claude

Archetype

Test your product with synthetic personas. Run one persona through a flow in a real browser, or run a behavioral study: the plugin picks the behavioral factors that matter for your users (patience, trust, familiarity and more), generates an archetype per factor plus a baseline and a stress case, runs them in parallel isolated headless browsers with a video per run, and reports completion per archetype, which factor made people give up, with what confidence, and what to change.

0 on GitHubby Synthetic Archetypev0.6.0updated 2 days agotesting
/

Plugin archetype from marketplace archetype in MCxiaoguu/Archetype_Plugin. Commands read from the repo's manifest — 2 days ago.

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

What it installs

Skills (9)

  • check-run-status

    Check the status, progress, and results of an Archetype validation run by its run id. Use when the user asks about run status, validation progress, or the outcome of a specific run.

  • list-features

    List the user's saved Archetype features so they can pick one to validate. Use when the user wants to see which features are available for validation or asks to browse their Archetype features.

  • logout

    Log out of Archetype. Use for /archetype:logout or when the user wants to disconnect, sign out, switch accounts, or clear the plugin's saved credentials. Deletes the locally cached token via the core MCP server; run history is preserved.

  • persona

    Persona-pool dashboard and questionnaire-driven pool creation. Use for /archetype:persona — lists the user's persona pools (name, description, members, created) usable in validation runs; if none exist (or the user says new), walks them through a short questionnaire, previews candidate directions, a

  • setup

    Onboarding for the Archetype plugin. Use for /archetype:setup or whenever the user wants to connect, log in, re-authenticate, or get started with Archetype. Runs the device-flow login wizard via the core MCP server, then shows the status dashboard and suggests first steps.

  • status

    Show the Archetype connection dashboard — which account is connected, token health, backend reachability, saved-feature count, recent runs from this machine, and a quick link to the Archetype portal. Use for /archetype:status or when the user asks who is logged in, whether the plugin is connected, o

  • study

    Run a behavioral study with /archetype:study. Use when the user wants to know which kinds of users struggle with or abandon a flow, why, and what to change, rather than one validation run. Takes a goal, a url, who the users are (the ICP) and what counts as done; picks the behavioral factors that mat

  • validate-feature

    Feature-first entry into an Archetype validation run. Use when the user asks to validate, test, or run validation on a specific saved feature by name (e.g. "validate the signup feature"). Resolves the feature via list_features, then runs the same actor loop as the validation skill with the feature's

  • validation

    The core Archetype actor loop. Use for the /archetype:validation command. With no arguments, connects the session to Archetype (login wizard). With arguments, parses the natural language into one or MORE run objects (goal, url, pool, feature, preconditions) — comparison phrasing like "as <pool A> an

Subagents (2)

  • feature-validator-headless

    The Archetype validation actor on an isolated headless Playwright browser instead of Claude in Chrome. It is the actor for every study run (the dispatch prompt names its browser, one of the plugin servers archetype-browser-1 to -4, or archetype-watch-1 and -2 for headed runs) and for ad hoc runs whe

  • feature-validator

    Use this agent to run a full Archetype validation cycle for a headless / delegated orchestration — start a run, become the assigned persona, drive Chrome through each scenario, and report structured results back to the backend, all in one invocation. Examples: "Validate the signup flow at localhost:

MCP servers (7)

  • archetype-browser-1

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-browser-1

  • archetype-browser-2

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-browser-2

  • archetype-browser-3

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-browser-3

  • archetype-browser-4

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-browser-4

  • archetype-watch-1

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-watch-1 --headed

  • archetype-watch-2

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/browser-server.py archetype-watch-2 --headed

  • core

    runs: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/core-server.py

Hooks (5)

  • SessionStart

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session-hook.py"

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/action-hook.py"

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/action-hook.py"

  • PostToolUseFailure

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/action-hook.py"

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/permission-hook.py"

View source on GitHub syntheticarchetype.com

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

storybook

claudecodex

Build, preview, and test UI components with Storybook.

7 skills

storybookjs/storybook 91,552

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain Archetype?

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 pluginslisted