AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證pair is the process layer for AI-assisted development. It gives your AI assistant the context, guidelines, and skills to work the way your team works.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Code is the easy part.
AI-assisted software development — structured Knowledge Base, Agent Skills, and adoption files that give AI coding assistants the context they need to ship quality software.
This installs the pair Knowledge Base into your project. Your AI assistant reads .pair/ and .claude/skills/ to follow your team's standards, process, and architecture decisions.
In Claude Code? Skip the command line — install the bootstrap plugin and let it do the above:檢視完整 README ↗Code is the easy part.
AI-assisted software development — structured Knowledge Base, Agent Skills, and adoption files that give AI coding assistants the context they need to ship quality software.
npm install -g @foomakers/pair-cli
pair-cli install
This installs the pair Knowledge Base into your project. Your AI assistant reads .pair/ and .claude/skills/ to follow your team's standards, process, and architecture decisions.
In Claude Code? Skip the command line — install the bootstrap plugin and let it do the above:
/plugin marketplace add foomakers/pair
/plugin install pair@pair
/pair-assistant
The plugin ships one skill: an assistant that installs pair-cli and runs it — so your project ends up with exactly the tree the command above produces — and then keeps helping you drive the CLI and answer questions from your own knowledge base. See Install Channels.
.pair/llms.txt for machine-readable KB discovery (llmstxt.org)pair is developed using pair itself. The entire SDLC — from PRD to code review — is driven by AI assistants reading the same Knowledge Base that ships to users.
Resources managed by pair in this repo:
| Directory | What it contains |
|---|---|
.pair/knowledge/ | 9 how-to guides, 9 guideline areas (code design, testing, security, collaboration, ...), templates for commits, PRs, stories, ADRs |
.pair/adoption/tech/ | Architecture, tech stack, infrastructure, way of working, 15 ADRs |
.pair/adoption/product/ | PRD, subdomain model |
.pair/adoption/decision-log/ | Non-architectural decision records |
.claude/skills/ | 41 Agent Skills — process workflows (implement, review, refine) and capabilities (quality gates, estimation, manual testing, debt assessment) |
AGENTS.md | Universal agent entry point linking to .pair/ |
Visit the pair documentation site for guides, reference, and tutorials.
MIT — Foomakers