菜单
Quick validation run before committing to a full sweep. Runs a scenario with minimal seeds/epochs, checks for crashes and metric sanity, reports go/no-go.
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。
基于 SOC 职业分类
SWARM: System-Wide Assessment of Risk in Multi-agent systems. Simulate multi-agent dynamics, test governance, study emergent risks.
Query the SWARM knowledge graph structurally — find pages, list backlinks, follow link paths, and surface related/semantic neighbors across docs, scenarios, slash commands, agents, roles, and code references. Prefer this over grep when you need *connected* answers ("what links to X", "how does X relate to Y", "what's similar to X").
Scaffold research papers from SWARM run data with auto-populated tables
Run parameter grid sweeps across SWARM scenarios and generate summary statistics
Generate publication-quality visualizations from SWARM simulation data
Execute a SWARM simulation scenario and export standardized artifacts
| name | sanity-check |
| description | Quick validation run before committing to a full sweep. Runs a scenario with minimal seeds/epochs, checks for crashes and metric sanity, reports go/no-go. |
| version | 1.0 |
| metadata | {"author":"swarm-research-os","generated_from":"research-os-v0.1"} |
| allowed-tools | Read Bash Glob |
Scenario: $ARGUMENTS
If no scenario provided, ask which scenario to check.
scenarios/python -m swarm run scenarios/$SCENARIO --seed 42 --epochs 5 --steps 5
p values in [0, 1]## Sanity Check: {scenario}
Status: GO / NO-GO
Runtime: {seconds}s
Metrics:
- Welfare: {value}
- Toxicity: {value}
- Acceptance rate: {value}
- Quality gap: {value}
{If NO-GO: describe the issue and suggest fix}
{If GO: ready for full sweep with --seeds N}