AnnualReports
Aggregate several hundred cybersecurity annual reports from CrowdStrike, Mandiant, IBM, Verizon, Microsoft, CISA, OWASP, Wiz,…
macOS performance diagnostics via a read-only CLI: CPU/GPU/memory hogs, throttling, swap, disk. USE WHEN mac slow, system slow, what's slowing down my mac, computer is slow, what's eating CPU, CPU usage, GPU usage, what's using the GPU, memory pressure, RAM usage, swap, runaway
Claude Code
$ npx -y skills add danielmiessler/lifeos --skill Vitals --agent claude-code
Codex
$ npx skills add danielmiessler/lifeos --skill Vitals -a codex -y
Cursor
$ npx skills add danielmiessler/lifeos --skill Vitals -a cursor -y
Gemini CLI
$ npx skills add danielmiessler/lifeos --skill Vitals -a gemini-cli -y
GitHub Copilot
$ npx skills add danielmiessler/lifeos --skill Vitals -a github-copilot -y
OpenCode
$ npx skills add danielmiessler/lifeos --skill Vitals -a opencode -y
Windsurf
$ npx skills add danielmiessler/lifeos --skill Vitals -a windsurf -y
name: Vitals
evals:
manual:
reason: "a live performance diagnosis must be checked against the actual Mac state and the reported symptom"
falsifier: "the reviewer finds a reported bottleneck absent from collected evidence or a diagnosis that does not address the supplied symptom"
metadata:
short-description: "Diagnose macOS CPU, GPU, memory, energy, thermal, disk, and startup pressure through read-only tools. Excludes network and deployed-site diagnostics."
version: 1.1.1
description: "macOS performance diagnostics via a read-only CLI: CPU/GPU/memory hogs, throttling, swap, disk. USE WHEN mac slow, system slow, what's slowing down my mac, computer is slow, what's eating CPU, CPU usage, GPU usage, what's using the GPU, memory pressure, RAM usage, swap, runaway process, fans loud, mac running hot, thermal throttling, system health, check my mac, how's my system running, top processes, energy hogs, activity monitor, startup items, launch agents load, system taxed. NOT FOR network/wifi, deployed-app health, or security scanning."Read-only macOS performance inspection: a deterministic CLI gathers the numbers, `Interpretation.md` turns them into a diagnosis instead of a data dump.
The tool is read-only by contract: it never kills, renices, unloads, or writes system state. Remediation is recommended to the operator, never executed by the skill.
The CLI is `bun ~/.claude/skills/Vitals/Tools/Vitals.ts <subcommand>`, with subcommands `check` (fast snapshot, under 1s), `hogs` (live per-process CPU/energy, ~3s), `gpu`, `memory`, `disk`, `thermal`, `startup` and `full` (everything, ~4s), plus the flags `--json` and `--top N`. Each intent's Tool contract names the calls it uses.
| Intent | Trigger | File | |--------|---------|------| | **HealthCheck** | "how's my system", "check my mac", "system health" | `Intents/HealthCheck.md` | | **FindCulprit** | "mac is slow", "what's eating CPU/GPU/memory", "fans loud" | `Intents/FindCulprit.md` | | **DeepDiagnosis** | "full diagnosis", "deep check", chronic/recurring slowness | `Intents/DeepDiagnosis.md` |
| File | Read when | |------|-----------| | `Interpretation.md` | any intent: thresholds, known-process table, diagnosis shape |
User customizations at `<configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Vitals/` (`configRoot` is `$CLAUDE_CONFIG_DIR` when set, else `~/.claude`) override the defaults when that directory exists.
Provenance for the first four: live probes during the 2026-08-13 build.
**Example 1: Something feels slow**
User: "My Mac is dragging, what's going on?" → FindCulprit intent → A named culprit with two evidence classes and a recommended action awaiting approval
**Example 2: Routine check**
User: "How's my system doing?" → HealthCheck intent → A one-screen 🟢/🟡/🔴 verdict with per-subsystem lines, abnormalities flagged against thresholds
**Example 3: Fans blasting**
User: "Why are my fans so loud?" → FindCulprit intent → When `kernel_task` tops the list, the report names the thermal cause behind the cooling response, not the process
⛰️ LifeOS — The universal AI Harness designed to move you from Current to Ideal state in both life and work.
Aggregate several hundred cybersecurity annual reports from CrowdStrike, Mandiant, IBM, Verizon, Microsoft, CISA, OWASP, Wiz,…
3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis —…
Curated aphorism collection with CRUD: content-based matching, themed search, thinker research, and usage tracking to avoid…
Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses…
Static visual content in 20+ formats (diagrams, infographics, comics, icons, wallpaper) via Nano Banana Pro by default, Nano…
Directs visual quality across images, films, slides, and site captures through a direction council, two vendors' vision judgments…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…