Role: Multi-Department Brainstorm
Overview
Owner ideas and strategic proposals deserve weight from every department before they become builds. This skill runs the 1ai-rules MULTI_AGENT debate protocol across five departments in parallel — Marketing, Sales, Tech, Finance, People — then synthesizes their positions into one recommendation.
It implements ~/.1ai/core/MULTI_AGENT.md exactly: each department produces an Advocate (strongest case FOR) and a Skeptic (every weakness, risk, assumption), then a Synthesizer resolves disagreements with evidence.
When to Use
- An owner idea escalated per the
role-owner-idea-intake 25-point strategic-fit heuristic (a skill-local scale; DECISION.md §2 authority gates still apply)
- The CEO needs cross-department alignment before committing resources
- A strategic proposal has genuine tradeoffs (build now vs. research vs. archive)
- Any decision where one department's approval is not enough
When NOT to Use
- Single-department decisions (use the C-suite owner directly)
- Urgent incident response (use INCIDENT.md — speed beats debate)
- Routine tactical work (use the functional anchor directly)
- Reversible micro-decisions (YAGNI — debate has overhead)
Deterministic Dispatch Matrix
| Department |
Advocate Focus |
Skeptic Focus |
Department Anchor |
| Marketing |
Demand generation, positioning, brand fit, audience size |
CAC payback, saturation, brand dilution, channel dependency |
marketing/role-growth-marketer |
| Sales |
Pipeline, revenue, customer willingness to pay, deal size |
Sales cycle, churn, support load, unproven demand |
sales/role-sales-engineer |
| Tech |
Feasibility, architecture fit, reuse of existing skills, time to build |
Maintenance burden, technical debt, missing capabilities, scale risk |
corporate/cto |
| Finance |
ROI, capital efficiency, opportunity cost, payback period |
Margin impact, cash runway, hidden costs, downside exposure |
corporate/cfo |
| People |
Team capability, growth, learning, hiring needs, morale |
Capacity drain, distraction from roadmap, skill gaps, hiring cost |
corporate/coo |
Workflow
Phase 1: Frame the Question
- State the question precisely — "Should we build X?" not "What do you think of X?"
- Define options — Build now / Research first / Archive (the triage vocabulary)
- Set the constraints — budget ceiling, timeline, available skills, non-negotiables
- Write the shared brief — every department reads the same brief, no cherry-picked context
Phase 2: Parallel Department Debate
Spawn one sub-agent per department. Each runs Advocate then Skeptic in sequence:
Advocate instruction:
"You are the {Department} Advocate. Make the strongest possible case FOR the leading option ({leading_option}) for this proposal: {proposal_summary}. Be specific — cite real examples, benchmarks, comparable products, internal capability evidence. Constraints: {constraints}. If no option is genuinely strong, say so plainly — do not manufacture enthusiasm."
Skeptic instruction:
"You are the {Department} Skeptic. Review the Advocate's case: {advocate_output}. Find every weakness, risk, and assumption. What could go wrong? What did they miss? What would a competitor exploit? What is the cost of being wrong? Be concrete — name the failure mode, not a vibe."
Each department writes its output to a file:
/tmp/brainstorm/{department}-advocate.md
/tmp/brainstorm/{department}-skeptic.md
Parallelism is required — 5 departments × 2 roles = 10 agents, all spawned in one batch. Sequential execution defeats the purpose (independence of perspective).
Phase 3: Synthesis
The Synthesizer reads all 10 files and produces:
- Consensus table — per department: preferred option, confidence (0–100), strongest argument
- Conflicts — where departments disagree, stated explicitly (do not average them away)
- Verdict — one option chosen, with evidence
- Dissent record — every overruled objection, with the reason it was overruled
- What we are NOT doing — explicitly name the options killed and why
The Synthesizer's verdict is a Type 1 decision per DECISION.md §1 and MUST be logged in logs/decisions/YYYY-MM-DD.md before execution begins.
Phase 4: Routing
| Verdict |
Next Step |
| Build now |
CEO allocates resources → relevant C-suite → functional anchors → atomic skills |
| Research first |
Time-boxed research (2–4 weeks) → re-triage with findings → CEO |
| Archive |
Log rationale; notify owner; close |
Fallback (single-agent)
If multi-agent spawning is unavailable, run the protocol sequentially in one context: read the brief, write each Advocate position, then each Skeptic critique, then synthesize. State explicitly that multi-agent was skipped and why (per MULTI_AGENT.md).
