c-level-agents – skill Agent & Tự động hóa cho agent AI

c-level-agents — Founder-Mode Executive Team

A virtual C-suite delivered through slash commands and persona agents.

Keywords

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

What This Plugin Provides

13 cs-* Agents (in 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 ../../references/persona-voices.md for voice specs.

21 /c-level-agents:* Slash Commands (in skills/)

Forcing-question office hours (12):

• /c-level-agents:office-hours — YC-style 6-question intake
• /c-level-agents:cfo-review — unit economics, runway, dilution
• /c-level-agents:cmo-review — ICP, CAC payback, positioning
• /c-level-agents:cpo-review — RICE, JTBD, North Star, PMF
• /c-level-agents:cro-review — pipeline coverage, win rate, NRR
• /c-level-agents:cto-review — architecture risk, scaling cliff
• /c-level-agents:ciso-review — threat model, blast radius, compliance
• /c-level-agents:gc-review — contracts, IP, regulatory, term sheets
• /c-level-agents:cdo-review — training-data rights, data products, data assets
• /c-level-agents:caio-review — model selection, evals, AI risk, AI costs
• /c-level-agents:cco-review — GRR/NRR decomposition, churn root cause, CS coverage
• /c-level-agents:vpe-review — DORA metrics, cycle time, eng hiring funnel, team structure

Strategic sprint pipeline (5):

• /c-level-agents:brief → /c-level-agents:boardroom → /c-level-agents:decide → /c-level-agents:execute → /c-level-agents:post-mortem

Meta + safety (4):

• /c-level-agents:founder-mode — auto-routes to the right C-role
• /cs-onboard — founder interview → company-context.md
• /c-level-agents:cross-eval — multi-model consensus
• /c-level-agents:freeze — cooldown lock on a decision

Quick Start

/cs-onboard                          # populate company context first
/c-level-agents:office-hours "should we hire a VP Sales?"
/c-level-agents:founder-mode "runway pressure"   # auto-routes to CFO
/c-level-agents:boardroom briefs/pricing-v3.md   # full panel

Architecture

User question
   │
   ├─ Single-role? → cs-{role}-advisor agent
   │                     ↓
   │                  /cs-{role}-review command (forcing Qs)
   │                     ↓
   │                  Skill tools + references
   │                     ↓
   │                  Bottom Line + Memo
   │
   └─ Multi-role?  → /c-level-agents:boardroom
                        ↓
                     6-phase deliberation (Phase 2 isolation)
                        ↓
                     /c-level-agents:decide → decision-logger (two-layer memory)
                        ↓
                     /c-level-agents:execute → 90-day plan

Integration Points

• Existing 33 c-level skills — wrapped, not replaced
• decision-logger — every /c-level-agents:decide writes here
• chief-of-staff — routing layer the agent orchestrates
• board-meeting — protocol the /c-level-agents:boardroom command runs
• llm-wiki — optional persistent memory bridge (see ../../references/llm-wiki-bridge.md)
• executive-mentor — adversarial /em:* commands stack cleanly on top

Design Principles

1. Voice is bookended, analysis is neutral.

2. Artifacts over chat. Every command produces a Markdown artifact the next command consumes.

3. Phase 2 isolation in boardroom. Independent thinking before cross-examination.

4. Graceful degradation. /c-level-agents:cross-eval falls back to Claude-only.

5. No paid dependencies. All Python tools are stdlib-only.

References

• [persona-voices.md](../../references/persona-voices.md)
• [llm-wiki-bridge.md](../../references/llm-wiki-bridge.md)
• [Parent c-level CLAUDE.md](../../../CLAUDE.md)
• [Existing executive-mentor sibling](../../../c-level-advisor/executive-mentor/)

---

Version: 1.0.0

Last Updated: 2026-05-12

Status: Production Ready