Debug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed calls, troubleshooting audio problems, investigating conversation breakdowns, reviewing error logs, or optimizing underperforming agents. Includes transcript analysis, error diagnosis, and performance troubleshooting.

**定义**：

在 only-danmuku 的 CleanDDD Kotlin 项目中编写或修改聚合/命令/查询/API 端点/事件/防腐层 Client/仓储/配置/测试时使用；遵循 代码实现规约.md 与 design/_gen + genDesign 的生成流程。

**Current problem**: 669-line agent with embedded knowledge

Delegate complex tasks to Amplifier's multi-agent framework. Use when: (1) research/comparison needing multiple perspectives, (2) multi-file code projects, (3) architecture/design reviews, (4) user asks for deep/thorough work. NOT for: simple Q&A, quick edits, casual chat, anything needing <5s response. CLI: amplifier-openclaw.

Code generation guard for Node.js/TypeScript/Next.js - prevents OWASP Top 10 vulnerabilities while writing code

Fix bugs using TDD starting from README + Issue (following codegen-test), aligning with existing implementation conventions, and leveraging Serena MCP semantic search/editing to implement changes with high performance and race-safety in mind.

Perform refactoring using TDD starting from README + Issue (following codegen-test), aligning with existing implementation conventions, and leveraging Serena MCP semantic search/editing to improve internal quality with high performance and race-safety in mind.

A skill for writing Go tests in a TDD workflow. Follow README/Issue requirements and existing test conventions, add a balanced set of table-driven cases across behavior/boundaries/branches, and produce maintainable tests without excessive mocking or coverage-chasing.

Generates clear, conventional commit messages from git diffs. Use when writing commit messages or reviewing staged changes.

ManiSkill은 GPU 가속 병렬 시뮬레이션을 제공하는 강화학습 전용 로봇 환경입니다.

**Type:** Blue Team - Defensive Security Agent

Process customer refunds quickly. Search by order number or email, view order details, and issue full/partial refunds with automatic customer notifications. Use for customer support, order issues, or goodwill refunds. Triggers on "refund", "issue refund", "process refund", "customer wants refund", or similar queries.

Create engaging, authentic LinkedIn posts like a Top Voice. Use this skill when asked to write LinkedIn content, social media posts for LinkedIn, professional thought leadership content, or help with LinkedIn engagement strategy. Triggers include requests for LinkedIn posts, professional social content, thought leadership pieces, or viral/engaging LinkedIn content.

Loro CRDT state management with loro-mirror. Use when working on files in src/lib/crdt/.

Edit LCP protocol docs under docs/protocol/ in BOLT-style (TLVs, message formats, state flow).

**Type:** AI Research Agent

Pattern detection and automatic skill recommendation system. Activates when analyzing Cortex memory files, detecting recurring work patterns, or determining if new skills are needed. Analyzes .cortex_log.md, PRD files, and task lists to identify patterns (API calls, testing, deployment, etc.) appearing 5+ times. Generates Synapse_RECOMMENDATIONS.md with prioritized skill suggestions. Use when optimizing workflows or identifying automation opportunities.

Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.

**Version:** 1.0.0