ux-spec-process
claude8-phase, gated UX specification pipeline for DoD/defense collaboration features — orchestrator + phase agents + composable skills, from problem brain-dump to publish-ready spec
26 skills · 12 commands · 8 agents · hooks
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
Plugin prfaq-prototype from marketplace mattermost-ai-marketplace in mattermost/mattermost-ai-marketplace. Commands read from the repo's manifest — 17 days ago.
Artifact FrontmatterEmits 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
Clarification ProtocolReusable 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-
Feedback SynthesizerCategorizes raw stakeholder feedback into actionable priority tiers with suggested fixes for gate decisions
Playground BootstrapPre-flight for /prfaq-prototype. Makes sure the active target playground exists inside the workspace. If it's missing and the target profile names a repo, prompts the user to clone a fresh copy (plus any companion repos it needs) and install dependencies; if it exists, verifies it's the expected rep
PRFAQ ParserNormalizes an arbitrary Mattermost PRFAQ markdown file (T3-aware) into a structured, format-independent PRFAQ extract — feature intent, tier, actors, named surfaces, capabilities/actions, behavioral rules, verbatim UI copy, scope, open design questions, dependencies — reconciling in-document contrad
PRFAQ Source ResolverStep 0 of /prfaq-prototype. Turns whatever the user shared — a local file, a GitHub link, a Google Doc, a Confluence page, a Mattermost thread, or any other doc link — into a local markdown source under PRFAQs/ that the prfaq-parser can read. Routes each link to a matching connected tool, prompts th
Sandbox ComposerTarget-profile-driven component composition. Enumerates the active playground's real component library at runtime, reads each component's props before use, and fills scaffolded scene files with typed JSX, defense-realistic demo data, and any verbatim PRFAQ copy — flagging gaps instead of inventing p
Sandbox ScaffolderTarget-profile-driven scaffolding for a multi-scene, multi-option prototype into the active playground defined in ${CLAUDE_PLUGIN_ROOT}/config/prototype-targets.json. Reads the target's real conventions at runtime (folder layout, manifest shape, scene API), checks for collisions/reuse, and creates t
Scene MapperTurns a PRFAQ extract into a ranked screen/scene inventory, a set of genuine option-divergence axes for multi-option prototyping, an assumptions ledger, and a rough scene→component feasibility map against the active target playground. Feeds the prfaq-analyst clarification round and the prototype-bui
Walkthrough BuilderBuilds a stakeholder guided-tour over live sandbox prototypes — rail, plain-language copy, and per-step iframe deep-links. Use after a prototype exists when the user asks for a walkthrough, guided tour, click-through, or stakeholder explanation of a feature.
/prfaq-prototype:prototypeFast-path — turn a PRFAQ into shareable, multi-option interactive prototypes for faster alignment
persona-criticCustomer persona simulation agent. Loads a bundled FY26 persona from the plugin's personas catalog and critiques a design artifact or PRFAQ in character (first-person). Invoked by the /prfaq-prototype:prototype persona-review step, or directly with a persona slug + artifact path.
prfaq-analystFast-path Stage 1 specialist. Converts an arbitrary PRFAQ (T3-aware) into a prototype brief — structured extract + ranked scene inventory + genuine multi-option divergence axes + an assumptions ledger — then surfaces a single clarification round (surface-and-pause) so the human sets scope, options,
prototype-builderFast-path Stage 2 specialist. Takes the prfaq-analyst's brief + scene plan + resolved clarifications and builds the chosen design options (one prototype, option-switchable scenes) into the active playground from ${CLAUDE_PLUGIN_ROOT}/config/prototype-targets.json, composing from the real component l
8-phase, gated UX specification pipeline for DoD/defense collaboration features — orchestrator + phase agents + composable skills, from problem brain-dump to publish-ready spec
26 skills · 12 commands · 8 agents · hooks
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
Skills for common development workflows — dependency management, module hygiene, and routine maintenance tasks
3 skills
Skills for developing Mattermost plugins
3 skills
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
Audit and improve CLAUDE.md files in repositories — scans, scores quality, and makes targeted updates
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
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.