marcusgoll
- 47 skills
- 0 followers
- 3 hours ago last updated
- ▌
- ▌
- ▌
- ▌ Task Breakdown Phase 2 · marcusgoll bundleStandard Operating Procedure for /tasks phase. Covers task sizing, acceptance criteria definition, and TDD-first task sequencing. (project)
- ▌ Parallel Execution Optimizer 2 · marcusgoll bundleIdentify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight (5 checks), /implement (task batching), /prototype (N screens). Auto-triggers when detecting multiple independent operations in a phase.
- ▌
- ▌
- ▌ Deep Quick · marcusgollFast mode for small tasks (<30 lines, single file). Use when user asks for 'quick fix', 'fast fix', 'simple change'. Skips planning, 3-iteration limit.
- ▌ Cancel Deep · marcusgollCancel active deep loop session. Use when user asks to 'stop deep', 'cancel deep', 'abort loop'. Cleans up state files.
- ▌ Deep Status · marcusgollCheck deep loop progress and session state. Use when user asks 'what status', 'where are we', 'deep status'. Shows phase, tasks, and iteration count.
- ▌ Deep Triage · marcusgollClassify task complexity as QUICK/STANDARD/DEEP. Use when user asks 'how complex', 'triage this', 'assess difficulty'. Determines appropriate workflow.
- ▌ Start Ralph · marcusgollStart autonomous PRD processing (ralph mode). Use when user asks for 'overnight mode', 'process PRD', 'autonomous execution'. Long-running background tasks.
- ▌ Blind Critic · marcusgoll bundleJudge a built surface against a reference artifact via blind A/B comparison. Use during the REVIEW phase of deep loop, or ad hoc when the user asks to "critique the UI against the prototype", "blind critic", "compare to the design", or "is this as good as the reference".
- ▌ Cancel Ralph · marcusgollStop ralph mode PRD processing. Use when user asks to 'cancel ralph', 'stop autonomous mode'. Halts background execution.
- ▌ Deep Cleanup · marcusgollClean up stale deep loop files. Use when user asks to 'clean up', 'remove .deep directories'. Removes old session artifacts.
- ▌ Deep Execute · marcusgollProcess queued tasks from .deep/tasks.md. Use when user asks to 'execute queue', 'process tasks', 'run queued work'. Supports multi-session claim-based coordination with git conflict handling.
- ▌ Deep Fullstack · marcusgollCoordinate frontend+backend development with shared types. Use when building full-stack features, 'connect frontend to API', or 'end-to-end'. Includes E2E testing.
- ▌ Diagnose Hooks · marcusgollTroubleshoot hook errors. Use when user sees 'PreToolUse hook error', 'PostToolUse error', or asks to 'diagnose hooks'. Identifies and fixes plugin hook failures.
- ▌ Internal Ralph · marcusgollInternal ralph mode executor. Processes PRD backlog using Task subagents. Called by start-ralph, not user-invoked directly.
- ▌ Design Tournament · marcusgollProduce a design reference where none exists, by interrogating the problem then running a blind round-robin between candidates. Use when starting a new page or surface with no prototype, when the existing prototype has been outgrown, or when the user asks to "explore designs", "compare approaches", "run a design tournament", or "which layout is better".
- ▌
- ▌ Deep Add · marcusgollAdd tasks to deep loop queue (.deep/tasks.md). Use when user asks to 'add task', 'queue this', 'deep add'. Interactively gathers task details.
- ▌ Dry Run · marcusgollPreview command effects without making changes. Simulates file writes, git operations, agent spawns, and state changes. All reads execute normally for accurate preview. Use --dry-run flag on any command.
- ▌ Ultrathink · marcusgollDeep planning philosophy for craftsman-level architecture. Transforms planning from research-then-design to research-question-simplify-design. Use when --deep flag is set, for epics, complex features (30+ tasks), or when auto_deep_mode preference is enabled. Invokes assumption questioning, codebase soul analysis, and ruthless simplification. (project)
- ▌ Debug Phase · marcusgoll bundleSystematic debugging techniques including error classification, root cause analysis (5 Whys), reproduction strategies, and error documentation. Use when debugging errors, investigating failures, analyzing stack traces, fixing bugs, or documenting errors in error-log.md. (project)
- ▌
- ▌
- ▌
- ▌
- ▌ Analysis Phase · marcusgoll bundleValidates cross-artifact consistency and detects breaking changes during feature analysis. Use when running /analyze command, validating spec-plan alignment, checking task-implementation consistency, or identifying API/database/UI breaking changes before deployment. (project)
- ▌ Finalize Phase · marcusgoll bundleCompletes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project)
- ▌ Planning Phase · marcusgoll bundleGenerates implementation plans with code reuse analysis, architecture design, and complexity estimation during the /plan phase. Use when planning feature implementation, analyzing code reuse opportunities, or designing system architecture after specification phase completes. Integrates with 8 project documentation files for constraint extraction. (project)
- ▌ Error Recovery · marcusgollClassify workflow failures and attempt automatic recovery. Use when sprint/feature fails during implementation to determine if auto-fix is possible or manual intervention required.
- ▌
- ▌
- ▌ Optimization Phase · marcusgoll bundleValidates production readiness through performance benchmarking, accessibility audits, security reviews, and code quality checks. Use after implementation phase completes, before deployment, or when conducting quality gates for features. (project)
- ▌ Shadcn Integration · marcusgollIntegration guide for shadcn/ui components with OKLCH design tokens. Use when setting up shadcn, customizing themes, or adding components to Next.js projects. Auto-trigger on /init --tokens --shadcn flag.
- ▌
- ▌ Specification Phase · marcusgoll bundleProvides standard operating procedures for the /specify phase including feature classification (HAS_UI, IS_IMPROVEMENT, HAS_METRICS, HAS_DEPLOYMENT_IMPACT), research depth determination, clarification strategy (max 3, informed guesses for defaults), and roadmap integration. Use when executing /specify command, classifying features, generating structured specs, or determining research depth for planning phase. (project)
- ▌
- ▌ Implementation Phase · marcusgoll bundleExecutes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project)
- ▌ Task Breakdown Phase · marcusgoll bundleStandard Operating Procedure for /tasks phase. Covers task sizing, acceptance criteria definition, and TDD-first task sequencing. (project)
- ▌ Staging Deployment Phase · marcusgollDeploys features to staging environment with database migrations, health checks, and deployment verification. Use during /ship-staging phase or when deploying to staging environments for validation before production release.
- ▌ Staging Validation Phase · marcusgoll bundleGuides manual staging validation before production deployment through smoke tests, critical user flow testing, data migration verification, and rollback capability checks. Use when validating staging deployments, running pre-production tests, or preparing for production promotion in staging-prod deployment model. (project)
- ▌ Regression Test Generator · marcusgoll bundleGenerate regression tests when bugs are discovered during /debug or continuous checks. Auto-detects test framework, creates Arrange-Act-Assert tests, and links to error-log.md entries. (project)
- ▌ Production Deployment Phase · marcusgollExecutes production deployment workflow by promoting validated staging builds to production with semantic versioning, health checks, and release tagging. Use when running /ship-prod command, deploying to production after staging validation, or promoting staging builds to production environment.
- ▌ Parallel Execution Optimizer · marcusgoll bundleIdentify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight (5 checks), /design-variations (N screens), /implement (task batching). Auto-triggers when detecting multiple independent operations in a phase.