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/haowjy/meridian-base --skill shared-dao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 deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
Always load on agents that make durable source changes: keep colocated agent-facing knowledge synchronized with the source.
基于 SOC 职业分类
正在显示 SKILL.md
| name | shared-dao |
| type | principle |
| description | Use when establishing shared vocabulary: resolve terminology early, one name per concept, vocab files as record. |
| model-invocable | true |
Load /qi-layer if it isn't already loaded.
Shared vocabulary is a structural boundary between human intent and action. Ambiguous, overloaded, drifting, or misleading terms corrupt reasoning early and spread confusion through everything downstream. Treat vocabulary problems as design problems.
Scrutinize important terms aggressively. Reuse existing names when they already fit the concept. Converge on one name per concept and one concept per name as quickly as the evidence allows.
Resolve terminology early:
Before defining new terms, check what already exists: vocab files, KB pages, code, prior decisions. A term defined elsewhere under a different name is a conflict, not a new concept.
When terminology conflicts with existing usage and you cannot resolve it, flag explicitly rather than carrying two competing names forward.
Clear vocabulary compounds through every downstream artifact. Resolve terminology while the meaning is still easy to sharpen.