MCP App StoreMCP App StorePerformance Benchmark captures page performance metrics (TTFB, FCP, LCP, DOM timings, resource sizes), stores baselines, compares current runs against baselines, and generates regression reports with actionable recommendations. It supports per-page audits, diff-based runs for PRs, trend analysis, and performance budgets.
Use this skill when you want to: capture a baseline before a large change, validate that a PR doesn't regress Core Web Vitals, run quick timing checks, or produce trend reports across historical runs. Common triggers include manual audits, CI checks on PRs, and periodic performance monitoring.
Likely compatible with Claude Code / browse daemon based agents and CLI-driven automation (benchmarks rely on the browse daemon and shell tools).
Performance regression detection skill for the gstack ecosystem. Uses a browse daemon to collect Core Web Vitals, TTFB, bundle sizes, and resource timing from live pages, then compares against saved baselines. Well-documented 9-phase workflow with concrete metric collection commands and clear regression thresholds. However, it's a .tmpl template with unresolved placeholders ({{PREAMBLE}}, {{BROWSE_SETUP}}) and depends entirely on the gstack browse daemon ($B) and gstack-slug binary, making it unusable outside that ecosystem.
gstack browse daemon ($B)gstack-slug binary (~/.claude/skills/gstack/bin/gstack-slug)Solid conceptual design for performance benchmarking. The template approach limits portability. No security concerns beyond mild shell eval risk from gstack-slug binary.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
GraphQL Inspector — Validate
Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Blender Build-Go (bgo)
Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail