Pollymetric — AI skill for Claude Code
Your Mac's health at a glance, in the menu bar.
How to install Pollymetric
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open pouyanafisi/pollymetric and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Pollymetric does
Your Mac's health at a glance, in the menu bar. See what's slowing it down by name, catch problems that keep coming back, free up space safely, spot sneaky startup items, and have your AI agent explain and fix issues. Private, local, and light on battery.
Alternatives in AI
- Startup Canvas — Generate Startup Canvas combining Product Strategy and Business Model 7.8k ★
- OpenSpace — "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/ 7.5k ★
- J Space Cognition Suite V3.7 — J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r 3k ★
README
Pollymetric
Is your Mac OK, and is there anything you should do?
One glance at your menu bar tells you.
What it does for you
**Know at a glance whether your Mac is OK.** A score in your menu bar, and one line saying why it isn't perfect. It stays quietly gray while all is well and only turns amber or red when something needs you.
**See what's actually slowing it down.** Not "node" or a wall of cryptic process names: *"next dev in storefront, started by Claude Code in iTerm2."* Everything is grouped by the app that started it, so you know what to close.
**Catch the problem that keeps coming back.** Pollymetric remembers the last two weeks. Something that spikes for twenty seconds and vanishes is still on the record, and anything that keeps flaring up gets flagged, with how often and how much.

Related Skills
Lagless
A native macOS task manager for the age of AI agents: see every Claude Code session, Codex thread and MCP serv
Humanizer Workbench
Rewrite AI text into natural writing with a CLI and Claude Code skill that spot AI patterns, refine tone, and
Find Unknowns
Agent Skill: Unknowns SOP for AI coding agents — blind spot scan, prototype, interview, implementation notes,
Ours Fleet
Run a fleet of persistent, identity-bound AI agents across harnesses (Claude Code first, more coming). Declara
Burn O Meter
See what your AI coding agents really cost — tokens, spend, cache efficiency and rate limits. Works with Claud
Biomass Conversion Index Monitoring System
A strictly local Claude Code plugin that calculates your Harmony Deviation Index, and preserves the evidence f
Related Agents
Observability Adversary
Fresh-context, refute-framed review through the 3am operations loss function. Hunts errors swallowed where nob
Apple UI Designer
Visual and theme redesigns in current Apple design language (macOS 27 / iOS 26+ Liquid Glass, vibrancy, system
Shonda Rhimes Board
Use this agent for retention strategy, engagement hooks, narrative arcs, and 'what keeps people coming back' a