菜单
Use when the user asks to debug Dirac_solver execution, verify OpenClaw execution capability, or validate state synchronization across queue, bridge, and progress sync files.
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/photonics-dhl/Dirac_solver --skill dirac-debug-ops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。
Use when running Octopus DFT/TDDFT calculations — select optimal mpirun -np and ParStates/ParDomains/OMP configuration for the system size. For new molecules or large systems, run a quick parallel scaling benchmark first.
Use when the user asks to debug Dirac_solver execution, verify OpenClaw execution capability, or validate state synchronization across queue, bridge, and progress sync files.
Use for Dirac execution stage to run harness and Octopus with endpoint fallback and audit artifacts.
基于 SOC 职业分类
正在显示 SKILL.md
| name | dirac-debug-ops |
| description | Use when the user asks to debug Dirac_solver execution, verify OpenClaw execution capability, or validate state synchronization across queue, bridge, and progress sync files. |
scripts/run_dirac_debug_ops.py# Snapshot only (non-intrusive)
python scripts/run_dirac_debug_ops.py --mode snapshot
# Dispatch only (route + execute)
python scripts/run_dirac_debug_ops.py --mode dispatch --task "Dirac_solver 调试" --execute --auto-replan
# Full check: snapshot -> dispatch -> snapshot
python scripts/run_dirac_debug_ops.py --mode full --task "Dirac_solver 调试 /auto smoke" --execute --auto-replan
pid, alive).execution_bus.last_task snapshot.state/dirac_solver_progress_sync.json) phase/checks.step, time, total_energy)--mode snapshot first when diagnosing production issues.dispatch_status and failure_reason from tool output.