Skip to content
UsecaseBoard
← All use cases
xdevtools

FlowReel: Playwright E2E flows become narrated product demos

At a glance

Confidee/flowreel (Apache-2.0 Claude Code plugin) turns deterministic Playwright flows into captioned, narrated demo videos with a dev-then-staging release gate—assertions decide pass/fail; Claude writes/explains flows but does not judge them. This workflow is listed under devtools, demo-as-code, testing, claude-code-plugin, learnable-paradigm.

Agents / tools
FlowReel, Claude Code, Playwright

Building a tool for these workflows? Sponsor / inquire.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

`/plugin marketplace add Confidee/flowreel` then `/flowreel:run <flow>` so one Playwright path is both release gate and narrated demo.
Explore all →
hnmcp

mcp-router: search+lazy MCP proxy that actually cut tokens

Open-source mcp-router sits between Claude Code and many MCP servers: find_tools / call_tool / run_script stand in for hundreds of tools; on a 441-tool fleet vs six other proxies it finished 6/6 tasks at −29% tokens while peers often used more tokens or failed—Show HN + public BENCHMARK.md.

mcp-routerClaude CodeMCP
Source ↗
githubmulti-agent

Squadra: source-bound proof for multi-window coding agents

MIT-local Python skill/CLI/dashboard coordinates Claude Code, Codex, and Cursor on one project: shared registry, ack-before-work, prove bound to file fingerprints, independent (non-author) review, and cross-provider usage/balance so green tests on the wrong code cannot close a task.

SquadraClaude CodeCodex+2
Source ↗
blogmcp

GitLab MCP server generally available in 19.5

GitLab 19.5 makes the MCP server GA on Free/Premium/Ultimate: Claude Code, Cursor, Codex and other MCP clients get consolidated tools (get_merge_request, get_pipeline) plus Duo Agent Platform flow handoff under existing GitLab permissions, with GitLab.com rate limits of 60/min Free and 600/min paid.

GitLab MCPClaude CodeCursor+3
Source ↗
blogMCP

Functionize MCP: Studio app context for coding-agent tests

Functionize ships an MCP server so Claude Code/Cursor/Copilot hand change context to Studio, which builds/runs smoke or regression suites against the live app and returns the first failing step in-chat—closing the gap where agents never saw the product run.

Functionize MCPFunctionize StudioClaude Code+2
Source ↗