MCP App StoreMCP App Store
from OStack SaaS105
Automated performance benchmarking and regression detection: captures baselines, measures Core Web Vitals, and compares metrics across PRs to flag regressions.
This skill provides an automated performance engineering workflow. It captures baseline metrics (TTFB, FCP, LCP, JS/CSS bundle sizes, request counts), runs targeted audits (via a browse daemon), and compares before/after metrics to detect regressions on pull requests. It generates human-readable reports and recommendations for slow resources and remediation steps.
Use this skill as part of CI or code review when you want to ensure changes don't degrade page performance — for PR checks, trend analysis, or ad-hoc audits. Trigger with commands like /benchmark <url> or when reviewing PRs that touch frontend assets.
Designed for use with agent environments that can run shell snippets and the browse daemon (ostack/Claude Code contexts). Ideal for engineering-focused agents with access to repo and CI tools.
A performance regression detection skill that uses the ostack browse daemon to measure Core Web Vitals, capture baselines, and compare metrics across PRs. Well-structured 9-phase workflow with clear output formats and regression thresholds. No bundled scripts to test. The ostack framework preamble contains serious security anti-patterns including curl|bash installation, shell eval of script output, and auto-update mechanisms without confirmation.
Not malicious — the skill's core function (performance measurement) is entirely read-only and benign. However, the ostack framework preamble contains multiple security anti-patterns: curl|bash for bun install (-35), source of script output (-8), eval of script output (-8), and auto-update without confirmation (-18). The actual benchmark instructions (Phases 1-9) are well-designed, comprehensive, and safe. Security score reflects the preamble risks which would execute in any session using this skill.
Post-Deploy Canary Monitor
Automated production monitoring that uses visual snapshots and performance metrics to detect regressions immediately after deployment.
/setup-deploy — Deployment Configuration
Detect and configure deployment platform and health checks for a project (Fly, Render, Vercel, Netlify, Heroku, custom) and persist settings to CLAUDE.md for au
Chief Security Officer (CSO) Audit
Comprehensive security audit agent that performs OWASP Top 10 analysis, STRIDE threat modeling, and attack surface mapping.
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.
Clerk Vue Patterns
Vue 3 integration patterns for Clerk: composables, router guards, and Pinia auth store integration.
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.