菜单
Use when the simulator receives a validated plan from the planner and must initialize the race: parsing the plan, spawning runner agents, starting the telemetry collector, and firing the start gun. Triggered once per simulation, before the first tick.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/GoogleCloudPlatform/race-condition --skill preparing-the-race命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | preparing-the-race |
| description | Use when the simulator receives a validated plan from the planner and must initialize the race: parsing the plan, spawning runner agents, starting the telemetry collector, and firing the start gun. Triggered once per simulation, before the first tick. |
| license | Apache-2.0 |
This skill initializes the simulation after a validated plan arrives from the planner.
Each numbered step is a separate model response. The skill toolset guards against multi-step responses with an error.
Pre-Race Progress:
- [ ] Response 1: prepare_simulation (alone)
- [ ] Response 2: spawn_runners + start_race_collector (parallel)
- [ ] Response 3: fire_start_gun
Why separate responses: prepare_simulation sets state
(simulation_ready, runner_count, simulation_id) that the other
tools read. The skill guard rejects parallel calls that would race
with that state write.
Call only prepare_simulation with the JSON plan from the planner.
The tool extracts the route, computes tick parameters, and stores
configuration in session state.
Call spawn_runners and start_race_collector together in the same
response. The two tools are independent: spawning runners and
subscribing to broadcasts have no data dependency, so they execute
simultaneously for faster startup.
Call fire_start_gun to broadcast the START_GUN event to all spawned
runner agents.
prepare_simulation(plan_json, tool_context, duration_seconds=120, tick_interval_seconds=10, total_race_hours=6.0):
Parse the plan JSON, compute max_ticks, and store simulation config
in state.spawn_runners(count, tool_context):
HTTP POST to the gateway spawn API to create runner agent sessions.start_race_collector(tool_context):
Start a RaceCollector subscribed to gateway:broadcast for runner
telemetry.fire_start_gun(tool_context):
Broadcast a START_GUN RunnerEvent to all spawned runner agents via
Redis.call_agent(agent_name, message, tool_context):
Delegate inter-agent communication via the shared A2A utility.