AGENT SKILL

computer-specs

Profile the hardware of the machine you're running on — RAM, CPU(s), GPU(s), and free disk space — then describe it in plain natural language. Use whenever the user asks about their computer's specs or hardware — e.g. "what are my specs", "what's my hardware", "how much RAM / how many cores / what GPU do I have", "system profile", "spec out this machine", or "can my computer handle <workload>".

License 许可
Apache-2.0
最近更新
2026-07-23
Stars
★ 0
Forks
0

01 前言 Front Matter

name
computer-specs
description
Profile the hardware of the machine you're running on — RAM, CPU(s), GPU(s), and free disk space — then describe it in plain natural language. Use whenever the user asks about their computer's specs or hardware — e.g. "what are my specs", "what's my hardware", "how much RAM / how many cores / what GPU do I have", "system profile", "spec out this machine", or "can my computer handle <workload>".

02 资源文件 1

03 SKILL.md 正文

computer-specs

Report the running machine's hardware, in natural language.

How

  1. Run the bundled profiler: bash "${CLAUDE_PLUGIN_ROOT:-plugins/computer-specs}/specs.sh". It is cross-platform (macOS + Linux), read-only, and degrades gracefully — a field it can't determine comes back as unknown rather than failing. It prints a labeled block:
    OS:    <os / kernel / arch>
    CPU:   <model — cores/threads>
    RAM:   <total>
    GPU:   <chipset(s)>
    Disk:  root volume / — <total> total, <free> free
    
  2. Translate that block into a natural-language profile — don't just echo it back. Open with a one-line headline (e.g. "You're on a well-specced Apple Silicon Mac…"), then describe the RAM, CPU(s), GPU(s), and free disk in prose. If the user asked in the context of a workload ("can it handle X?"), answer that using the numbers.
  3. If a field is unknown (a tool wasn't available on this OS), say so plainly — never guess or invent a value.

Notes

  • Read-only. The script only queries hardware; it changes nothing.
  • Keep it conversational and brief — a profile, not a data dump.
  • Covers macOS and Linux; on any other OS it reports that plainly.

04 同仓库更多 Skills

SoftwareAssassin2
SoftwareAssassin2/Plugins

wendy

Summon Wendy, a performance coach modeled on Wendy Rhoades from Billions, when the user invokes /wendy or asks for Wendy by name, or explicitly asks to get his head right — tilting, stalling, spiraling, avoiding, flat, or needing to lock in before a hard push. Wendy works the operator's state, never the plan. Do NOT use for feedback on strategies, plans, or decisions, and do not trigger uninvited.

★ 0
SoftwareAssassin2
SoftwareAssassin2/Plugins

ubiquitous-language

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to ./docs/ubiquitous-language.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD". Forked from Matt Pocock's "ubiquitous-language" skill.

★ 0
SoftwareAssassin2
SoftwareAssassin2/Plugins

tdd

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development. Forked from Matt Pocock's "tdd" skill.

★ 0
SoftwareAssassin2
SoftwareAssassin2/Plugins

voice

Speak Claude's responses aloud through the native OS voice (macOS `say`) — on demand via /speak:speak (last response) or /speak:specify (pick one), or automatically on every response via a toggleable Stop hook. Works locally on a Mac and, through a manually started host listener, from inside a Dev Container. Use when the user wants responses read aloud / spoken / voice output, wants auto-speak turned on or off, or asks whether the speak install is healthy.

★ 0
SoftwareAssassin2
SoftwareAssassin2/Plugins

merge-request:review

Review a pull/merge request (by id) or batch-review every open one against Chris's own engineering standards, staging high-signal findings to .data/merge/<ID>.md for later posting. Fetches head SHAs and applies the "Reviewed at commit" skip check BEFORE any checkout, resolves the head fork-safely, builds/tests it in a dedicated worktree, and treats a failing build/checkout as the top blocking finding. First runs /detect-source-control and hard-stops when the forge is unsupported. Use as "review the PR", "review the open MRs", "any PRs need my eyes", "review <id>".

★ 0
SoftwareAssassin2
SoftwareAssassin2/Plugins

merge-request:post-findings

Take the findings staged by /merge-request:review in .data/merge/<ID>.md and, with per-finding approval, post the approved ones to the forge as inline comments (general-comment fallback when a finding has no valid diff location) — or formally sign off a clean PR/MR with a single "Looks good." First runs /detect-source-control and hard-stops when the forge is unsupported. Nothing reaches the forge except through the bundled scripts. Also runs a propose-then-confirm learned-preferences loop that teaches /merge-request:review what you value (Don't-raise / Wording / Confirmed-valued), and records skipped findings to the artifact's

★ 0