当用户希望 Camp 中多位成员共同讨论、从不同角度分析、比较方案、评估利弊或讨论后形成建议时使用。主持人发起和继续整理讨论,成员在收到本次讨论任务时也使用。普通单人问题、无关发言、迟到补充和已经结束的讨论不使用。
Scanned 9/2/2026
Install to Claude Code
npx -y skills add murray17/rovai-ai --skill campfire --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Campfire?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/murray17-campfire)More formats (shields.io, HTML) on the badges page.
---
name: campfire
description: 当用户希望 Camp 中多位成员共同讨论、从不同角度分析、比较方案、评估利弊或讨论后形成建议时使用。主持人发起和继续整理讨论,成员在收到本次讨论任务时也使用。普通单人问题、无关发言、迟到补充和已经结束的讨论不使用。
---
# 篝火讨论
Campfire 由当前 Default Lead 主持。成员先独立判断;只有一个会改变结论的关键分歧可以进入定向回应;最后发布一份统一纪要。
## 使用边界
用于多人讨论、不同视角分析、方案比较、利弊评估或讨论后建议。不用于普通单人任务、持续双人追问、严格信息隔离,或不足两位成员的场景。CampMessage 公开可见,因此独立作答不是盲评。
只有用户直接请求当前 Default Lead 才能开始新讨论。普通成员收到用户的召集请求时不得自行启动;成员只在收到本场正式讨论任务时参与。
## 角色路由
| 当前角色与输入 | 动作 |
| --- | --- |
| 当前 Default Lead 收到用户直接请求 | 读取 [Default Lead 指南](references/lead.md),开始第一轮 |
| 普通成员处于用户广播或同时触达 Default Lead 的阶段 | 读取 [参与者指南](references/member.md),保持静默 |
| 普通成员的当前 AgentRun 由正式独立观点或定向回应请求触发 | 读取 [参与者指南](references/member.md),返回一条完整结果 |
| Gather 原发起者收到本轮 completion | 读取 [Default Lead 指南](references/lead.md),继续综合或收口 |
| 任意角色收到纪要、迟到意见或无关发言 | 不自动续跑 |
按当前角色、请求来源和本轮完成结果判断,不凭消息标题推进流程。
## 公共规则
1. 同一 Default Lead 在一个 Camp 中一次只推进一场未结束的 Campfire。
2. 第一轮 Gather 邀请 2–3 位成员独立作答;只有关键分歧可以触发一次邀请 1–2 人的回应 Gather。
3. 每场最多两轮,每位成员每轮只返回一条完整结果。
4. 第二轮完成后必须发布唯一《篝火纪要》,不追加澄清轮;迟到观点不自动更新纪要。
5. 用户的停止、替换话题、移除成员或立即总结始终优先。
## 流程
```text
用户请求 Default Lead
→ 第一轮 Gather:2–3 份独立观点
→ 少于两份有效观点:部分纪要或终止
→ 无关键分歧:发布纪要
→ 有关键分歧:一次定向回应 Gather
→ 发布纪要
```
不要为展示讨论感强行制造反方。准备终止输出时读取 [篝火纪要写作指南](references/notes.md)。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.