基于 SOC 职业分类
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/vstorm-co/agenticos --skill architecture-decision-record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。
正在显示 SKILL.md
| name | Architecture decision record |
| description | Capture a decision, the options rejected, and the cost accepted. |
| category | documentation |
The value is not the decision. It is the reasoning, read in two years by somebody about to undo it.
Context — what forced a decision now, including constraints. Options — every one seriously considered, including doing nothing. Decision — what was chosen, in one sentence. Consequences — what this costs, what it makes harder, what it rules out. Status — proposed, accepted, superseded, with dates.
Consequences. An ADR listing only benefits is a sales pitch, and it is useless to the reader trying to work out whether the trade still holds.
The next reader will reconsider one of them. If it is described as a straw man, they will assume it was never properly examined and redo the work.
Write it after the fact to justify a decision, leave the date off, or edit a superseded ADR in place — supersede it with a new one that links back.
Work with messaging-channel bots — Telegram, Slack or Mattermost. Register a bot, route inbound messages through an agent, choose webhook vs polling, handle an @slug mention, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery, identity linking or "the bot answered as itself".
Change the agent spec — add or remove a field, rename one, tighten a rule, bump SPEC_VERSION, change publish-time validation, or touch YAML export/import. Use whenever editing app/agents/spec.py or anything that reads a stored spec. Every published agent and every client git repository holds a copy of this format, so a change that only works forwards breaks agents nobody touched.
Work with MCP servers — connect one, add an entry to the server catalog, debug "the agent cannot see my MCP tools" or a failing OAuth flow, or change how connections are probed, prefixed or filtered. Use when the ask involves an external SaaS tool (GitHub, Linear, Notion, Slack, Stripe, Postgres…) and before writing a capability that would just be an API client for one.