- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add michael-denyer/pstack-claude --skill benchmark-checklist -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add michael-denyer/pstack-claude --skill benchmark-checklist -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add michael-denyer/pstack-claude --skill benchmark-checklist -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add michael-denyer/pstack-claude --skill benchmark-checklist -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/benchmark-checklist來自發布者
Use this when you produce a performance number: a PR's before and after, a regression claim, a hillclimb harness, or a library or config choice. Answer each question with evidence from a run, not a guess about the code.
For a quick ballpark the user asked for, one run is enough. Still check questions 4 and 7, and say that it is one run. Skip the rest unless that run looks wrong. A choice between options is never a ballpark.
uptime and the core count with nproc. If the machine is busy, find out what is running. If you cannot stop it, interleave the sides so both see the same noise, and say so in the report.top, pidstat), a runtime profiler (node --cpu-prof, py-spy, perf), I/O wait, and syscall counts (strace -c on Linux), then map the hot spot to source. Watch the load generator too: if it saturates first, you measured the load generator. If a change did not move the number, the limiter explains why, so find it before you call the change useless.Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or re
---name: benchmark-checklistdescription: Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work…---# plugins/pstack/skills/benchmark-checklist/SKILL.md總覽
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
常見問題
從發布者下載 plugins/pstack/skills/benchmark-checklist/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/michael-denyer/pstack-claude。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。