ngocsangyem

Weekly-cadence engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. NOT for per-session or per-

JIRA Service Management via the jira-as wrapper: service desks, request types, requests, customers, organizations, queues, SLAs, approvals (8 sub-domains). Triggers: 'create JSM request', 'list service desks', 'SLA status for KEY', 'approve request KEY', 'list queue NAME'. Requires JSM-licensed tenant + agent role. NOT for core Jira issue ops (mk:jira-issue); NOT for project admin (mk:jira-admin).

Pack an EXTERNAL repository into a single AI-friendly file (markdown/xml/json). Use for third-party library analysis, security audits, or handoff to external LLMs. Do NOT use to pack the current project for inbound context — the host runtime already reads files lazily. Triggers: 'pack this repo', 'snapshot of X', 'export codebase', 'repomix'.

Ticket/PRD intake: product area classification, completeness scoring, RCA, technical assessment. Works with Jira (via mk:jira-issue / jira-as), Linear (via MCP), GitHub (via gh CLI), or manual paste. Triggers: 'analyze ticket', 'intake PRD', 'triage issue', 'classify ticket', 'check ticket'.

Test-to-requirement coverage mapping. Reads plan acceptance criteria and test files, produces a coverage gap report showing which requirements have no tests. Use during Phase 2 (Test) or Phase 4 (Review) to verify test completeness. Named after the Nyquist sampling theorem — sufficient test coverage prevents aliased (missed) requirements. NOT for running tests (see mk:testing); NOT for structural

Figma design analysis and implementation via Figma MCP. Parse Figma links, extract design specs, translate to code. Triggers: 'figma', 'design link', 'implement this design', 'design tokens'.

Persists and restores mid-session workflow progress across context resets. Use when resuming workflows, saving state, or handling context compaction. Triggers on: handoff, save state, resume workflow.

Task claiming and ownership tracking for parallel agent execution. Agents claim tasks from a shared queue with file ownership enforcement. Use during parallel execution phases when multiple agents work simultaneously.

Session-scoped safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Active for the current session only. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful m

Operational decision frameworks: triage, escalation, case management, billing ops. Use for 'how to handle X cases', 'build triage', 'escalation protocol'.

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.

Orchestrates single-task implementation pipeline: plan → test → build → review → ship. Use for feature work, plan execution, or fixes scoped to a single task. NOT for green-field product builds (see mk:autobuild); NOT for auto-invoked workflow orchestration (see mk:workflow-orchestrator).