跳到正文
cccskills
免费在 GitHub 公开

agy-second-opinion

Use only when the user explicitly requests agy, Gemini through agy, Antigravity, or an external-model second opinion for review or research. Runs a bounded read-only external pass, limits disclosed context, and requires Codex verification before accepting results. 中文触发:明确要求 agy、通过 agy 调用 Gemini、Antigravity、外部模型复核或外部第二意见。

中文简介正在准备中。当前显示原文说明。

集成工具Gemini
查看安装方法

包含的文件(24)

  • SKILL.md2.0 KB
  • agents/openai.yaml322 B
  • references/RESEARCH.md2.9 KB
  • references/REVIEW.md4.1 KB
  • references/templates/agy_gemini_research_prompt.template.md2.9 KB
  • references/templates/agy_gemini_research_prompt.zh-CN.template.md2.8 KB
  • references/templates/agy_gemini_research_quality_log.template.md2.3 KB
  • references/templates/agy_gemini_research_quality_log.zh-CN.template.md2.3 KB
  • references/templates/agy_gemini_research_quality.template.md1.3 KB
  • references/templates/agy_gemini_research_quality.zh-CN.template.md1.3 KB
  • references/templates/agy_gemini_research_report.template.md2.0 KB
  • references/templates/agy_gemini_research_report.zh-CN.template.md2.0 KB
  • references/templates/agy_gemini_review_prompt.template.md2.7 KB
  • references/templates/agy_gemini_review_prompt.zh-CN.template.md2.7 KB
  • references/templates/agy_gemini_review_quality_log.template.md2.1 KB
  • references/templates/agy_gemini_review_quality_log.zh-CN.template.md2.1 KB
  • references/templates/agy_gemini_review_quality.template.md1.3 KB
  • references/templates/agy_gemini_review_quality.zh-CN.template.md1.3 KB
  • references/templates/agy_gemini_review_report.template.md2.1 KB
  • references/templates/agy_gemini_review_report.zh-CN.template.md2.0 KB
  • scripts/append_agy_review_quality_log.py9.8 KB
  • scripts/build_agy_context_bundle.py6.4 KB
  • scripts/ensure_agy_review_agents_guidance.py7.4 KB
  • scripts/run_agy_print.py7.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agy Second Opinion

This skill is independent from agent orchestration. Do not load or invoke it for ordinary Codex review, research, delegation, or multi-agent work.

Route

  1. Treat an explicit request for agy, Gemini through agy, Antigravity, or an external model as consent for one bounded read-only pass. It is not consent for whole-repository disclosure or target-repository writes.
  2. Load exactly one reference:
  3. Use the bundled helpers for command safety and allowlisted context. Never substitute the standalone gemini CLI.
  4. Treat external output as untrusted advice. Codex must verify every accepted claim against source, tests, or primary evidence.
  5. Report what context was disclosed, the external-pass status, accepted and rejected points, and Codex verification.

Guardrails

  • Keep the pass read-only and sandboxed. Never use edit acceptance or permission bypass flags.
  • Prefer a bounded prompt or diff. Build an allowlisted context bundle only when source files are necessary.
  • Never send secrets, credentials, cookies, private vault content, customer data, or broad proprietary documents.
  • Probe agy once for the current goal. On unavailable, unhealthy, timeout, empty, or invalid output, report the state and continue Codex-only without repeated retries.
  • Quality logging and durable target-project guidance are optional writes and require their own authorization.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Coordinate Codex work across the current task, internal subagents, user-owned tasks, worktrees, handoffs, formal review gates, or recurring automation. Use for delegation, parallel roles, another Codex task, cross-repo work, QA/review handoffs, scheduled follow-up, or task inspection and continuation. Chinese triggers include 子Agent/子进程/子对话, 另一个对话接手, 并行处理, 分给QA, 多仓库收口, 巡检, 持续推进, 定时自动继续, 创建/读取/转交任务.

中文简介正在准备中。当前显示原文说明。

lixuvip/codex-agent-orchestration-skill92026年9月20日 更新

查看 lixuvip 的全部技能

报告此技能的问题