‹ 首页

dev-ask

@evolution-foundation · 收录于 5 天前 · 上游提交 2 个月前

Advisory router — query Claude, Codex, or Gemini for a quick second opinion. Experimental — only Claude is guaranteed available; other models require dev-mcp-setup configuration.

场景技术决策代码评审方案对比

适合你，如果在开发中需要快速获取多个AI模型的建议

/ 下载安装
https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/dev-ask ↗
/ 通过 npx 安装 校验哈希
npx oh-my-skill add evolution-foundation/evo-nexus/dev-ask
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- evolution-foundation/evo-nexus/dev-ask
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify evolution-foundation/evo-nexus/dev-ask
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
509GitHub stars
~408上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 7f5dd76 · 表述以原文为准
它做什么

安装后，你可以让Claude单独向某个模型（Claude、Codex或Gemini）提问，并返回该模型的回答和来源。用于快速获取特定模型的第二意见。注意：仅Claude默认可用，其他需配置。

什么时候触发

当你需要某个特定模型对问题给出意见，或想对比不同模型回答时触发。通常是你主动要求向某个模型提问。

装好后可以这样说
会调用Gemini模型分析代码。
会调用Codex模型解释。
会调用Claude自身模型。
技能原文 SKILL.md作者撰写 · Apache-2.0 · 7f5dd76

Dev Ask

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.

EXPERIMENTAL. Quick advisory query to a specific LLM (Claude, Codex, Gemini) for a second opinion. Different from dev-ccg which runs all three in parallel — dev-ask is single-shot.

Use When
  • You want a fast second opinion from a specific model
  • Comparing how different models approach the same problem
  • Validating Claude's answer against another model
Do Not Use When
  • Need consensus across models → use dev-ccg
  • Just need an answer → ask the active session directly
  • Codex/Gemini APIs not configured → only Claude available, fall back
Workflow
  1. Pick the target model: claude | codex | gemini
  2. Format the question model-agnostically
  3. Send via the appropriate API
  4. Return the answer with the model's name attached
  5. Optional: save to workspace/development/research/[C]ask-{topic}-{date}.md
Configuration

| Model | Required setup | |---|---| | Claude | Native — always available | | Codex | OpenAI API key configured via dev-mcp-setup | | Gemini | Google API key configured via dev-mcp-setup |

If a target model isn't configured, the skill warns:

"{model} is not configured. Only Claude is currently available. Configure via dev-mcp-setup or use dev-ccg to compare available models."
Output Format
## Ask — {target model}

### Question
{question}

### Answer (from {model})
{answer}

### Note
[Any caveats — model version, response time, confidence, etc.]
Pairs With
  • dev-ccg (multi-model parallel)
  • dev-mcp-setup (configures non-Claude APIs)
  • @apex-architect (often the consumer of multi-model perspectives)
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…