Structured workflows, parallel grok sub-agents, and closed-loop pipelines for Claude Code
31 skills. Invoke with /<name>. Generated from skill frontmatter — this page cannot drift.
| Skill | Ships to host projects | What it does |
|---|---|---|
/planner |
yes | Decompose complex tasks into chapter-based plans saved to drom-plans/, with progress tracking and session resumption |
/implementer |
yes | Write production-quality code following project conventions |
/reviewer |
yes | Code review with severity ratings and actionable feedback |
/debugger |
yes | Systematic bug investigation and root cause analysis |
/refactorer |
yes | Safe, incremental code restructuring with test verification at each step |
/architect |
yes | System design, technology decisions, and architecture decision records |
/orchestrator |
yes | Design and run closed-loop pipelines that iterate until all checks pass |
/api-expert |
yes | Design and implement contract-first REST APIs in Java/Spring Boot with OpenAPI 3.1, security, rate limiting, and consistent resource shapes |
/ascii-architect |
yes | Convert thoughts, architectures, processes, and images into token-efficient ASCII art diagrams |
| Skill | Ships to host projects | What it does |
|---|---|---|
/grok-fleet |
yes | Fan out work to grok CLI sub-agents in parallel from WSL, with filesystem-based progress, monitoring, and stop control — combined with Claude sub-agents |
/df-research |
yes | Deep research on the grok fleet — decompose, multi-perspective sweep, independence and contradiction audit, adversarial critics, cite-check gate |
| Skill | Ships to host projects | What it does |
|---|---|---|
/web-quality-audit |
yes | Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to “audit my site”, “review web quality”, “run lighthouse audit”, “check page quality”, or “optimize my website”. |
/accessibility |
yes | Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to “improve accessibility”, “a11y audit”, “WCAG compliance”, “screen reader support”, “keyboard navigation”, or “make accessible”. |
/seo |
yes | Optimize for search engine visibility and ranking. Use when asked to “improve SEO”, “optimize for search”, “fix meta tags”, “add structured data”, “sitemap optimization”, or “search engine optimization”. |
/performance |
yes | Optimize web performance for faster loading and better user experience. Use when asked to “speed up my site”, “optimize performance”, “reduce load time”, “fix slow loading”, “improve page speed”, or “performance audit”. |
/core-web-vitals |
yes | Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to “improve Core Web Vitals”, “fix LCP”, “reduce CLS”, “optimize INP”, “page experience optimization”, or “fix layout shifts”. |
/best-practices |
yes | Apply modern web development best practices for security, compatibility, and code quality. Use when asked to “apply best practices”, “security audit”, “modernize code”, “code quality review”, or “check for vulnerabilities”. |
| Skill | Ships to host projects | What it does |
|---|---|---|
/discovery-process |
yes | Run a continuous discovery cycle from a fuzzy problem to a tested decision using opportunity mapping, assumptions, and small experiments before building. |
/problem-statement |
yes | Turn vague complaints and feature requests into testable, user-centred problem statements before a team chooses a solution. |
/jobs-to-be-done |
yes | Uncover what customers hire or fire a product to accomplish; use for discovery, interviews, positioning, prioritisation, and churn analysis. |
/customer-journey-map |
yes | Map an end-to-end customer journey to locate concentrated pain, emotional shifts, broken touchpoints, and moments where the experience is won or lost. |
/user-story-mapping |
yes | Build a journey-centred story map and slice a thin, coherent first release when a team needs shared scope and release decisions. |
/epic-breakdown-advisor |
yes | Break an epic into independently shippable vertical stories, ordered to expose risk and generate useful learning early. |
/user-story |
yes | Write implementation-ready user stories with role-goal-benefit context, testable Gherkin acceptance criteria, and an INVEST quality check. |
/user-story-splitting |
yes | Split an oversized user story into small, valuable end-to-end slices when it cannot be delivered, reviewed, or learned from safely as one unit. |
/prd-development |
yes | Create or revise a product requirements document when a team needs agreement on the problem, outcomes, scope, exclusions, constraints, and rollout. |
/roadmap-planning |
yes | Build outcome-based now/next/later roadmaps when priorities may shift and feature-date promises would mislead. |
/prioritization-advisor |
yes | Select and apply RICE, ICE, value-effort, weighted scoring, or cost of delay when prioritizing product work without false precision. |
| Skill | Ships to host projects | What it does |
|---|---|---|
/add-javaducker |
yes | Configure JavaDucker as an optional companion tool for semantic code search and indexing |
/remove-javaducker |
yes | Remove JavaDucker companion tool configuration from this project |
| Skill | Ships | What it does |
|---|---|---|
/dynamodb-architect |
yes | Design, review, refactor and debug DynamoDB data layers — access patterns first, key and index design, capacity and cost, and the migration paths for changes that cannot be made in place. Use whenever work touches a DynamoDB table, schema, GSI, or a throttling or cost problem. |