发现最适合你需求的 AI 技能
Multi-agent collaboration and task delegation via the Agent Client Protocol (ACP) using acpx. Form agent teams from Claude Code, Codex, OpenCode, Gemini, Cursor, Copilot, and other ACP-compatible agents. Run parallel workstreams, switch agent modes, orchestrate deliberation and consensus, or delegate coding tasks to another agent. Triggers include "delegate to Claude", "use Claude Code", "ask Claude to", "parallel agents", "acpx", "ACP", "agent delegation", "form a team", "council", "multi-agent
Use when a coding, debugging, or research task should run inside one long-lived ACPX session while a separate supervisor keeps checking real engineering progress until the work is accepted complete or explicitly failed. 用于需要单一 ACPX 长会话执行、并由独立监工持续检查真实工程进度直到任务明确完成或失败的场景。
>
|
>
审查或改进前端 UI 的语义结构、键盘支持、焦点管理、标签以及常见的 WCAG 相关问题，并将报告保存为 Markdown 文件。当用户提到无障碍、accessibility、a11y、WCAG，或在实现交互组件时自动激活。
PDF to Markdown converter - extract text, tables and formulas from PDF files to clean Markdown. Use when converting PDF documents, extracting PDF content, parsing PDF text, or summarizing PDF reports."
专业的学术论文写作助手。当用户要求撰写、修改、润色学术论文，或需要论文结构规划、参考文献整理、学术用语规范化、查重检测等支持时使用。触发短语包括："写论文"、"润色论文"、"修改论文"、"论文结构"、"参考文献格式"、"学术用语"、"论文查重"等。
对学术论文（流行病学、生物统计学方向）进行深度结构化解析。当用户说"分析这篇论文"、"对这篇文献进行分析"、"论文分析"或类似话语时，自动激活此技能。
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
|
write, critique, score, compare, and revise english academic abstracts for ai, systems, and computer science papers using computable symbolic rules, lightweight ontologies, and sentence-level discourse constraints. use when the task involves drafting an abstract from notes, repairing sentence-to-sentence logic, checking verb-noun compatibility such as growth versus development, scoring two abstract fragments with a formal rule-based metric, bootstrapping or downloading a domain ontology, removin
