claude

vc-test

PREVIEW — one testing flow per ticket: /vc-test:ticket-context (one gated context bundle, read from Jira or Azure Boards and GitHub or Azure Repos through vc-init's $VC_RUN bridge, or through the host's MCP servers on a host-governed project), /vc-test:qa-test-strategy (floors, gate, an independent verifier), then scenarios that hunt significant bugs, approved at one human point, one agent each, costed per step. /vc-test:init for its own settings. Depends on vc-init and vc-fix. /vc-test:qa-triage-results runs from the plugin; investigation is vc-fix:qa-investigate. /vc-test:qa-design and the ui-ux-expert agent run the visual lane on a Playwright lane the run leaves free.

2 on GitHubby Virto Commercev0.15.0SEE LICENSE IN LICENSEupdated 2 days ago
/

Plugin vc-test from marketplace ai-tools in VirtoCommerce/ai-tools. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (4)

  • qa-design

    [Testing] Design system consistency & UX heuristics: live-token audit, BL-UI invariants, Nielsen's 10, Claude Design spec verification.

  • qa-test-strategy

    [QA Method] Use when a ticket's context is gathered and nothing has been tested yet, to choose how it is tested — risks, technique and oracle per risk, which artifacts run, entry/exit criteria — before paying for a run. Writes {RUN_DIR}/test-strategy.md (the ticket's run folder), one section per rou

  • qa-triage-results

    [QA Methodology] Triage a completed regression run's non-passing cases (FAIL / BLOCKED / SKIPPED) — or, with `ticket <KEY>`, the non-passing rows of a /qa-test or /qa-test-fast testing-checklist.md (checklist, exploratory and visual findings): collect each + its evidence (trace, screenshots, console

  • ticket-context

    One gated context bundle for one tracker ticket: the ticket's own fields (summary, type, status, priority, components, description, AC-field text), ACs with provenance, comment signals, epic and siblings, every attachment, inline image and link analysed (HAR and logs scrubbed first), design conditio

Slash commands (2)

  • /vc-test:init

    [Setup] Onboard vc-test onto a deployment — after vc-init's /project-init, declare which environments a run may write to and where the project's knowledge store is (the profile's `test` block, through vc-init's writer), and check every test environment has an admin and a storefront account. Never as

  • /vc-test:qa-ticket

    [Testing] PROTOTYPE vc-test — one feature-test ticket by scenarios: context → change map → approved scenarios, one agent each, beside the background AC run → triage → verdict, costed.

Subagents (7)

  • change-map

    Layer 0 of /vc-test:qa-ticket: reads the /vc-test:ticket-context bundle (and the domain's mind map and data model when they exist) and returns the ticket's change map as ONE JSON object — every AC as IMPLEMENTED or NO CODE with its sources, the hidden code no AC asks for, one hotspot per bundle hots

  • checklist-writer

    Writes the thin testing-checklist.md of /vc-test:qa-ticket: one row per AC (and per unit/api suspicion) for the background AC run, the Ref/Data/oracle rules of the qa-checklist skill, an empty scenario-results table at the end. Reads the approved strategy and the change map; runs no check and writes

  • fetch

    Host-governed fetch for /vc-test:ticket-context (vc-test spec U23, B9). On a project whose tracker and code host are reachable only through the host plugin's MCP servers, it answers one pass of prepare's needs-fetch: for each request in requests.json it calls the read tool of the server the request'

  • strategy-verifier

    Independent, read-only gate check for /vc-test:qa-test-strategy. Dispatched fresh when a strategy holds a Critical risk, before the user is asked to approve it: re-derives every clause of the skill's §Gate from the bundle and the strategy file (the deterministic command first, then the model-owned h

  • ticket-context-analyst

    Read-only ticket context extractor for /vc-test:ticket-context. Reads only the files the skill already fetched and scrubbed (its mode's analyst-<mode>.json and the paths in it). Three modes — TICKET (ACs, comment signals, epic/siblings, guesses), MATERIALS (attachments, inline images, linked pages a

  • ui-ux-expert

    UI/UX auditor for a web storefront or component library: accessibility (WCAG 2.2 AA, axe-core), design-system and design-spec conformance, layout stability, responsive behaviour, and usability tested as a real user doing a task (can they finish it, at what cost), on the Playwright lane its brief nam

  • verdict-writer

    Writes verdict.md and verdict.json of /vc-test:qa-ticket from the run's result files: the strategy, the checklist with its results, the change map, the trace reconciliation, the write-zone check, the triage report and the run cost. Tests nothing and re-opens no page. No shell, no network, no browser

View source on GitHub

More from VirtoCommerce/ai-tools

All 6 plugins →

vc-fix

claude

Bug lifecycle for Virto Commerce QA — bug filing, autonomous fixing, fix verification, online bug monitoring, self-diagnostics (/vc-self-check), and one renderer for every result comment and report page (/vc-fix:qa-report). Onboarding comes from vc-init (installed with it). Self-contained plugin (10 agents, 16 skills, 7 commands).

16 skills · 7 commands · 10 agents · hooks

2

vc-perf

claude

Three-layer performance loop — BenchmarkDotNet A/B (L1), k6 load harness (L2), dotnet-trace allocation/CPU/DB attribution (L3), machine-readable perf-verdict, optimization PRs. Depends on vc-init (onboarding, profile) and vc-fix (routing, backend dev/review agents). Advisory only.

4 skills · 5 commands · 1 agent

2

vc-secrets

claudecodex

Runs a declared process with its secrets resolved at launch, so no plaintext token sits in an MCP config, a settings env block or a .env file.

3 skills · hooks

2

Skills for the Virto Commerce storefront (vc-frontend): keep a theme fork up to date with upstream, and add a storefront plugin to a backend module. Can make mistakes: review every change before merging.

3 skills

2

vc-init

claude

Onboarding for the Virto Commerce QA plugins — /project-init, the only writer of project-profile.json. Every token it and its dependents need (GitHub, Azure DevOps, Jira) is kept in vc-secrets and reaches a process only through the $VC_RUN bridge, so none sits in a project file. Depends on vc-secrets; Installs on its own; every Virto plugin that reads the profile depends on it.

1 skill · 1 command · hooks

2

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

Install the "AAS QA & Test Automation" workflow plugin from Agentic Awesome Skills.

14 skills

sickn33/agentic-awesome-skills 49,620

Maintain vc-test?

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 plugins6 plugins