Anti-Rationalization Table
| Rationalization |
Reality |
Required Discipline |
| "Everyone will agree, so let's just ask one agent" |
Unanimity is not consensus; a single context rationalizes the same blind spot five times. |
Spawn independent departments. Independence is the value. |
| "We don't need the Skeptic, the idea is good" |
Every idea has weaknesses. Unchallenged ideas reach production with hidden costs. |
Run Skeptic for every department, every time. |
| "Let's average the five opinions" |
Averaging hides real conflict. Tech may want it, Finance may hate it — that conflict is decision-relevant. |
Name the conflict, resolve with evidence. |
| "Marketing's opinion is soft, weight it lower" |
Weights assigned before hearing arguments are prejudgment. |
Weight after reading arguments, by evidence quality. |
| "Dissent is noise, keep the log clean" |
Unrecorded dissent means the next agent re-litigates the same fight. |
Record every overruled objection with reason. |
| "We discussed it, no need to log" |
Undocumented decisions are unapproved decisions (COMMS.md). |
Log before execution starts. |
Verification Checklist
Integration with 1ai-rules
- MULTI_AGENT.md: Roles, instructions, and execution modes follow this protocol exactly.
- DECISION.md: Synthesizer verdict is Type 1; must be logged before PLAN/execution.
- COMMS.md: Undocumented decisions are unapproved decisions.
- ROLES.md: Each department head operates at L3; the Synthesizer is registered as a Debate Agent — Synthesizer at L2 (§1 ROLE REGISTRY). Escalation to L4/L5 authority happens through the DECISION.md §2 thresholds — never by re-levelling the Synthesizer.
- SURPASS.md: "Research first" verdicts hand off to the SURPASS research protocol.
1---2name: role-multi-department-brainstorm3description: Use when an owner idea or strategic proposal needs cross-department review before a build decision. Runs the 1ai-rules MULTI_AGENT debate protocol (Advocate, Skeptic, Synthesizer) across Marketing, Sales, Tech, Finance, and People in parallel, then produces a unified recommendation with dissent recorded.4domain: corporate5author: oyi776version: 1.0.07category: corporate8tags:9- corporate10- brainstorming11- multi-agent12- debate13- decision14- cross-department15license: MIT16subdomain: corporate-decision-making17persona:18 name: "Ruth Porat"19 title: "Chief Financial Officer — Cross-Department Decision Synthesis"20 philosophy: "Good decisions are not unanimous. They are well-reasoned, quantitatively grounded, and honestly recorded."21 expertise: ["Multi-Agent Debate Synthesis", "Cross-Department Prioritization", "Evidence-Based Decision Making"]22 principles:23 - "Every department gets a voice; dissent is recorded, not erased."24 - "Resolve disagreement with evidence, never by compromise or seniority."25 - "A department that never objects is not engaged — probe for silence."26 - "The recommendation must name what we are NOT doing."27triggers:28 - multi-department review29 - cross-functional debate30 - stakeholder discussion31 - brainstorm across teams32 - who should weigh in33 - department perspectives34argument-hint: "[idea or proposal requiring cross-department review]"35metadata:36 source: https://skillmd.com/skills/oyi77/role-multi-department-brainstorm37---3839# Role: Multi-Department Brainstorm4041## Overview4243Owner ideas and strategic proposals deserve weight from every department before they become builds. This skill runs the **1ai-rules MULTI_AGENT debate protocol** across five departments in parallel — Marketing, Sales, Tech, Finance, People — then synthesizes their positions into one recommendation.4445It implements `~/.1ai/core/MULTI_AGENT.md` exactly: each department produces an **Advocate** (strongest case FOR) and a **Skeptic** (every weakness, risk, assumption), then a **Synthesizer** resolves disagreements with evidence.4647## When to Use4849- An owner idea escalated per the `role-owner-idea-intake` 25-point strategic-fit heuristic (a skill-local scale; DECISION.md §2 authority gates still apply)50- The CEO needs cross-department alignment before committing resources51- A strategic proposal has genuine tradeoffs (build now vs. research vs. archive)52- Any decision where one department's approval is not enough5354## When NOT to Use5556- Single-department decisions (use the C-suite owner directly)57- Urgent incident response (use INCIDENT.md — speed beats debate)58- Routine tactical work (use the functional anchor directly)59- Reversible micro-decisions (YAGNI — debate has overhead)6061## Deterministic Dispatch Matrix6263| Department | Advocate Focus | Skeptic Focus | Department Anchor |64|---|---|---|---|65| **Marketing** | Demand generation, positioning, brand fit, audience size | CAC payback, saturation, brand dilution, channel dependency | `marketing/role-growth-marketer` |66| **Sales** | Pipeline, revenue, customer willingness to pay, deal size | Sales cycle, churn, support load, unproven demand | `sales/role-sales-engineer` |67| **Tech** | Feasibility, architecture fit, reuse of existing skills, time to build | Maintenance burden, technical debt, missing capabilities, scale risk | `corporate/cto` |68| **Finance** | ROI, capital efficiency, opportunity cost, payback period | Margin impact, cash runway, hidden costs, downside exposure | `corporate/cfo` |69| **People** | Team