claude

ux-spec-process

8-phase, gated UX specification pipeline for DoD/defense collaboration features — orchestrator + phase agents + composable skills, from problem brain-dump to publish-ready spec

6 on GitHubby Abhijit Singhv1.0.0MITupdated 17 days agodesign
/

Plugin ux-spec-process from marketplace mattermost-ai-marketplace in mattermost/mattermost-ai-marketplace. Commands read from the repo's manifest — 17 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (26)

  • Artifact Frontmatter

    Emits the skimmable two-layer skim block at the TOP of every phase artifact — TL;DR, phase + complexity tier, what-changed-since-last-version, decisions locked (and which flipped from a Recommended default), open [VERIFY WITH PM] items, and a one-line reading guide. Goal — a reader answers what / ph

  • Assumption Extractor

    Identifies unstated assumptions in early-phase artifacts that could invalidate the design

  • Clarification Protocol

    Reusable contract for surfacing multiple-choice clarifying questions (with a recommended option) at phase intake and whenever in-phase ambiguity exceeds threshold. Defines question shape, threshold scoring, capture format, and bypass. Phase-specific question banks live in the calling agent. Surface-

  • Competitive Analyzer

    Analyzes how multiple platforms handle UX problems for classified/IL4+ environments, identifying gaps and differentiation opportunities.

  • Component Composer

    Selects and assembles components from the prototype's component library (enumerated at runtime) with correct props for a given screen description

  • Dedup

    The cite-don't-restate pass for every phase artifact. Before writing each section, check overlap with prior-phase artifacts; replace restatement of framing/context with a one-line citation block that quotes the key claim and links to the source; NEW content (this phase's decisions, requirements, fin

  • defense-ux-context

    Shared operating context for the 8-phase UX spec pipeline — the defense-UX persona, compliance scope, complexity tiers, interaction modes, gate enforcement, output rules, and prompt-injection policy. The orchestrator and every phase agent read this FIRST and treat it as TRUSTED. Replaces what used t

  • Design System Conflict Checker

    Verifies proposed UI elements (icons, components, color tokens, badge types, modal patterns) against existing system usage. Outputs a conflict table flagging proposed elements that overlap with existing semantic uses. Use before recommending any new UI element to prevent ambiguity in the shipped pro

  • Edge Case Hunter

    Adversarial review of completed UX specs to find missing states, contradictions, security gaps, and mobile coverage issues

  • Feedback Synthesizer

    Categorizes raw stakeholder feedback into actionable priority tiers with suggested fixes for gate decisions

  • Flow Auditor

    Reviews user flows for missing paths, security bypasses, and navigation deviations in DoD collaboration specs

  • flow-generator

    Drafts screen-level flow definitions from a selected solution direction

  • Interview Synthesizer

    Synthesizes raw user research notes into structured findings that feed the Problem Statement and PRD

  • Option Builder

    Creates multiple design option pages in the prototype following the repo's established multi-option pattern for stakeholder comparison and selection

  • Option Presenter

    Generates option comparison matrix, BLUF recommendation, and screenshot manifest for stakeholder decision-making

  • PRD Generator

    Generates a structured DoD-optimized Product Requirements Document from a problem statement and research brief.

  • Problem Sharpener

    Converts raw problem brain dumps into a BLUF-format problem statement optimized for DoD/defense context

  • Prototype Scaffolder

    Creates page file structure (TSX + SCSS module + manifest entry) in the sandbox mattermost-proto-playground project

  • Section Writer

    Writes concise, decision-focused UX spec sections for DoD collaboration platforms. Emphasizes behavior, outcomes, and non-obvious constraints over exhaustive element-by-element documentation.

  • Solution Scorer

    Evaluates multiple solution approaches using a multi-criteria matrix and produces a BLUF recommendation with risk analysis.

  • spec-updater

    Apply feedback-driven changes to a UX spec and update it in Confluence

  • Standards Mapper

    Identifies specific compliance controls relevant to a feature and maps them to UX design implications

  • State Matrix Builder

    Generates all 6 required UI state variants for a screen per Phase 6 gate checklist

  • Threat Modeler

    Reviews specifications for UI-layer security risks including data spillage paths, implicit trust, and misconfiguration vulnerabilities.

