Chromatic_Governance

Interactive front-end design companion — iterate on layouts, live component previews, and design tokens in a real browser, then hand the validated design to the frontend-family implement skills. Use when the user wants to design or refine UI look-and-feel, compare layout/wireframe options, preview real components, or tune color/spacing/typography before building.

Ingest, decompose, govern, and route large repository PDR packages into agent-routable work queues with manifests, decision registers, risk registers, governance gates, and swarm-ready handoff packets. Use when the user provides repo PDR packages, audit bundles, project design records, implementation plans, backlog packs, or governance artifacts and wants them parsed, scored, split into agent assignments, and dispatched through the Chromatic router.

Triage scattered, nonlinear, or overloaded thinking into a structured stack of decisions, priorities, and handoffs. Use when the project feels ambiguous, when too many threads are running in parallel, when you cannot determine what to work on next, or when a session has accumulated more open questions than resolved ones.

Audit and redesign a repository's folder structure, root hygiene, scattered files, and naming conventions. Use when the repo root is cluttered, directories have grown organically without governance, files are misplaced across boundaries, or you need a clean canonical tree before onboarding agents or contributors.

Enforce numbered folder and subfolder naming standards across a repository. Audit whether directories follow an established numeric prefix convention (e.g. .01_, .02_, 01-, 1.) and produce a compliance report with remediation steps. Use when repo directories have grown without consistent naming, when onboarding contributors, or before a structural refactor.

Plan, audit, and standardize GitHub organization and repository governance — including personal-to-org repo transfers, branch protection, rulesets, team permissions, labels, repository settings, secrets review, and post-transfer validation. Use when moving repos into an organization, auditing existing permissions, generating settings checklists, or producing migration runbooks.

Capture durable project memory after significant decisions, repo changes, PDR completions, migrations, agent dispatches, audits, or implementation cycles. Use when updating project state, decision registers, changelogs, memory logs, source-of-truth maps, or next actions across Claude, Codex, Cursor, Gemini, GitHub, and local repositories.

Track, report, and manage context window and token usage across models and agent sessions. Use when diagnosing slow responses, planning context-heavy tasks, monitoring subagent token budgets, logging usage across sessions, or deciding when to invoke context-prune, handoff, or model switching.

Convert PDRs, repo-router dispatch boards, project queues, audit findings, and agent tasks into execution-ready handoff packages for Cursor, Codex, Claude, Gemini, GitHub Issues, and local LLM/IDE agents. Use when operationalizing plans across other LLMs or IDEs, creating implementation briefs, generating target-specific task files, or packaging repo work into portable handoffs with allowed actions, blocked actions, acceptance criteria, and stop conditions.

plan advanced blender and 3d asset workflows, including modeling, materials, textures, rigging, export, optimization, web/runtime delivery, and asset library management. use when the user asks about blender, 3d models, textures, glb/gltf, game assets, or 3d ui elements.

plan and document reusable frontend component libraries, component apis, variants, states, accessibility, tests, and usage examples. use when the user asks for ui components, design system primitives, reusable react/vue/svelte components, or component governance.

design and maintain reusable css libraries, design tokens, base styles, utilities, layout systems, component css, and documentation. use when the user asks how to build, organize, govern, or refactor css for a project or shared ui system.

evaluate public or external ui/ux platforms, low-code tools, prototype builders, hosted dashboards, and design/development platforms. use when the user asks which ui platform, builder, dashboard tool, or prototyping platform fits a use case.

plan and scaffold interactive guis, ui/ux platforms, web apps, control panels, demos, and low-code style interfaces. use when the user asks for an interactive interface, clickable prototype, gui app, visual workflow, or local/hosted ui surface.

choose and scaffold local app approaches including tui, cli, local web dashboards, python gui, electron, tauri, and desktop-style tools. use when the user asks for a local app, terminal ui, desktop app, offline tool, or local-first workflow.

design or scaffold quick dashboards, admin panels, kpi views, internal tools, status boards, and monitoring uis. use when the user asks for dashboards, control panels, reporting views, metrics uis, or quick visual management interfaces.

create tailwind design systems, presets, config tokens, utility conventions, component recipes, and best-practice tailwind workflows. use when the user asks about tailwind, utility-first css, class organization, or reusable tailwind ui patterns.

review and improve ui/ux designs for usability, accessibility, responsiveness, information architecture, forms, interaction states, and performance. use when the user asks for frontend best practices, ui critique, ux review, or design polish.

inventory, extract, classify, and plan migration of webpage assets from urls, local html, css, and frontend bundles. use when the user asks to copy a site style, inspect a webpage, collect images/fonts/icons/scripts/media/3d assets, or create an asset manifest.

