本文へスキップ
TakoAPI
スキル一覧に戻る

agi-terminal-helper

liuwujijay 作

Coding Agents & IDEs
586ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

A practical runbook for using OpenClaw exec safely (sandbox-first, explicit confirmations, and debugging playbooks).

説明

このスキルでできること

A runbook for using OpenClaw's exec tool safely in real workspaces. Covers sandbox vs host execution, working directory discipline, long-running process patterns, and macOS permission issues. Includes concrete playbooks for common failure scenarios like skills not loading or Peekaboo bridge problems.

Instead of generic terminal advice, it gives workspace-specific patterns with explicit safety gates, so destructive commands require confirmation and sandbox/host environment differences don't cause silent failures.

使いどころ

  • Debugging why a custom skill isn't loading in OpenClaw
  • Running untrusted build scripts in a sandbox environment
  • Diagnosing macOS screen recording permission failures in OpenClaw
  • Polling long-running test or build processes without blocking
  • Auditing a workspace before making destructive file changes

ワークフロー例

入力

User asks: why isn't my new skill showing up in OpenClaw?

エージェント
  1. 1

    Run ls -la ./skills to verify the skill folder exists in the workspace

  2. 2

    Run find ./skills -maxdepth 2 -name SKILL.md -print to confirm SKILL.md is present

  3. 3

    Check frontmatter in SKILL.md for validity

  4. 4

    Confirm skills.load.watch is enabled if files were recently changed

  5. 5

    Report which precedence layer (workspace vs bundled) is winning

出力

Identified missing SKILL.md or invalid frontmatter; user corrects the file and skill loads on next watch cycle.

インストール

clawhub install liuwujijay/agi-terminal-helper

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク