jm-adk

Designs narrative arcs for technical deliverables that transform data and findings into compelling, memorable stories. Trigger: "tell the story", "narrative arc", "make it compelling".

Conway's Law analysis, team interaction modes, cognitive load assessment, organizational design for delivery. Use when user asks to "analyze team topology".

Technical debt classification, interest estimation, and payoff prioritization. Trigger: "quantify tech debt", "debt inventory", "debt interest", "technical debt".

Repository scanning, tech stack identification, architecture signal extraction, and domain mapping. Trigger: analyze repository, scan codebase, map architecture, identify tech stack, discover structure.

Fact-checking technical claims, multidimensional feasibility validation across performance, integration, scalability, security, and team capability. Trigger: "technical feasibility", "feasibility study", "fact check", "can we build", "is it possible".

Applies progressive disclosure, precise terminology, and evidence attribution to technical documents. Trigger: "write the document", "technical documentation", "progressive disclosure".

Test coverage gaps, test quality metrics, and testing strategy assessment. Trigger: "analyze test coverage", "test quality", "coverage gaps", "testing strategy".

Test pyramid design, automation architecture, E2E testing, contract testing, shift-left practices, and test data management. Trigger: "testing strategy", "test pyramid", "test automation", "E2E testing", "contract testing", "test data".

Designs comprehensive test strategies including test pyramid, TDD/BDD flows, contract testing, and mutation testing. Trigger: "test strategy", "testing approach", "test pyramid", "what tests do we need".

Multi-criteria decision framework using weighted scoring matrices, ATAM scenarios, and sensitivity analysis. Trigger: "analyze trade-offs", "compare options", "weighted scoring", "ATAM", "decision matrix".

Optimizes document accessibility, readability, and information hierarchy for technical audiences. Trigger: "improve readability", "document UX", "information design".

Validates frontmatter and body structure of all skills, agents, and commands in a plugin. Triggers: validate components, check frontmatter, component audit, skill validation.

Validates cross-reference integrity across all plugin components. Detects broken references, orphaned skills, missing aliases, and settings.json inconsistencies. Triggers: validate cross-refs, check references, dependency audit, orphan detection.

THE CRITICAL SKILL -- validates hooks.json structure, event names, and type-event compatibility. Detects prompt/agent hooks on events lacking ToolUseContext. Triggers: validate hooks, check hooks.json, hooks audit, hook safety check.

Validates plugin.json completeness, field correctness, and consistency with actual plugin contents. Triggers: validate manifest, check plugin.json, manifest audit.

Validates plugin directory layout against the official Claude Code plugin spec. Triggers: validate structure, check layout, directory audit, plugin skeleton check.

Design vector storage for RAG and semantic search: pgvector setup, embedding model selection, chunking strategies, HNSW vs IVFFlat index comparison, hybrid search (dense + sparse), and metadata filtering.

Audit and optimize Core Web Vitals (LCP, INP, CLS), bundle size, loading strategy, and rendering pipeline. Use when user asks to "optimize performance", "improve Core Web Vitals", "reduce bundle size", or "fix slow page load".

Implement web application security: Content Security Policy (CSP), CORS configuration, XSS prevention, CSRF protection, security headers, input validation. Use when user asks to "implement web security", "add CSP", "fix XSS vulnerability", or "harden the application".

Designs collaborative workshops including event storming, impact mapping, and design sprints with agendas, facilitation guides, and output templates. Trigger: "design a workshop", "event storming", "impact mapping", "design sprint".