discover
Ecosystem Discovery
Estimated Time: 10-30 minutes (depending on ecosystem size and GitHub search)
Prerequisites: A starting repo with real code (not empty scaffolding)
Output: ecosystem-map.md in the starting repo's .stackshift/ directory, .stackshift-batch-session.json in the starting repo directory for handoff
All path variables MUST be double-quoted in shell commands. This skill is single-session with no resume capability -- if interrupted, re-run from Step 1.
When to Use This Skill
Activate when:
- The user has one repo and wants to find everything it connects to
- A large-scale reverse-engineering project needs repo enumeration
- The user wants to map an entire platform before running batch analysis
- The dependency graph between multiple repos/services is unknown
Trigger Phrases:
More from jschulte/claude-plugins
reverse-engineer
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.
106gap-analysis
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.
24analyze
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.
20complete-spec
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.
19create-specs
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'.
19cruise-control
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.
18