- 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 rohitg00/pro-workflow --skill llm-gate -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 rohitg00/pro-workflow --skill llm-gate -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 rohitg00/pro-workflow --skill llm-gate -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 rohitg00/pro-workflow --skill llm-gate -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/rohitg00/pro-workflow/tree/HEAD/skills/llm-gate來自發布者
Use Claude Code's type: "prompt" hooks to create intelligent quality gates that use AI to verify operations.
Use when:
Claude Code supports hooks with type: "prompt" that run a small LLM (Haiku by default) to verify conditions:
{
"PreToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "prompt",
"if": "Bash(git commit*)",
"prompt": "Check if this git commit follows conventional commit format (<type>(<scope>): <summary>). The commit command is: $ARGUMENTS. Return {\"ok\": true} if valid, {\"ok\": false, \"reason\": \"...\"} if not.",
"model": "haiku",
"timeout": 15
}]
}]
}
The hook:
$ARGUMENTS with the JSON hook input{"ok": true} or {"ok": false, "reason": "..."}{
"type": "prompt",
"if": "Bash(git commit*)",
"prompt": "Verify this git commit follows conventional commits: type(scope): summary. Types: feat,fix,refactor,test,docs,chore,perf,ci. Summary under 72 chars. Input: $ARGUMENTS",
"model": "haiku"
}
{
"type": "prompt",
"if": "Bash(rm *)",
"prompt": "Check if this rm command is safe. Flag if it uses -rf on important directories (src/, node_modules/, .git/). Input: $ARGUMENTS",
"model": "haiku"
}
{
"type": "prompt",
"matcher": "Write",
"prompt": "Check if this file write contains hardcoded API keys, secrets, passwords, or tokens. Input: $ARGUMENTS. Return ok:false if secrets found.",
"model": "haiku"
}
For complex verification, use type: "agent" (runs a full agent):
{
"type": "agent",
"if": "Bash(git push*)",
"prompt": "Review all staged changes for security issues before pushing. Check for: hardcoded secrets, SQL injection, XSS vulnerabilities, exposed internal URLs.",
"model": "haiku",
"timeout": 60
}
if condition to avoid running on every tool callLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.
---name: llm-gatedescription: LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions…---# skills/llm-gate/SKILL.md常見問題
從發布者下載 skills/llm-gate/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/rohitg00/pro-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。