebase analysis to generate 11 comprehensive documentation files. Adapts output based on the selected route -- Greenfield extracts business logic only (tech-agnostic), Brownfield extracts business logic + technical implementation (tech-prescriptive). Step 2 of 6 in reverse engineering. Use when asked to reverse engineer the codebase, extract business logic, or generate comprehensive documentation.

Generate a visual spec-to-code coverage map showing which code files are covered by which specs. Creates ASCII diagrams, reverse indexes, and coverage statistics. Use after implementation or during cleanup to validate spec coverage.

End-to-end legacy widget migration pipeline. Accepts a widget ID as argument (e.g., v9.widgets.model-selector.responsive.v1, ws-hours) — auto-resolves source location, extracts business logic, generates preference catalog, maps to Iris design system, and produces BMAD-compatible specs and stories for React Router 7 + Iris + TypeScript. Run from your target repo — no need to navigate to the widget source.