Multi-model consensus council. Spawns parallel judges with configurable perspectives. Modes: validate, brainstorm, research. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".

Placeholder for the Handoff Ready workflow in the RPI Lifecycle plugin. Invoke when the user asks for handoff ready within this plugin family scope.

Review incoming PRs, agent-generated changes, or diffs. Structured review with security, correctness, performance, and maintainability checks. Triggers: "review", "review PR", "review changes", "code review", "review this PR", "review agent output", "check this diff".

Test generation, coverage analysis, and TDD workflow. Triggers: "test", "generate tests", "test coverage", "write tests", "tdd", "add tests", "test strategy", "missing tests", "coverage gaps".

Parses the latest /insights report and autonomously generates PDRs, queues items into next-session-queue, writes an audit file. Triggers: harvest insights, process insights, queue insights, insights to pdr.

Cross-rig knowledge consolidation. One-time sweep + ongoing tiered promotion. Walks all .agents/ directories, extracts learnings, deduplicates, and promotes to knowledge base. Triggers: harvest, consolidate knowledge, extract learnings, knowledge sweep.

Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".

Audits all configurable system properties and shows how they cascade into subsystems, pipelines, hooks, and ways of working. Supports pre-change preview, post-change report, and before/after diff via snapshots. Triggers: system audit, audit properties, property impact, what does X affect, settings cascade.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Evaluate agent performance after a sprint, review, incident, build cycle, or multi-agent run. Use when the user asks what worked, what failed, which agents were effective, where delegation broke down, or how to improve future agent workflows.

Create and maintain an auditable roster of agents, roles, responsibilities, capabilities, permissions, and review relationships for Claude Code, IDE agent teams, plugin families, or multi-agent sprints. Use when the user asks which agents exist, what each agent should do, how to define specialist roles, or how to avoid overlapping authority.

Map decision rights and action permissions across humans, agents, skills, plugin families, hooks, scripts, MCP servers, CI jobs, and external systems. Use when the user asks who can approve, edit, merge, deploy, access secrets, run commands, or make final decisions in an agent workflow.

Resolve disagreements between agents, skill outputs, plans, reviews, tests, docs, or architecture decisions using evidence hierarchy and explicit decision rules. Use when agents disagree, outputs conflict, recommendations diverge, sources contradict each other, or a coordinator needs a final decision path.

Choose the right agent, skill, plugin family, or workstream owner for a task using scope, risk, authority, and required evidence. Use when the user asks to assign work, split a request among agents, decide who should act next, route tasks across plugin families, or prevent the wrong agent from taking action.

Decide when an agent must stop and ask a human, higher-authority reviewer, or specialist agent before continuing. Use when a task involves destructive actions, credentials, production systems, external side effects, legal/security risk, ambiguous instructions, failed validation, or unresolved conflict.

Split complex work across agents, branches, or git worktrees with clean boundaries, dependencies, merge order, and review gates. Use when the user asks to run agents in parallel, coordinate a sprint, divide a large implementation, use worktrees, or prevent parallel agents from clobbering each other.

Design reviewer order, approval gates, and separation-of-duties rules for agent-generated work. Use when the user asks who should review an implementation, how to set up multi-agent review, when human approval is required, or how to keep coding, security, QA, architecture, and release checks distinct.

create architecture decision records for meaningful technical decisions, tradeoffs, standards, dependency choices, interface boundaries, data ownership, plugin structure, or agent governance. use when a decision should be durable, explainable, reviewable, or preserved for future contributors and agents.

review software architecture, plugin architecture, service boundaries, repository structure, technical plans, or proposed refactors for correctness, maintainability, scalability, and risk. use when a user asks whether a design is sound, when agents need a system-level review before implementation, or when major changes could create coupling, data, security, or operational risks.

create concise technical design documents for features, services, plugins, agents, integrations, migrations, or refactors. use when a user needs a build-ready design, implementation plan, decision context, assumptions, risks, alternatives, rollout plan, or reviewable architecture proposal before coding.