debate

GitHub

协调 Claude 和 GPT 进行多轮交叉批判与辩论,最终由 Agent 综合双方观点生成合成答案。适用于需要深度压力测试和多视角权衡的复杂问题场景。

examples/debby/skills/debate/SKILL.md omnigent-ai/omnigent

Trigger Scenarios

用户要求多个 AI 模型互相批评或辩论 需要对复杂问题进行多视角深度验证以达成共识

Install

npx skills add omnigent-ai/omnigent --skill debate -g -y
More Options

Non-standard path

npx skills add https://github.com/omnigent-ai/omnigent/tree/main/examples/debby/skills/debate -g -y

Use without installing

npx skills use omnigent-ai/omnigent@debate

指定 Agent (Claude Code)

npx skills add omnigent-ai/omnigent --skill debate -a claude-code -g -y

安装 repo 全部 skill

npx skills add omnigent-ai/omnigent --all -g -y

预览 repo 内 skill

npx skills add omnigent-ai/omnigent --list

SKILL.md

Frontmatter
{
    "name": "debate",
    "description": "Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a synthesis. Use when the user wants the two perspectives stress-tested against each other, not just shown side by side."
}

debate — make the two partners argue it out

Normally Debby fans a question out to both partners and shows the two answers side by side. debate goes further: it relays each partner's answer to the other partner for criticism, loops that for a configurable number of rounds, and then converges on a synthesis.

Rounds

The user picks how many rounds of back-and-forth to run. Default: 1 round. A "round" is one full cross-critique exchange (each partner sees and criticizes the other's latest answer). Honor an explicit count from the user ("debate this for 3 rounds"); otherwise run 1.

Procedure

  1. Round 0 — collect the opening answers. If you do not already have a fresh answer from each partner for this question, dispatch it to both claude and gpt in parallel via sys_session_send (ANSWER mode), give each call a stable per-partner title — the topic with the partner's name attached (e.g. debate-pricing-claude / debate-pricing-gpt), end your turn, and collect both with sys_read_inbox. If you already showed the user both answers this turn, reuse those as round 0.

  2. For each debate round (default 1):

    • Send claude the OTHER partner's latest answer (GPT's) and ask it to critique that answer and then give its own updated answer (CRITIQUE mode). Reuse that partner's own title so it continues its thread.
    • Send gpt the OTHER partner's latest answer (Claude's) and ask the same. Dispatch both in the same turn so they run concurrently.
    • End your turn; collect both updated answers with sys_read_inbox.
    • Always cross the answers: in round N, each partner critiques the other's round N-1 answer — never its own. Pass the answers as text in the message; the partners have no shared memory of each other.
  3. Converge. After the final round, write the synthesis yourself:

    ## 🟠 Claude — final
    <Claude's last answer, lightly trimmed>
    
    ## 🔵 GPT — final
    <GPT's last answer, lightly trimmed>
    
    ## How the debate moved them
    <2-4 bullets: what each conceded, what each held, where they
     ultimately agreed or still disagree>
    
    ## Synthesis
    <your even-handed convergence — the strongest combined answer,
     flagging any genuine remaining disagreement rather than papering
     over it>
    

Notes

  • Keep it even-handed. You are the moderator, not a third debater — your own opinion enters only in the Synthesis, and even there it is a synthesis of the two, not a new position.
  • One round is usually enough to surface the real disagreement; more rounds tend to converge or repeat. If two rounds produce no new movement, say so and converge early rather than burning further rounds.
  • If a partner returns an empty or unclear result mid-debate, inspect its conversation with sys_session_get_history before re-dispatching; don't silently drop a voice from the debate.

Version History

  • a8f41cb Current 2026-08-12 09:03

Same Skill Collection

.claude/skills/antigravity-sdk-e2e-dev/SKILL.md
.claude/skills/copilot-sdk-e2e-dev/SKILL.md
.claude/skills/cursor-sdk-e2e-dev/SKILL.md
.claude/skills/harness-integration-guide/SKILL.md
.claude/skills/pi-native-e2e-dev/SKILL.md
deploy/docker/SKILL.md
examples/deep-research/skills/deep-research/SKILL.md
examples/polly/skills/cross-review/SKILL.md
examples/polly/skills/fanout/SKILL.md
examples/polly/skills/investigate/SKILL.md
examples/scribe/skills/api-docs/SKILL.md
examples/scribe/skills/changelog/SKILL.md
examples/scribe/skills/migration-guide/SKILL.md
examples/sentinel/skills/security-audit/SKILL.md
omnigent/onboarding/agent/skills/build-omnigent/SKILL.md
omnigent/onboarding/agent/skills/detect-framework/SKILL.md
omnigent/onboarding/agent/skills/omnigent-knowledge/SKILL.md
.claude/skills/antigravity-native-e2e-dev/SKILL.md
.claude/skills/cli-setup-verify/SKILL.md
.claude/skills/polly-e2e-dev/SKILL.md
.claude/skills/run-load-test/SKILL.md

Metadata

Files
0
Version
a8f41cb
Hash
90be81a2
Indexed
2026-08-12 09:03

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-12 17:55
浙ICP备14020137号-1 $Гость$