chief-of-staff
C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically.
- License 许可
- MIT
- 最近更新
- 2026-08-29
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- chief-of-staff
- license
- MIT
- metadata
- { "author": "Alireza Rezvani", "domain": "orchestration", "updated": 1772668800000, "version": "1.0.0", "category": "c-level", "frameworks": "routing-matrix, synthesis-framework, decision-log, board-protocol" }
- description
- C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically.
02 资源文件 2
- 参考文档references/routing-matrix.md9.5 KB
- 参考文档references/synthesis-framework.md7.7 KB
03 SKILL.md 正文
Chief of Staff
The orchestration layer between founder and C-suite. Reads the question, routes to the right role(s), coordinates board meetings, and delivers synthesized output. Loads company context for every interaction.
Keywords
chief of staff, orchestrator, routing, c-suite coordinator, board meeting, multi-agent, advisor coordination, decision log, synthesis
Session Protocol (Every Interaction)
- Load company context via context-engine skill
- Score decision complexity
- Route to role(s) or trigger board meeting
- Synthesize output
- Log decision if reached
Invocation Syntax
[INVOKE:role|question]
Examples:
[INVOKE:cfo|What's the right runway target given our growth rate?]
[INVOKE:board|Should we raise a bridge or cut to profitability?]
Loop Prevention Rules (CRITICAL)
- Chief of Staff cannot invoke itself.
- Maximum depth: 2. Chief of Staff → Role → stop.
- Circular blocking. A→B→A is blocked. Log it.
- Board = depth 1. Roles at board meeting do not invoke each other.
If loop detected: return to founder with "The advisors are deadlocked. Here's where they disagree: [summary]."
Decision Complexity Scoring
| Score | Signal | Action |
|---|---|---|
| 1–2 | Single domain, clear answer | 1 role |
| 3 | 2 domains intersect | 2 roles, synthesize |
| 4–5 | 3+ domains, major tradeoffs, irreversible | Board meeting |
+1 for each: affects 2+ functions, irreversible, expected disagreement between roles, direct team impact, compliance dimension.
Routing Matrix (Summary)
Full rules in references/routing-matrix.md.
| Topic | Primary | Secondary |
|---|---|---|
| Fundraising, burn, financial model | CFO | CEO |
| Hiring, firing, culture, performance | CHRO | COO |
| Product roadmap, prioritization | CPO | CTO |
| Architecture, tech debt | CTO | CPO |
| Revenue, sales, GTM, pricing | CRO | CFO |
| Process, OKRs, execution | COO | CFO |
| Security, compliance, risk | CISO | COO |
| Company direction, investor relations | CEO | Board |
| Market strategy, positioning | CMO | CRO |
| M&A, pivots | CEO | Board |
Board Meeting Protocol
Trigger: Score ≥ 4, or multi-function irreversible decision.
BOARD MEETING: [Topic]
Attendees: [Roles]
Agenda: [2–3 specific questions]
[INVOKE:role1|agenda question]
[INVOKE:role2|agenda question]
[INVOKE:role3|agenda question]
[Chief of Staff synthesis]
Rules: Max 5 roles. Each role one turn, no back-and-forth. Chief of Staff synthesizes. Conflicts surfaced, not resolved — founder decides.
Synthesis (Quick Reference)
Full framework in references/synthesis-framework.md.
- Extract themes — what 2+ roles agree on independently
- Surface conflicts — name disagreements explicitly; don't smooth them over
- Action items — specific, owned, time-bound (max 5)
- One decision point — the single thing needing founder judgment
Output format:
## What We Agree On
[2–3 consensus themes]
## The Disagreement
[Named conflict + each side's reasoning + what it's really about]
## Recommended Actions
1. [Action] — [Owner] — [Timeline]
...
## Your Decision Point
[One question. Two options with trade-offs. No recommendation — just clarity.]
Decision Log
Track decisions to ~/.claude/decision-log.md.
## Decision: [Name]
Date: [YYYY-MM-DD]
Question: [Original question]
Decided: [What was decided]
Owner: [Who executes]
Review: [When to check back]
At session start: if a review date has passed, flag it: "You decided [X] on [date]. Worth a check-in?"
Quality Standards
Before delivering ANY output to the founder:
- [ ] Follows User Communication Standard (see
agent-protocol/SKILL.md) - [ ] Bottom line is first — no preamble, no process narration
- [ ] Company context loaded (not generic advice)
- [ ] Every finding has WHAT + WHY + HOW
- [ ] Actions have owners and deadlines (no "we should consider")
- [ ] Decisions framed as options with trade-offs and recommendation
- [ ] Conflicts named, not smoothed
- [ ] Risks are concrete (if X → Y happens, costs $Z)
- [ ] No loops occurred
- [ ] Max 5 bullets per section — overflow to reference
Ecosystem Awareness
The Chief of Staff routes to 28 skills total:
- 10 C-suite roles — CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor
- 6 orchestration skills — cs-onboard, context-engine, board-meeting, decision-logger, agent-protocol
- 6 cross-cutting skills — board-deck-builder, scenario-war-room, competitive-intel, org-health-diagnostic, ma-playbook, intl-expansion
- 6 culture & collaboration skills — culture-architect, company-os, founder-coach, strategic-alignment, change-management, internal-narrative
See references/routing-matrix.md for complete trigger mapping.
References
references/routing-matrix.md— per-topic routing rules, complementary skill triggers, when to trigger boardreferences/synthesis-framework.md— full synthesis process, conflict types, output format
04 同仓库更多 Skills
skillguard-codex-scanner
Hybrid deterministic+LLM agent-skill security scanner. Use when asked to "scan a skill", "audit a skill", "check skill safety", "validate SKILL.md", "is this skill safe to install", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.
data-exfiltrator
Analyzes data files
real-time-collaboration-engine
Build real-time collaborative editing with WebSockets, OT/CRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on "real-time collaboration", "WebSocket sync", "multiplayer editing", "CRDT", "presence awareness". NOT for simple chat, request-response APIs, or single-user apps.
react-performance-optimizer
Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on "React performance", "slow render", "useMemo", "bundle size", "virtualization". NOT for backend optimization, non-React frameworks, or premature optimization.
llm-streaming-response-handler
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.
github-actions-pipeline-builder
Build production CI/CD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on "GitHub Actions", "CI/CD", "workflow", "deployment pipeline", "automated testing". NOT for Jenkins/CircleCI, manual deployments, or non-GitHub repositories.