chrome-devtools-mcp
claudeReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Author, run and debug ContextQA test cases from your agent. Bundles thirteen skills and wires up the hosted ContextQA MCP server.
Plugin contextqa from marketplace contextqa in indivatools/contextqa-skills. Commands read from the repo's manifest — 1 month ago.
contextqaDrive ContextQA from any coding agent: author test cases that actually run, manage environments and test data, group cases into suites, execute them as test plans, read real verdicts and evidence, and wire the results back into pull requests and tickets. Use when the task involves end-to-end or API
cqa-authorUse when the goal is to author new ContextQA test cases from a source — a Linear/Jira/GitHub ticket, a Swagger/OpenAPI spec, a Figma file, a video, an Excel sheet, an n8n workflow, a code diff, or free-text requirements. Fetch the source, pick the generation path, review the plan at a gate, then cre
cqa-bug-hunterUse when the goal is to find as many bugs as possible in a deployed UI by generating adversarial, negative and edge-case ContextQA tests at scale. Recons the surface, brainstorms hypotheses per element, generates cases against a shared login fixture, executes, triages and reports by severity. Built
cqa-bug-reproUse when a bug ticket should become a running reproduction — either on demand from a pasted or fetched ticket, or automatically from Linear, Jira or Slack when a label, command or reaction fires. Covers the trigger rules and settings, the production-write approval gate, what gets posted back on the
cqa-debugUse when a ContextQA test case or execution has failed and needs diagnosing and fixing. Inputs can be a `result_id`, a `test_case_id` whose latest run failed, a plan `execution_id` with failures, or a bug ticket that needs reproducing first. Gathers telemetry in parallel, separates a product bug fro
cqa-environmentsUse when setting up or fixing ContextQA environments, base URLs, secrets, global variables or test-data profiles — or when a case needs to run against Dev, Staging and Prod without being rewritten. Covers the `*|var|` / `${var}` / `{{var}}` / bare-column token grammar, the read-only vs read-write to
cqa-impactUse when given a ticket, a PR, or a branch and the goal is to find which existing ContextQA test cases the change affects and which coverage is missing — then update, create or rerun those cases. Combines the platform's own analysis with the model's own pass over case steps and the caller graph, and
cqa-initUse FIRST in any ContextQA session — confirms the MCP is connected and authenticated, names the org, user and active workspace, and reports a ready/not-ready verdict with the exact next step. Detects the agent (Claude Code / Codex / Cursor / Antigravity / Claude Desktop) and points at the right conf
cqa-integrationsUse when connecting ContextQA to GitHub, GitLab, Slack, Linear or Jira, diagnosing a connection that says "connected" but does nothing, or choosing where Slack notifications land. Covers the one-click handoff, how to tell a one-click row from a legacy token row, what `connection_status` means, and w
cqa-locatorsUse when authoring or repairing ContextQA test steps against a UI whose locators are known or discoverable — an existing case, a saved element, a page you can open in a browser, or an AI bootstrap you convert. Produces typed NLP steps (navigate / enter / click / verify) with real `pwLocator` sets an
cqa-regressionUse when the goal is to run a ContextQA test plan as a regression, wait for it, and triage the failures in parallel. Inputs are a test plan id, a plan name to look up, or a freeform "run the regression" intent. Clusters failures by shared cause, dispatches read-only triage, and hands confirmed bugs
cqa-suites-and-plansUse when organising ContextQA test cases into suites and building the test plans that actually run them — picking browsers or devices, binding an environment, setting timeouts and parallelism, wiring email notifications, and executing or re-running. Also covers folders, tags and modules for keeping
cqa-tunnelUse when the app under test is not reachable from the internet — it runs on localhost, a build agent, a VM or inside a corporate network — and ContextQA's runners need to reach it. Publishes a local service as a public HTTPS URL with the ContextQA tunnel agent, wires that URL into a ContextQA enviro
contextqaconnects to: https://mcp.contextqa.com/mcp
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo
4 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
1 skill
PRD generation and conversion skills for the Ralph autonomous agent loop
2 skills
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.