literature-retrieval

LLM-based zero-shot and few-shot classification for flexible intent detection

Route AI requests to different LLM providers using SwiftOpenAI-CLI's agent mode. This skill automatically configures the CLI to use the requested provider (OpenAI, Grok, Groq, DeepSeek, or OpenRouter)

Multi-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.

>

Capture image from webcam and optionally view or send it. Use when wanting to see surroundings, take a photo, check what's visible, or share a view with collaborator. Trigger words: look, see, webcam, camera, photo, capture, what's around, show me.

Process merge queue items as a Loom merge worker - claim, merge, mark done, handle no-op merges, and resolve compound block conflicts correctly.

Start a ralph style looping session

'深度调研的多实例（多 Agent）编排工作流：把一个调研目标拆成可并行子目标，用 Codex CLI（`codex exec`）在默认 `workspace-write` 沙箱内运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付“成品报告文件路径 + 关键结论/建议摘要”。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及“深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研”等场景。'

> **Attribution**: [Beads](https://github.com/steveyegge/beads) by [Steve Yegge](https://github.com/steveyegge)

Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonom

Modify topic triggers — trigger phrases and model description. Use when the user asks to add, remove, or change trigger phrases, or edit a topic's model description.

Add a global variable to a Copilot Studio agent. Use when the user needs a variable that persists across topics in the same conversation and can optionally be visible to the AI orchestrator.

ARGUMENTS: $ARGUMENTS

定时任务功能**内置在 mycc 后端**，启动后端后自动生效。

Creates a comprehensive pre-launch checklist covering engineering, design, marketing, support, legal, and operations readiness. Use before releasing features, products, or major updates to ensure nothing is missed.

Creates a structured competitive analysis comparing features, positioning, and strategy across competitors. Use when entering a market, planning differentiation, or understanding the competitive landscape.

Create professional, print-ready HTML documents that export to PDF with customizable branding.

用 OpenClaw 驱动 Codex CLI 的受管运行时。支持交互式 tmux 会话、一次性 exec 任务、会话状态查询、显式 session-id 路由、启动阻塞识别与完成通知。

先阅读 AGENTS.local.md 作为 AGENTS.md 的基底 然后添加本文件的其他内容。

>

Respond terse like smart caveman. All technical substance stay. Only fluff die.

>

>

>

>

发布时间：2024年10月22日

>

>-

Reference for the workmux CLI that manages git worktrees and

qiqing-liuyu

Fixation is the default state. When a generator (human or LLM) has been working on a problem, attention concentrates on the current framing and subsequent ideas tend to be local variations on it. This

Claude Code internal subagents. These are NOT end-user agents — they're

- [Agents Overview](https://raw.githubusercontent.com/google/adk-docs/refs/heads/main/docs/agents/index.md)

See [CLAUDE.md](CLAUDE.md) for project instructions.

The `dev-intelligence-orchestrator` skill provides intelligent development tool orchestration with **self-improving learning capabilities** through mcp-prompts integration.

Classify construction data by type (structured, unstructured, semi-structured). Analyze data sources and recommend appropriate storage/processing methods

Forecast project outcomes using historical data: cost overruns, schedule delays, risk probabilities. Machine learning models for construction prediction.

Predict project completion dates using ML models. Forecast schedule delays based on current progress, historical patterns, and risk factors.

Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery

>

>

>

>

Clear stored Woz credentials and log out.