xiaohei-info

Use when architecture work hinges on DDD-style domain modeling: subdomains, bounded contexts, context relationships, aggregate boundaries, and how those decisions shape overview or detailed design artifacts.

Use when architecture or backend work needs pre-code structural guidance from design patterns, or post-code cleanup guidance from refactoring and code-smell-driven improvement.

Structured methodology for comparing technology options (frameworks, platforms, tools) and documenting adoption decisions with evidence-based reasoning.

Use when an architect in the deploy-and-ops stage must produce or review the 部署架构图 / 物理架构图 so that physical topology, deployment boundaries, and run-stage assumptions are visible during handoff.

Use when an architect in the solution-design stage must produce or review the 业务解决方案架构图 and needs the fully merged specialist method directly inside the new lifecycle family instead of via a legacy wrapper skill.

Use when an architect in the solution-design stage must produce or review a 业务流程图 that explains roles, steps, and handoff order without collapsing into system architecture, technical architecture, or detailed-design flow logic.

Use when an architect in the solution-design stage must produce or review the 领域模型 artifact so business objects, semantic boundaries, and major relationships are explicit before technical design begins.

Use when an architect in detailed technical design must produce or review the 关键流程图 or 状态机 and needs the fully merged branch-complete core-flow specialist method directly inside the new lifecycle family.

Use when importing, installing, packaging, or publishing third-party Hermes skills so category placement, support files, discoverability, and open-source release surfaces stay correct.

Build log monitoring systems that avoid duplicate alerts and false positives. Use when creating cron-based monitoring, log error tracking, or alert deduplication.

Use when creating or refining any Hermes cron job whose final delivery goes to humans on Telegram or similar chat platforms. Prioritize user-readable alert design, compact default output, severity gating, and exception-driven expansion over exhaustive internal dumps.

Use before claiming work is complete, fixed, or passing. Requires fresh verification evidence before any success claim.

Set up or document a Karpathy-style LLM Wiki workflow in Obsidian, especially when raw material should live in Inbox and compiled knowledge should live in _wiki.

Compile one or more raw Obsidian Inbox notes into the `_wiki/` layer using controlled source pages, selective downstream updates, and mandatory index/log maintenance.

Review the health of an existing `_wiki/` compiled knowledge layer, surface priority fixes, and triage backlog candidates. Use after initial wiki scaffolding or periodically during maintenance.

Use when Hermes should run a complete multi-role subagent workflow: decompose work, assign isolated planner/investigator/implementer/reviewer tasks, integrate results, and verify before claiming success.