c-level-agents
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinesec-level-agents — Founder-Mode Executive Team
c-level-agents — 创始人模式高管团队
A virtual C-suite delivered through slash commands and persona agents.
通过斜杠命令和角色Agent提供的虚拟C-suite团队。
Keywords
关键词
founder mode, virtual c-suite, executive team, boardroom, office hours, cfo review, cmo review, strategic sprint, decision logging, cross-model consensus, persona agents, chief of staff, forcing questions
创始人模式(founder mode)、虚拟C-suite(virtual c-suite)、高管团队(executive team)、董事会(boardroom)、办公时间(office hours)、CFO评审(cfo review)、CMO评审(cmo review)、战略冲刺(strategic sprint)、决策日志(decision logging)、跨模型共识(cross-model consensus)、角色Agent(persona agents)、Chief of Staff、强制提问(forcing questions)
What This Plugin Provides
该插件提供的功能
8 cs-* Agents (in agents/
)
agents/8个cs-* Agent(位于agents/
目录下)
agents/Each agent wraps an existing c-level skill and adds:
- A distinct cognitive voice (numerate skeptic, narrative-first, etc.)
- Forcing questions specific to the role
- Workflow orchestration tied to skill Python tools
- Output template: Bottom Line → What → Why → How to Act → Your Decision
See for voice specs.
../references/persona-voices.md每个Agent封装了现有的C级技能,并新增:
- 独特的认知风格(如数字敏感型怀疑派、叙事优先型等)
- 针对该角色的强制提问
- 与技能Python工具绑定的工作流编排
- 输出模板:核心结论 → 内容 → 原因 → 行动方案 → 你的决策
角色风格规范请查看。
../references/persona-voices.md17 /cs:* Slash Commands (in skills/
)
skills/17个/cs:*斜杠命令(位于skills/
目录下)
skills/Forcing-question office hours (8):
- — YC-style 6-question intake
/cs:office-hours - — unit economics, runway, dilution
/cs:cfo-review - — ICP, CAC payback, positioning
/cs:cmo-review - — RICE, JTBD, North Star, PMF
/cs:cpo-review - — pipeline coverage, win rate, NRR
/cs:cro-review - — architecture risk, scaling cliff
/cs:cto-review - — threat model, blast radius, compliance
/cs:ciso-review - — contracts, IP, regulatory, term sheets
/cs:gc-review
Strategic sprint pipeline (5):
- →
/cs:brief→/cs:boardroom→/cs:decide→/cs:execute/cs:post-mortem
Meta + safety (4):
- — auto-routes to the right C-role
/cs:founder-mode - — founder interview →
/cs:onboardcompany-context.md - — multi-model consensus
/cs:cross-eval - — cooldown lock on a decision
/cs:freeze
强制提问办公时间(8个):
- — YC风格的6问题导入
/cs:office-hours - — 单位经济效益、现金流runway、股权稀释
/cs:cfo-review - — ICP、CAC回收期、定位策略
/cs:cmo-review - — RICE框架、JTBD、北极星指标、PMF
/cs:cpo-review - — 销售漏斗覆盖率、赢单率、NRR
/cs:cro-review - — 架构风险、规模化瓶颈
/cs:cto-review - — 威胁模型、影响范围、合规性
/cs:ciso-review - — 合同、知识产权、监管要求、条款清单
/cs:gc-review
战略冲刺流程(5个):
- (简报)→
/cs:brief(董事会审议)→/cs:boardroom(决策)→/cs:decide(执行)→/cs:execute(事后复盘)/cs:post-mortem
元功能与安全(4个):
- — 自动路由至对应C级角色
/cs:founder-mode - — 创始人访谈 → 生成
/cs:onboardcompany-context.md - — 跨模型共识
/cs:cross-eval - — 决策冷却锁定
/cs:freeze
Quick Start
快速开始
/cs:onboard # populate company context first
/cs:office-hours "should we hire a VP Sales?"
/cs:founder-mode "runway pressure" # auto-routes to CFO
/cs:boardroom briefs/pricing-v3.md # full panel/cs:onboard # 先填充公司上下文
/cs:office-hours "should we hire a VP Sales?"
/cs:founder-mode "runway pressure" # 自动路由至CFO
/cs:boardroom briefs/pricing-v3.md # 全团队审议Architecture
架构
User question
│
├─ Single-role? → cs-{role}-advisor agent
│ ↓
│ /cs:{role}-review command (forcing Qs)
│ ↓
│ Skill tools + references
│ ↓
│ Bottom Line + Memo
│
└─ Multi-role? → /cs:boardroom
↓
6-phase deliberation (Phase 2 isolation)
↓
/cs:decide → decision-logger (two-layer memory)
↓
/cs:execute → 90-day plan用户问题
│
├─ 单角色?→ cs-{role}-advisor agent
│ ↓
│ /cs:{role}-review命令(强制提问)
│ ↓
│ 技能工具+参考资料
│ ↓
│ 核心结论+备忘录
│
└─ 多角色?→ /cs:boardroom
↓
6阶段审议(第二阶段独立思考)
↓
/cs:decide → 决策日志器(双层记忆)
↓
/cs:execute → 90天计划Integration Points
集成点
- Existing 28 c-level skills — wrapped, not replaced
- decision-logger — every writes here
/cs:decide - chief-of-staff — routing layer the agent orchestrates
- board-meeting — protocol the command runs
/cs:boardroom - llm-wiki — optional persistent memory bridge (see )
../references/llm-wiki-bridge.md - executive-mentor — adversarial commands stack cleanly on top
/em:*
- 现有28个C级技能 — 仅封装,不替换
- 决策日志器 — 每次都会写入此处
/cs:decide - Chief of Staff — Agent编排的路由层
- 董事会会议 — 命令执行的协议
/cs:boardroom - llm-wiki — 可选的持久化记忆桥接(查看)
../references/llm-wiki-bridge.md - executive-mentor — 对抗性命令可无缝叠加
/em:*
Design Principles
设计原则
- Voice is bookended, analysis is neutral.
- Artifacts over chat. Every command produces a Markdown artifact the next command consumes.
- Phase 2 isolation in boardroom. Independent thinking before cross-examination.
- Graceful degradation. falls back to Claude-only.
/cs:cross-eval - No paid dependencies. All Python tools are stdlib-only.
- 风格固定,分析中立。
- 优先产出工件而非聊天。 每个命令都会生成Markdown工件,供下一个命令使用。
- 董事会审议第二阶段独立思考。 交叉质询前先独立思考。
- 优雅降级。 在无其他模型时会fallback到仅使用Claude。
/cs:cross-eval - 无付费依赖。 所有Python工具均仅使用标准库。
References
参考资料
- persona-voices.md
- llm-wiki-bridge.md
- Parent c-level CLAUDE.md
- Existing executive-mentor sibling
Version: 1.0.0
Last Updated: 2026-05-12
Status: Production Ready
- persona-voices.md
- llm-wiki-bridge.md
- Parent c-level CLAUDE.md
- Existing executive-mentor sibling
版本: 1.0.0
最后更新: 2026-05-12
状态: 已就绪可投入生产