- 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 pedrohcgs/claude-code-my-workflow --skill diagnose -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 pedrohcgs/claude-code-my-workflow --skill diagnose -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 pedrohcgs/claude-code-my-workflow --skill diagnose -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 pedrohcgs/claude-code-my-workflow --skill diagnose -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/pedrohcgs/claude-code-my-workflow/tree/HEAD/.agents/skills/diagnose來自發布者
This skill's instructions live in .claude/skills/diagnose/SKILL.md.
Read that file now and follow it, with the files it points to. Read AGENTS.md
first if you have not already.
It was written for Claude Code. Running it from Codex, Antigravity or another agent:
$ARGUMENTS, use what the user asked for..claude/agents/ (through the
Agent or Task tool), do that step where it appears in the procedure: never later, and never
skip it. A step that gates what follows still gates it (/commit runs its verifier before it
commits). Read the agent's file for what the step checks./verify-claims for citations) before
relying on it.allowed-tools, model, effort, argument-hint and
disable-model-invocation in the source's frontmatter configure Claude Code. Ignore them.AGENTS.md
yourself; the git pre-commit gate and CI still apply to your commits.Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regressi
---name: diagnosedescription: Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise →…---# .agents/skills/diagnose/SKILL.md總覽
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate looks wrong", or "it worked yesterday". Tuned for research code (R/Stata/Python): type coercion, NA/merge blow-ups, factor levels, clustering/SE choices, weighting, collinearity/convergence, seeds, package-version drift. Use `--no-fix` to localize the root cause without editing shared or load-bearing files.
常見問題
從發布者下載 .agents/skills/diagnose/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/pedrohcgs/claude-code-my-workflow。
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。