discuss
SolidUse when a topic benefits from multiple perspectives debating before a decision.
AI & Automation 11 stars
3 forks Updated yesterday MIT
Install
Quality Score: 82/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Moderated Multi-Agent Discussion
Start a backend-managed structured discussion with AI agents.
Pass `--user` to participate as a human observer.
## Execution
1. **If no topic is provided**: gather it interactively, plus:
- participant count (2-8, default: 4)
- debate vs open discussion
- requested roles or perspectives
2. **Analyze the topic** and prepare persona inputs.
- Identify the professional domain and the main disagreement axes.
- If geographic or institutional origin matters, prepare `demographics: { origin_weights, outlier_ratio }`.
- Write a 1-2 sentence background brief per slot.
- Assign a distinct name culture per slot.
3. **Generate persona seeds** with:
`coral-cli discuss seed --input-json -`
using the prepared `{ controversy_axes, n, demographics?, seed }` payload on stdin.
4. **Turn the seed output into personas**.
- Use the seed positions, tone, and any `suggested_origin` / `is_outlier` fields.
- Reuse your normal persona-generation workflow if you have one.
- Keep agent names stable and tool-safe.
5. **Build the agent list** and start the session.
- Required AI agents use `{ name, persona, provider?, model? }`.
- If `--user`, add:
`{ name: 'user', persona: '# User — Human Participant\nHuman observer with real-time participation via /bid skill.', participation: 'observer' }`
- Start with:
`coral-cli discuss start --input-json -` for the full `{ topic, agents, config? }` payload.
Include `c...
Details
- Author
- kangig94
- Repository
- kangig94/coral
- Created
- 6 months ago
- Last Updated
- yesterday
- Language
- TypeScript
- License
- MIT
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
discussion
Conduct an open-ended interview that discovers decision points live and records each settled decision to the thread's decision log — use when the user wants to think a topic through without knowing every question up front.
0 Updated today
Jei-sKappa AI & Automation Solid
agent-debate
Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human decision.
26 Updated 6 days ago
WenyuChiou AI & Automation Listed
agent-discussion
Use when Codex needs read-only external feedback for planning, architecture review, code discussion, strategy review, or decision support.
2 Updated 1 months ago
leviuszen