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
phxagents v3 為 Claude Code、Amp、Codex、Pi 與 OpenCode 帶來唯一的 Elixir 與 Phoenix 技能套件,提供 10 種工作流程,適用於所有執行環境。
AI 翻譯
phxagents v3 brings one canonical Elixir and Phoenix skill set to Claude Code, Amp, Codex, Pi, and OpenCode, with 10 workflows adapted for every runtime.
開發工具Python · ShellGitHub @oliver-kriska上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
Claude Code 插件支援 Elixir/Phoenix/LiveView——包含 26 位專家代理、Iron Laws 執行與 Tidewave MCP 整合。規劃功能時使用平行研究代理,執行時自動驗證,審查時以 4 代理平行稽核,並將學習成果捕捉為可重複使用的知識。
AI 翻譯
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Docs: phxagents.dev -- install guides per runtime,
the runtime compatibility matrix, all
26 Iron Laws, and a browsable
skill and agent catalog.
Claude Code is great. But it doesn't know that assign_new silently skips on reconnect, that :float will corrupt your money fields, or that your Oban job isn't idempotent.
This plugin does. It coordinates 26 specialist agents that plan, implement,
review, and verify your Elixir/Phoenix code in parallel -- each with domain
expertise, fresh context, and enforced Iron Laws
that catch the bugs your tests won't.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Docs: phxagents.dev -- install guides per runtime,
the runtime compatibility matrix, all
26 Iron Laws, and a browsable
skill and agent catalog.
Claude Code is great. But it doesn't know that assign_new silently skips on reconnect, that :float will corrupt your money fields, or that your Oban job isn't idempotent.
This plugin does. It coordinates 26 specialist agents that plan, implement,
review, and verify your Elixir/Phoenix code in parallel -- each with domain
expertise, fresh context, and enforced Iron Laws
that catch the bugs your tests won't.檢視完整 README ↗