Command
mermaid
Build beautiful Mermaid diagrams using beautiful-mermaid. Covers all 6 diagram types, theming, SVG/ASCII output, and CoCo Platform integration.
@coco-researchView CommandDevelopment
Command
/think
Called by team.md router when action is `think`. Balanced pipeline: L1 researches, L2 generates options, L3 stress-tests them.
Install
$ npx -y skills add coco-research/coco --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/think
Context preview
What this command does when you run it.
Called by team.md router when action is `think`. Balanced pipeline: L1 researches, L2 generates options, L3 stress-tests them.
Command definition
think.mddescription: "Use when the user runs /team think, asks for options analysis, or wants a brainstorm before deciding. Generates structured options, stress-tests them across review layers, and returns a decision matrix with a recommendation."
/team think — Analysis & Brainstorm Pipeline
> Called by team.md router when action is `think`. > Balanced pipeline: L1 researches, L2 generates options, L3 stress-tests them.
Role Selection Bias
| Layer | Preferred Roles | Count | |-------|----------------|-------| | L1 | domain-researcher, technical-analyst, business-analyst | 3-4 | | L2 | senior-pm, senior-backend-eng or senior-frontend-eng (domain-dependent), technical-writer | 2-3 | | L3 | domain-accuracy, doc-quality | 2 | | L4 | principal-architect or principal-pm | 1 |
Pipeline Customization
Layer 1: Problem Analysis
L1 agents decompose the problem:
- **domain-researcher** → What approaches exist in the industry?
- **technical-analyst** → What are the technical constraints and options?
- **business-analyst** → What are the business constraints and stakeholder needs?
Layer 2: Option Generation
L2 agents produce structured options:
- Each option has: Description, Pros, Cons, Effort estimate, Risk assessment
- Options are compared in a decision matrix
- senior-pm frames options from product perspective
- Engineers frame options from technical perspective
**Toolkit integration:**
- Check team:toolkit.md for brainstorming tools
- Apply structured thinking frameworks (MECE, first principles, inversion)
Layer 3: Stress Testing
L3 agents challenge each option:
- What could go wrong?
- What assumptions are we making?
- What's the worst-case scenario?
- Which option survives scrutiny best?
Layer 4: Decision Recommendation
Principal produces:
- Recommended option with rationale
- Risk mitigation plan for the recommended option
- Conditions under which alternative options would be better
- Decision framework for the user to make the final call
GSD Integration
N/A — Brainstorming is project-context-independent.
Read more
description: "Use when the user runs /team think, asks for options analysis, or wants a brainstorm before deciding. Generates structured options, stress-tests them across review layers, and returns a decision matrix with a recommendation."
/team think — Analysis & Brainstorm Pipeline
> Called by team.md router when action is `think`. > Balanced pipeline: L1 researches, L2 generates options, L3 stress-tests them.
Role Selection Bias
| Layer | Preferred Roles | Count | |-------|----------------|-------| | L1 | domain-researcher, technical-analyst, business-analyst | 3-4 | | L2 | senior-pm, senior-backend-eng or senior-frontend-eng (domain-dependent), technical-writer | 2-3 | | L3 | domain-accuracy, doc-quality | 2 | | L4 | principal-architect or principal-pm | 1 |
Pipeline Customization
Layer 1: Problem Analysis
L1 agents decompose the problem:
- **domain-researcher** → What approaches exist in the industry?
- **technical-analyst** → What are the technical constraints and options?
- **business-analyst** → What are the business constraints and stakeholder needs?
Layer 2: Option Generation
L2 agents produce structured options:
- Each option has: Description, Pros, Cons, Effort estimate, Risk assessment
- Options are compared in a decision matrix
- senior-pm frames options from product perspective
- Engineers frame options from technical perspective
**Toolkit integration:**
- Check team:toolkit.md for brainstorming tools
- Apply structured thinking frameworks (MECE, first principles, inversion)
Layer 3: Stress Testing
L3 agents challenge each option:
- What could go wrong?
- What assumptions are we making?
- What's the worst-case scenario?
- Which option survives scrutiny best?
Layer 4: Decision Recommendation
Principal produces:
- Recommended option with rationale
- Risk mitigation plan for the recommended option
- Conditions under which alternative options would be better
- Decision framework for the user to make the final call
GSD Integration
N/A — Brainstorming is project-context-independent.
Ships withcoco
CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills, 280 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.
Get the whole plugin
Stats
221
Stars
11
Forks
Active
Maintenance
HTML
Language
19h ago
Last commit
4mo ago
Created
Repo: coco-research/coco
Other commands on coco.
@coco-researchView CommandCommand
Command
reply
Draft a reply to a specific email. Usage: /email-reply Project Phase 2 Contract Data
@coco-researchView CommandCommand
save
Save matching emails to a project folder for sync processing. Usage: /email-save alice to emails/
@coco-researchView CommandCommand
search
Search emails by subject keywords. Usage: /email-search github webhook
@coco-researchView CommandCommand
summary
AI summary of today's emails — key decisions, action items, meetings. No arguments needed.
@coco-researchView Command