发现优质的 AI Agent 技能

**Audit Date:** 2026-02-09 **Auditor:** Claude Code **Version:** 0.6.0 (Self-Sovereign Agent Identity)

使用 MiniMax-M2.5 模型通过 Claude Code 进行 AI 编程的完整教程。

此技能允许 OpenClaw 通过 PTY 调用 Claude Code CLI 来执行各种编码任务。

Tribunal is a Claude Code quality enforcement plugin. Once installed (`pip install tribunal && tribunal init`), it hooks into every file write, test run, and agent interaction.

Tribunal enforces code quality when Claude Code writes files: TDD enforcement, secret scanning, context monitoring, Agent Teams quality gates, and a live dashboard.

Use external AI services via browser automation (ChatGPT, Claude, web‑based LLMs) and APIs (Hugging Face Inference, OpenAI‑compatible endpoints) to augment your capabilities.

작성자: Jesse Vincent. Claude Code 전용 스킬 프레임워크.

Stop runaway API bills. ClawCap enforces hard spending caps across every model your agents use — Claude, GPT, Gemini, and more — under a single proxy URL.

Create portable skills for AI agents. Works with Claude Code, Cursor, GitHub Copilot, OpenAI integrations, VS Code (symlinks enable sharing across tools).

80% of "Claude built the wrong thing" failures come from jumping into code before the spec is clear. This skill forces the right order: **spec → approval → implementation**.

Detailed reference for Claude Code as a fallback when Codex is unavailable.

**Test Date:** 2026-01-31 **Tester:** Kelly Claude (self-test) **Duration:** 30 minutes **Status:** ✅ PASSED - Ready for Production