ngocsangyem

Multi-pass structural code review with adversarial analysis, scope-aware dispatch, adversarial persona passes, and forced-finding protocol. Supports input modes: branch diff (default), PR number (#123), commit hash, pending changes (--pending). Use when asked to "review this PR", "code review", "pre-landing review", "check my diff", or "review #123". Proactively suggest when the user is about to m

Use when designing UI components, creating design systems, reviewing visual design, or checking accessibility compliance. Triggers on "design system", "UI review", "color palette", "font pairing", "accessibility audit", "responsive design", "WCAG check". Auto-activates when ui-ux-designer agent is working. Data-driven: 160 palettes, 73 font pairings, 161 product types, 98 UX guidelines, 25 chart t

Production ready. AI Agent Workflow System for Claude Code

Use when exploring technical solutions, comparing approaches, or generating alternatives for a validated problem. Triggers on "brainstorm solutions", "explore approaches", "compare options", "trade-off analysis", "how should we build". Do NOT use for product validation ("is this worth building?" → use mk:office-hours instead). Do NOT use when a plan already exists (→ use mk:plan-ceo-review instead

Gera arquivos llms.txt a partir da documentação do projeto, seguindo a especificação llmstxt.org. Use quando solicitado a criar índices de documentação amigáveis à IA, gerar llms.txt ou tornar um projeto detectável por assistentes de IA.

Use when measuring harness changes against ground truth — runs a small canary suite (5 quick tasks, 6 with --full) and records scores in trace-log.jsonl. Backs the dead-weight audit with measured deltas. Triggers on /mk:benchmark, "run benchmark", "measure harness", or before/after a harness change.

Analyzes ticket complexity and maps dependencies against an existing codebase before sprint planning. Triggers on 'how complex is this ticket', 'what should we work on first', 'can we fit this in the sprint', 'tech review before planning', 'plan the sprint'. NOT for writing implementation plans (see mk:plan-creator); NOT for scope/ambition review (see mk:plan-ceo-review).

Drive JIRA workflow lifecycle via the jira-as wrapper: transition, assign, resolve, reopen, manage versions and components. Triggers: 'transition KEY to Status', 'mark KEY as Done', 'assign KEY to user', 'reopen KEY', 'release version', 'create component'. NOT for issue CRUD (mk:jira-issue); NOT for bulk transitions (mk:jira-bulk).

Bulk Confluence operations on 10+ pages via the confluence-as wrapper: bulk-label / bulk-move / bulk-delete. Dry-run is MANDATORY first. Triggers: 'bulk update N pages', 'mass label', 'delete all pages matching CQL', 'bulk-move pages to PARENT'. NOT for single-page ops (mk:confluence-page); NOT for comment/attachment ops (mk:confluence-collaborate).

Manages git worktrees for parallel agent isolation. Creates isolated worktrees for parallel agents on parallel/{name}-{timestamp} branches, merges results with conflict detection, prunes stale metadata, and reports health status. NOT for user-initiated feature branches — use git worktree directly for that.

Deep spec analysis on a Confluence page. Reads page (+ children) via the confluence-as wrapper, produces a structured Spec Research Report with requirements, acceptance criteria, gaps, ambiguities, and suggested user stories for human review. Read-only — does NOT create Jira tickets. Triggers: 'analyze spec for PAGE-ID', 'extract requirements from confluence page', 'spec research on URL'. NOT for

Database patterns: schema design, migrations, query optimization, indexing. PostgreSQL primary. Use for 'database schema', 'migration', 'SQL optimization'.