Peer decision-review skill — Claude × Codex bilateral consultation for better product and implementation outcomes, not agreement theater. Triggers when the user writes "朋友", "/friend", or "friend" as a standalone message or invocation, or says "问问 codex", "和朋友商量", or "叫上朋友". Use proactively when another model can change the decision: product/architecture/API tradeoffs, ambiguity, non-trivial implementation planning, high-risk or irreversible work, global config changes, or investigation plateau. Does not block native ClaudeCode/Codex agent workflows. Preserve useful dissent; choose the best-supported route. Skip clear low-risk execution. The user is the final arbiter.
Project continuity handoff skill for Claude, Codex, the same agent after reset, or another collaborator. Triggers when the user writes "交班", "/handoff", or "handoff" as a standalone message or invocation, or asks for handover, 接力, resumption after context loss, role switch, or a persistent status package.
Execution Split Card for Claude × Codex after the user or a decision-ready 朋友/Buddys outcome chooses split execution. Trigger when the user explicitly writes "帮手", "/helper", or "helper", asks to split execution, or invokes an existing [SPLIT: YES] brief. [SPLIT: YES] is authorization, not an automatic trigger. Does not replace native ClaudeCode/Codex agent routes.
Buddys tri-agent decision-review skill for Claude × Codex × Gemini. Trigger when the user explicitly writes "兄弟们", "/buddys", "buddys", or legacy "/xiongdimen" / "xiongdimen", or asks to bring Codex and Gemini into the same product/design/review loop. Uses friend internally as Claude↔Codex transport and asks Gemini for bounded independent review. Does not block native ClaudeCode/Codex agent routes. Optimize for a better product decision, preserve useful dissent, and avoid consensus theater.
Peer decision-review skill — Codex × Claude bilateral consultation for better product and implementation outcomes, not agreement theater. Triggers when the user writes "朋友", "/friend", or "friend" as a standalone message or invocation, or says "问问 claude", "和朋友商量", or "叫上朋友". Use proactively when another model can change the decision: product/architecture/API tradeoffs, ambiguity, non-trivial implementation planning, high-risk or irreversible work, global config changes, or investigation plateau. Does not block native Codex/ClaudeCode agent workflows. Preserve useful dissent; choose the best-supported route. Skip clear low-risk execution. The user is the final arbiter.
Project continuity handoff skill for Codex, Claude, the same agent after reset, or another collaborator. Triggers when the user writes "交班", "/handoff", or "handoff" as a standalone message or invocation, or asks for handover, 接力, resumption after context loss, role switch, or a persistent status package with project background, goals, environment, file locations, solved and unsolved issues, error history, and next actions.
Execution Split Card for Codex × Claude after the user or a decision-ready 朋友/Buddys outcome chooses split execution. Trigger when the user explicitly writes "帮手", "/helper", or "helper", asks to split execution, or invokes an existing [SPLIT: YES] brief. [SPLIT: YES] is authorization, not an automatic trigger. Does not replace native Codex/ClaudeCode agent routes.
Buddys tri-agent decision-review skill for Codex × Claude × Gemini. Trigger when the user explicitly writes "兄弟们", "/buddys", "buddys", or legacy "/xiongdimen" / "xiongdimen", or asks to bring Claude and Gemini into the same product/design/review loop. Uses friend internally as Codex↔Claude transport and asks Gemini for bounded independent review. Does not block native Codex/ClaudeCode agent routes. Optimize for a better product decision, preserve useful dissent, and avoid consensus theater.