Use for multi-file code implementation requiring cross-review from heterogeneous models (Claude + Codex), or for architectural solutions needing adversarial inquiry verification. It's suitable for end-to-end collaboration in large coding tasks, not for small single-file modifications or pure data processing.
/plugin marketplace add PlutoLei/crossfire
The exact command may vary by repository. Check the README on GitHub.
For the skill author
Shows your skill is listed on Skillteca, generates a backlink and trackable traffic.
[](https://www.skillteca.com.br/skills/crossfire?utm_source=badge&utm_medium=readme&utm_campaign=badge)
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a C
Create new skills, modify and improve existing ones, and measure their performance. Use this skill for developing, editing, optimizing, testing, and benchmarking skills, as well as refining their descriptions for better triggering.
Captures agent actions across sessions, compresses them with AI, and injects relevant context into future interactions. Compatible with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode, and more.
This skill clusters GitHub issue backlogs by root cause into plan-master issues, redirects related children, and bundles architectural-fix PRs to close clusters atomically. It's ideal for triaging and consolidating numerous issues sharing underlying defects, or for building a plan series or roadmap.
Category alert
One short email with only the new Desenvolvimento skills. 4 minutes of reading, no spam, unsubscribe with one click.
You confirm your email on the first send. No spam. Unsubscribe with one click.
Claude Code (Opus 4.6) = Actor（架构师/审查员），Codex (GPT-5.4) = Executor + Critic（执行者/审计员）。异源模型交叉审查减少确认偏差——不同训练分布更可能发现对方盲区（arXiv:2602.03794）。Windows 环境下所有 Codex 调用需经过路径归一化预处理（详见 templates-and-faq.md「Windows 防护层」）。
| 角色 | 模型 | 职责 |
|---|---|---|
| 架构师 | Claude Opus 4.6 | 探索、规划、审查、修复、决策 |
| 执行者 | Codex gpt-5.4 | 编码实现、文件修改 |
| 审计员 | Codex gpt-5.4 --full-auto | 架构质询（Phase 0）、代码终审（Phase 2） |
[Description truncada. Veja o README completo no GitHub.]
