Agent building

Launch Loki Mode autonomous SDLC agent.

Generate music using ElevenLabs Music API.

Use ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation.

Generate sound effects from text descriptions using ElevenLabs.

Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine.

Set up Cyrus end-to-end — install prerequisites, configure authentication, create integrations (Linear, GitHub, Slack), add repositories, and launch.

Create a Linear OAuth application and configure Cyrus to use it — supports agent-browser automation or guided manual setup.

Format a final summary message for Linear.

Use when a security incident, data breach, or actively exploited vulnerability raises the question "who must we notify, where, and by when?" Screens one…

Design a Grok Bot role and create its setup prompt.

管理本地 Markdown/Obsidian 知识库：素材入库、健康检查、增量索引、关键词与 semantic-lite 检索、逐字原文资料包、归档和 MCP 连接。用于搜索知识库、整理资料及为 Agent 准备可定位的引用。

SSH version CVEs and post-auth tricks — regreSSHion, user enum, agent hijack.

Per-case mocked MCP override smoke skill used by skill-up e2e tests.

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself.

Verify Sandbox MCP can be installed and called from skill-up.

Use when the user wants paper-writing prompt templates or wants Codex to automatically choose and apply the best prompt logic for tasks such as 翻译, 润色, 改写…

Applies prompt repetition to improve accuracy for non-reasoning LLMs.

Review a diff of this repository from a Product Manager (PdM) perspective: documentation consistency (JSDoc placement, comment policy, README accuracy)…

Review a diff of this repository as a QA engineer: test quality (coverage, test-faking code, swallowed exceptions, conditional logic in tests, hardcoded…

Clarify a feature, change, or refactor through questions, then write a build prompt for another agent.

Distribute global skills across Codex, Claude Code, Pi, Hermes, and Cursor.

Draft /goal prompts and explain persistent agent loops.

Capture session context for a fresh agent.

Write four distinct prompts for AI image models.