Native multi-agent orchestration using Claude Code's Agent Tool. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
Computational Analysis via Code Execution - Execute custom computational analysis code, analyze software, and search for reference implementations. Use this skill for computational science tasks involving exec code software analysis search dataset search literature. Combines 4 tools from 2 SCP server(s).
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Convert laboratory protocols to executable JSON format using Thoth-OP for automated lab equipment control.
Use when the user wants a written implementation plan in Cursor before editing code, especially for multi-step tasks or changes touching several files.
Use when a written implementation plan already exists in Cursor and the next step is to execute it in small batches with checkpoints and verification.
严格按 plan.md 执行新功能开发。由角色 spec-executor 调用。 触发条件：(1) 角色 spec-executor 需要按 plan.md 实现代码， (2) 用户说"执行 Spec"/"开始实现"， (3) spec/ 目录下存在 plan.md 但没有 summary.md。 注意：v2.0 起移除路径 B（agent-teams）和测试步骤，spec-execute 只有单一职责： 按 plan.md 实现代码，产出 summary.md，归档。 如果目录下已有 summary.md，应使用 spec-update。
撰写代码实现计划（plan.md）。由角色 spec-writer 调用。 触发条件：(1) 角色 spec-writer 需要创建设计方案、API 规范、数据模型、架构设计、重构方案， (2) 用户说"创建 Spec"/"撰写设计文档"/"写技术规格"/"设计方案"， (3) spec/ 目录下需要新建 plan.md。 注意：v2.0 起 plan.md 不含测试计划章节（由 spec-tester 用 spec-test 单独创建）， execution_mode 固定为 single-agent。 如果目录下已有 summary.md，应使用 spec-update 而非本 Skill。
在线代码执行：支持 Python、JavaScript、TypeScript、Go、Rust、Java、C/C++、Ruby、PHP 等语言的沙箱运行。
Manage tasks, subtasks, tags, and templates via the slay CLI
List and manage running processes via the slay CLI
Create and manage automations via the slay CLI
Automatically title tasks based on conversation context
Shell script development workflow. Use when modifying files in scripts/ directory or any *.sh files.
Execute work through the directive pipeline — evaluate, plan, cast agents, build, review, and report. Takes a directive name (matching .context/directives/), a project path, or an ad-hoc CEO request. TRIGGER: Use this skill whenever the user requests non-trivial work that goes beyond a one-liner fix. This includes: building features, running projects with project.json, executing multiple tasks, multi-file changes, or any work with defined DOD/reviewers. Route through this pipeline so reviews and verification steps fire. Do NOT spawn builder agents directly. For heavyweight/strategic work, create a directive file in .context/directives/ first. For medium work with an existing project.json, pass the project path. For quick multi-step tasks, pass an ad-hoc description — no directive file needed.
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
Web browser automation and control via HTTP API
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
This skill should be used when the user asks to "create a Temporal workflow", "write a Temporal activity", "debug stuck workflow", "fix non-determinism error", "Temporal Python", "Temporal TypeScript", "Temporal Go", "Temporal Golang", "Temporal Java", "workflow replay", "activity timeout", "signal workflow", "query workflow", "worker not starting", "activity keeps retrying", "Temporal heartbeat", "continue-as-new", "child workflow", "saga pattern", "workflow versioning", "durable execution", "reliable distributed systems", or mentions Temporal SDK development.
