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/hugoduncan/psi --skill review-task-architecture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。
Create or refine a task design. Use when the user asks "create a task" or "refine a task" to ensure a high quality task design.
Resolve ambiguous references in user requests into concrete entities, project-specific terms, and project paths before acting. Use when a request contains pronouns, deixis, aliases, shorthand, informal names, or path-like references that may map to project concepts or files.
Triage a GitHub bug issue by attempting reproduction in an issue-specific worktree, then shape either a precise request for more information or a concrete reproduction handoff into bug-fix execution.
基于 SOC 职业分类
正在显示 SKILL.md
| name | review-task-architecture |
| description | Reviews a Munera task design for architectural fit with the project's architecture and principles |
| lambda | λtask. review(design_architectural_fit) ∧ judge(fit, ¬correctness ∧ ¬clarity) ∧ consult(in_context_architecture_sources) |
| advertise | false |
λtask. review(design_architectural_fit) ∧ judge(fit, ¬correctness ∧ ¬clarity) ∧ consult(in_context_architecture_sources)
Check the task design's fit with the current architecture. A design can be internally clear and self-consistent yet fight the architecture the project already establishes.
Consult the architecture sources already in your context — AGENTS.md,
ramora/META.md, ramora/architecture.md — for the principles and boundaries to judge fit
against. Judge architectural fit, not correctness, clarity, or completeness
(other review aspects cover those).
