voltagent-qa-sec
claudeTesting, security, and code quality experts - code review, penetration testing, QA automation
Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
Plugin stuntdouble from marketplace stuntdouble in stunt-double/stuntdouble-mcp. Commands read from the repo's manifest — 8 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.
check-agent-readinessCheck how well AI agents can find, understand and act on a website using the Stunt Double Index (agent readiness, AI visibility, checkout or support by agents), explain the score from real sessions, compare with peers, and re-score after fixes.
check-brandAudit a product or site against brand and tone-of-voice guidelines, with an actor reading every in-scope page like a customer and flagging copy, voice and presentation that break the rules, with evidence.
check-complianceCheck a product against legal and compliance requirements (cookie consent, privacy and terms access, required disclosures, claim substantiation, unsubscribe flows) and collect evidence for counsel to review.
check-continuityCheck continuity across surfaces (pricing, plan names, terminology, feature names, promises) between marketing site, product, docs and emails, with actors walking each surface and mismatches reported with evidence.
check-design-systemAudit a live product against its design system (typography, colour, spacing, components, iconography) on rendered pages with evidence, and re-check automatically when the Figma library publishes.
cloudPush a Stunt Double Studio checklist and its actor to a Stunt Double workspace with /stuntdouble:cloud <checklist>, run it there with an independent judge, write the cloud ids back and pull the run in beside local ones.
create-actor-panelCreate and configure Stunt Double actors (AI personas) with system prompts and knowledge entries, to cover user segments such as first-time users, enterprise admins or accessibility users.
design-reviewRun a design review of a proposed design, flow, prototype or live URL by interviewing several Stunt Double actors and synthesising themes, friction and recommendations.
doctorCheck that Stunt Double Studio can run locally with /stuntdouble:doctor: Node, Chrome, the viewer port and how local runs are billed.
maintain-automationsChange an existing Stunt Double workflow or checklist without losing run history: retime triggers, edit and rewire steps, build condition branches, update checks in place, pause or retire.
openOpen the Stunt Double Studio viewer with /stuntdouble:open: every local and cloud run in .stuntdouble/ with its verdicts, screenshots and activity.
run-qa-suiteRun every Stunt Double workflow and checklist in a workspace and produce a GO, CONDITIONAL or NO-GO release-readiness report.
run-user-interviewPlan, configure and launch a structured user interview with AI participants against a live URL on Stunt Double, then read the synthesised report (summary, themes, recommendations).
run-ux-validationValidate a user journey before merge or release by running Stunt Double workflows and checklists and reporting pass or fail with failure detail.
runRun a Stunt Double Studio checklist in a local Chrome with /stuntdouble:run <checklist> [resume]: an actor goes through localhost, staging or production, and the result comes back with each failed check's evidence and a viewer link.
setup-guardrailsSet up continuous guardrails on Stunt Double for critical flows (signup, checkout, sign-in): checklists plus a workflow that re-runs them on a schedule or on deploy and PR events.
setupSet up Stunt Double Studio in this project in one pass with /stuntdouble:setup: find the dev server, draft an actor and checklists from the app's routes, and add the CLAUDE.md notes, tool permission and session hooks, each change shown before it is written.
triage-feedbackReview, categorise and manage Stunt Double feedback submissions (new items, severity, status, patterns) across projects.
verify-changeVerify a code change on a preview, staging or production URL by running a Stunt Double actor through the affected flows, and optionally post the results on the pull request.
design-reviewerFacilitate design reviews and co-creation sessions using Stunt Double actors, interviewing personas about a prototype, preview or live design.
feedback-triagerTriage, prioritise and manage Stunt Double feedback to drive UX improvements, from new submissions through to resolved.
product-researcherGather user insights and validate product hypotheses using Stunt Double actors, interviews and feedback, from concept exploration to journey mapping.
qa-engineerRun and monitor Stunt Double checklists and workflows for QA validation of user-facing features, triage failures and verify fixes.
stuntdouble-actorThe actor in a local Stunt Double run. Goes through a product in a local Chrome as the persona in a start_run brief, judges each check with evidence and finishes the run. Dispatched by /stuntdouble:run with the start_run output as its prompt.
ux-friction-reviewerReview code changes for potential UX friction using Stunt Double personas, workflows and feedback.
stuntdoubleconnects to: https://app.stuntdouble.io/api/mcp
localruns: npx -y [email protected] mcp
node "${CLAUDE_PLUGIN_ROOT}/hooks/stuntdouble-hooks.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/stuntdouble-hooks.mjs"
Testing, security, and code quality experts - code review, penetration testing, QA automation
Reuse tested app journeys with code, design and integration checks.
3 skills
FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready. 16 prebuilt masters across 印度/汉传/藏传/南传 plus compare, debate, curriculum and help teaching modes and the create-master generator.
21 skills · hooks
A design-foundations system with a four-stage workflow (research → plan → mock → build). Design doctrine is loaded deterministically by Read() via a name→path resolver — six domains (content-design, behavioral, journey, deceptive-patterns, design-systems, ai-native) live as reference files in references/; two de-triggered skills (usability, data-viz) and two workflow skills (clarify, prototype) complete the plugin. The design-DNA pipeline grounds every candidate in two named references, then deals a seeded layout-first composition (scripts/dealer.mjs) — any axis user-pinnable — ahead of a criteria-bound critique and synthesis pass. Commands take any design idea from brief to viewable, gated artifact: research, plan, mock (sign-off gate), build (per-phase BUILD → REVIEW → commit). Review is dual-blind: an isolated cross-pillar critique and a deterministic detector (scripts/detect.mjs) gather findings independently and synthesize only after both finish.
4 skills · 4 commands · 2 agents
Optimize software performance through user-journey baselines, profiling, representative benchmarks, controlled experiments, and field verification. Use when asked to make an application, service, workflow, or hot path faster or more efficient, or to build the measurement loop first. Do not use for a reliability incident, capacity forecast, generic product A/B test, or operating a named telemetry or load-testing tool without an optimization objective.
194 skills
ユーザージャーニーマップを6つの専門エージェントチームで作成するスキル。認知から推薦まで5フェーズで行動・思考・感情・接点・機能・課題・機会・Devアクションを構造化しMarkdownとPencil(.pen)ビジュアルで出力する
1 skill · 6 agents
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.