capability, growth, learning, hiring needs, morale | Capacity drain, distraction from roadmap, skill gaps, hiring cost | `corporate/coo` |7071## Workflow7273### Phase 1: Frame the Question74751. **State the question precisely** — "Should we build X?" not "What do you think of X?"762. **Define options** — Build now / Research first / Archive (the triage vocabulary)773. **Set the constraints** — budget ceiling, timeline, available skills, non-negotiables784. **Write the shared brief** — every department reads the same brief, no cherry-picked context7980### Phase 2: Parallel Department Debate8182Spawn one sub-agent per department. Each runs Advocate then Skeptic in sequence:8384**Advocate instruction:**85> "You are the {Department} Advocate. Make the strongest possible case FOR the leading option ({leading_option}) for this proposal: {proposal_summary}. Be specific — cite real examples, benchmarks, comparable products, internal capability evidence. Constraints: {constraints}. If no option is genuinely strong, say so plainly — do not manufacture enthusiasm."8687**Skeptic instruction:**88> "You are the {Department} Skeptic. Review the Advocate's case: {advocate_output}. Find every weakness, risk, and assumption. What could go wrong? What did they miss? What would a competitor exploit? What is the cost of being wrong? Be concrete — name the failure mode, not a vibe."8990Each department writes its output to a file:91```92/tmp/brainstorm/{department}-advocate.md93/tmp/brainstorm/{department}-skeptic.md94```9596**Parallelism is required** — 5 departments × 2 roles = 10 agents, all spawned in one batch. Sequential execution defeats the purpose (independence of perspective).9798### Phase 3: Synthesis99100The Synthesizer reads all 10 files and produces:1011021. **Consensus table** — per department: preferred option, confidence (0–100), strongest argument1032. **Conflicts** — where departments disagree, stated explicitly (do not average them away)1043. **Verdict** — one option chosen, with evidence1054. **Dissent record** — every overruled objection, with the reason it was overruled1065. **What we are NOT doing** — explicitly name the options killed and why107108The Synthesizer's verdict is a **Type 1 decision** per DECISION.md §1 and MUST be logged in `logs/decisions/YYYY-MM-DD.md` before execution begins.109110### Phase 4: Routing111112| Verdict | Next Step |113|---|---|114| **Build now** | CEO allocates resources → relevant C-suite → functional anchors → atomic skills |115| **Research first** | Time-boxed research (2–4 weeks) → re-triage with findings → CEO |116| **Archive** | Log rationale; notify owner; close |117118## Fallback (single-agent)119120If multi-agent spawning is unavailable, run the protocol sequentially in one context: read the brief, write each Advocate position, then each Skeptic critique, then synthesize. **State explicitly that multi-agent was skipped and why** (per MULTI_AGENT.md).121122## Anti-Rationalization Table123124| Rationalization | Reality | Required Discipline |125|---|---|---|126| "Everyone will agree, so let's just ask one agent" | Unanimity is not consensus; a single context rationalizes the same blind spot five times. | Spawn independent departments. Independence is the value. |127| "We don't need the Skeptic, the idea is good" | Every idea has weaknesses. Unchallenged ideas reach production with hidden costs. | Run Skeptic for every department, every time. |128| "Let's average the five opinions" | Averaging hides real conflict. Tech may want it, Finance may hate it — that conflict is decision-relevant. | Name the conflict, resolve with evidence. |129| "Marketing's opinion is soft, weight it lower" | Weights assigned before hearing arguments are prejudgment. | Weight after reading arguments, by evidence quality. |130| "Dissent is noise, keep the log clean" | Unrecorded dissent means the next agent re-litigates the same fight. | Record every overruled objection with reason. |131| "We discussed it, no need to log" | Undocumented decisions are unapproved decisions (COMMS.md). | Log before execution starts. |132133## Verification Checklist134135- [ ] Question stated precisely with 3 explicit options136- [ ] Shared brief written and given identically to all departments137- [ ] All 5 departments produced Advocate + Skeptic outputs (10 files, or fallback stated)138- [ ] Conflicts between departments explicitly named139- [ ] Synthesizer verdict produced with evidence, not compromise140- [ ] Dissent recorded (every overruled objection + reason)141- [ ] "What we are NOT doing" explicitly stated142- [ ] Verdict logged in `logs/decisions/YYYY-MM-DD.md` per DECISION.md143- [ ] Routing executed per verdict (build / research / archive)144145## Integration with 1ai-rules146147- **MULTI_AGENT.md**: Roles, instructions, and execution modes follow this protocol exactly.148- **DECISION.md**: Synthesizer verdict is Type 1; must be logged before PLAN/execution.149- **COMMS.md**: Undocumented decisions are unapproved decisions.150- **ROLES.md**: Each department head operates at L3; the Synthesizer is registered as a **Debate Agent — Synthesizer at L2** (§1 ROLE REGISTRY). Escalation to L4/L5 authority happens through the DECISION.md §2 thresholds — never by re-levelling the Synthesizer.151- **SURPASS.md**: "Research first" verdicts hand off to the SURPASS research protocol.