  • Traceability Checker

    Generates PRD-to-spec traceability matrix, identifying requirements gaps and scope creep

  • UX Copy Reviewer

    Catches AI-slop language patterns in UI copy and design proposals, then suggests rewrites. Specifically targets em-dashes connecting independent clauses, disclaimer-style colons, corporate verbs, redundant phrasing, and sentences trying to do too many jobs. Use before showing any user-facing copy to

Slash commands (12)

  • /ux-spec-process:discover

    Phase 1 — Discovery (Problem Statement)

  • /ux-spec-process:flow

    Phase 5 — generate flow definitions per carried-forward direction, then audit + feedback synthesis

  • /ux-spec-process:ideate

    Phase 4 — solution directions + scored evaluation matrix

  • /ux-spec-process:prd

    Phase 3 — PRD + threat model + pre-flight review

  • /ux-spec-process:prototype

    Phase 6 — build code prototype in proto-playground

  • /ux-spec-process:research

    Phase 2 — Research Brief (standards + competitive intel)

  • /ux-spec-process:spec-clean

    Reset a spec project to brain-dump-only (destructive, prompts confirmation)

  • /ux-spec-process:spec-init

    Bootstrap a new spec project (folder, state object, brain dump)

  • /ux-spec-process:spec-publish

    Phase 8 — publish spec to Confluence as DRAFT (requires explicit confirmation)

  • /ux-spec-process:spec-run

    Run the full spec pipeline (Phases 1–7) with a checkpoint after each phase

  • /ux-spec-process:spec-status

    Show current phase, gate status, and artifacts for a spec project

  • /ux-spec-process:spec

    Phase 7 — generate UX spec draft (local only, never writes to Confluence)

Subagents (8)

  • discovery-agent

    Phase 1 specialist. Converts raw problem brain dump into a structured, stakeholder-approved Problem Statement document. Applies problem-sharpening, interview synthesis, and assumption extraction. Invoke for Phase 1 of the UX spec process.

  • flow-agent

    Phase 5 specialist. Generates screen-level flow definitions per carried-forward solution direction (or accepts designer-provided flows), then adversarially audits each set for completeness, security gaps, navigation consistency. Synthesizes review feedback from stakeholders into actionable review pa

  • ideation-agent

    Phase 4 specialist. Generates 3-5 conceptually distinct solution approaches with scored evaluation matrix, BLUF recommendation, and top 3 risk mitigations. Invoke for Phase 4 of the UX spec process.

  • prd-agent

    Phase 3 specialist. Generates Product Requirements Document (PRD), runs security threat model, and executes pre-flight review. Flags all [VERIFY WITH PM] items prominently for human review. Invoke for Phase 3 of the UX spec process.

  • prototype-agent

    Phase 6 specialist. Builds one design-option prototype per carried-forward direction in the sandbox mattermost-proto-playground from approved Phase 5 flows and Phase 4 solution directions. Composes screens from the sandbox component library (enumerated at runtime), generates all required UI states,

  • research-agent

    Phase 2 specialist. Synthesizes compliance standards, regulatory controls, and competitive intelligence into a Research Brief. Operates two sub-agents: Standards Sub-agent (NIST/DoD lookups) and Competitive Intelligence Sub-agent. Invoke for Phase 2 of the UX spec process.

  • spec-orchestrator

    Master orchestrator for the 8-phase UX spec generation system. Manages phase state machine, delegates to specialist agents, enforces the two-stage clarification gate, blocks advancement until gates are approved, and maintains the spec state audit trail. Use this as the entry point for all new spec w

  • spec-writer-agent

    Phase 7 specialist. Generates a clear, concise UX specification using the template as a menu (not a checklist). Runs internal validation passes for edge cases and traceability. Produces a spec draft as the gate artifact.

Hooks (1)

  • PreToolUse

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/guard-spec-state.py

View source on GitHub

More from mattermost/mattermost-ai-marketplace

All 20 plugins →

Turn a PRFAQ into shareable, multi-option interactive prototypes for faster alignment — parse the PRFAQ, align on scope and options with the human, then build into a swappable sandbox playground on the app's real layouts

10 skills · 1 command · 3 agents

6

Internal Cursor automation commands for Mattermost engineering workflows. Intended to be invoked by Cursor Automations only — not for individual/manual use.

3 skills · 3 commands

6

Skills for common development workflows — dependency management, module hygiene, and routine maintenance tasks

3 skills

6

Adversarial security review using a paranoid finder and a critical validator over a PR, local diff, or file list, with full-coverage accounting, finder/validator context isolation, and a code-traced attack-example gate

1 skill · 2 agents

6

Audit and improve CLAUDE.md files in repositories — scans, scores quality, and makes targeted updates

1 skill

6

Similar plugins

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling

19 skills

anthropics/skills 193,780

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

1 command · 6 agents

anthropics/claude-code 155,476

Professional UI/UX design intelligence for AI coding assistants. Includes searchable databases of styles, colors, typography, charts, and UX guidelines for React, Next.js, Astro, Vue, Nuxt.js, Nuxt UI, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, and Three.js.

7 skills

nextlevelbuilder/ui-ux-pro-max-skill 148,759

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.

1 skill · 4 agents · hooks

pbakaus/impeccable 109,099

Maintain ux-spec-process?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins20 plugins