Production ready. AI Agent Workflow System for Claude Code
This repository also configures its own agents. See what MeowKit tells them →
Skill Claude Code
Domain-aware complexity routing. Scans task description for domain keywords, matches against domain-complexity.csv, returns complexity level, workflow intensity, and execution tier. Extends Phase 0 orchestration.
Skill Claude Code
Fast parallel codebase scouting. Spawns multiple Explore subagents to search directories simultaneously, returning a consolidated file map with architecture fingerprint, complexity estimates, and routing suggestions. Use before planning, debugging, or any task spanning multiple directories. NOT for reading a single…
Skill Claude Code
Use when a problem requires structured step-by-step reasoning before acting. Prevents jumping to conclusions or guessing root causes without evidence. Triggers on complex debugging, multi-step analysis, hypothesis verification, or when mk:fix invokes diagnosis phase. NOT for being stuck on approach (too many…
Skill Claude Code
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.
Skill Claude Code
Ship workflow with explicit scopes: prepare stages and commits locally; release pushes and creates a PR; publish manages issues and versioning. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is ready or asks about deploying. Supports…
Skill Claude Code
Create a self-contained, visually polished HTML showcase page for a topic or set of artifacts. Supply a mission (topic summary) and optional artifact paths explicitly — the skill never auto-scans the repo. Writes output to assets/showcase/ /. Screenshots are optional (requires Puppeteer). Publishing is local-only by…
Skill Claude Code
Post-implementation simplification pass. Reduces complexity without changing behavior. Use after Phase 3 (Build GREEN) and before Phase 4 (Review). Catches dead code, unnecessary abstractions, over-engineering, and redundant patterns. Triggers on "simplify", "clean up", "reduce complexity", "too complex". NOT for…
Skill Claude Code
Create new skills with proper structure, compliance checks, and registration. Use when asked to create a skill, build a new skill, or scaffold a skill template. Enforces mk: prefix, sub-agents.md structure, and context engineering principles.
Skill Claude Code
Secure skill template with prompt injection defenses. Copy this template when creating new skills.
Skill Claude Code
Use when negotiating a file-based sprint contract between the generator (developer) and evaluator before code is written. Translates a product-level spec into testable acceptance criteria with rubric tie-ins. Triggers on /mk:sprint-contract, "draft a sprint contract", "negotiate scope for sprint", or before any…
Skill Claude Code
Generate novel UI from a text prompt via Stitch AI. Exports Tailwind/HTML, produces DESIGN.md for mk:frontend-design handoff. NOT for implementing existing designs — use mk:figma or mk:frontend-design for that.
Skill Claude Code
Pre-ticket Fibonacci sizing for a paste-mode batch of user stories. Default mode is advisory-only (writes a Story Sizing Report). Opt-in --auto-create delegates ticket creation to mk:jira-issue + mk:jira-collaborate with mandatory dry-run + single batch confirmation gate. NOT for single-ticket estimation…
Skill Claude Code
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.
Skill Claude Code
Set up parallel agent team for COMPLEX tasks. Creates worktree structure, generates ownership map, and initializes task queue. Use when orchestrator decomposes a task into parallel subtasks, or when asked to "set up team", "parallel setup", or "configure worktrees".
Skill Claude Code
Generate publish-grade SVG+PNG technical diagrams — architecture, data flow, flowchart, sequence, agent-memory, class, ER, state-machine, comparison, timeline, and more — across 8 visual styles. Writes output to tasks/visuals/ or an active plan's visuals/ directory. Requires rsvg-convert (librsvg) for PNG export…
Skill Claude Code
Use when writing tests, running validation scripts, or (in TDD mode) enforcing red-green-refactor cycle. Activates during Phase 2 (Test) and Phase 3 (Build). NOT for coverage gap mapping (see mk:nyquist); NOT for sprint contract negotiation (see mk:sprint-contract).
Skill Claude Code
Use when analyzing harness trace logs to surface recurring failure patterns and suggest harness improvements. Scatter-gather pattern across last N runs with mandatory HITL gate before any change is applied. Triggers on /mk:trace-analyze, "analyze traces", "find patterns in harness runs", or after a model upgrade…
Skill Claude Code
Use when writing TypeScript code, fixing type errors, or configuring strict type safety. Auto-activates on .ts/.tsx files. Covers null handling, utility types, and ESLint.
Skill Claude Code
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.…
Skill Claude Code
Validates an approved plan against 8 dimensions before Phase 3 begins. Catches incomplete acceptance criteria, missing dependencies, and unresolved risks. Use after Gate 1 approval and before Phase 2 (Test). Produces a validation report with pass/fail per dimension.
Skill Claude Code
Unified verification: build→lint→test→type-check→coverage. Use for 'is everything green', 'run all checks', 'verify build'. Auto-called by mk:cook. NOT for lint/format only (see mk:lint-and-validate); NOT for test-to-requirement coverage mapping (see mk:nyquist).
Skill Claude Code
Use when a plan directory (plan.md + phase-.md) needs a visual review. By DEFAULT this drives the STRUCTURED visual-plan artifact (visual-plan/plan.json) via the mewkit visual-plan CLI — generate if absent, validate, open the local studio (view/edit), and export plan.html from the approved artifact. Pass --static for…
Skill Claude Code
Use for deep Vue 3 best-practices review, recommendations, and the full ordered authoring workflow — built-in components (Teleport, Suspense, KeepAlive, Transition, TransitionGroup), animation techniques, slots, fallthrough attrs, custom directives, async components, render functions, plugins, and the…
Skill Claude Code
Use for Vue 3 testing best-practices review and recommendations — designing and auditing Vitest + Vue Test Utils tests for components, composables, Pinia stores, Vue Router, async/Suspense, Teleport, forms, and accessibility, plus Playwright E2E test-design strategy. Advisory/review only — recommends patterns and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: