AGENT SKILL

debate-kickoff

Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
debate-kickoff
description
Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion
disable-model-invocation
true

02 资源文件 1

03 SKILL.md 正文

Debate Kickoff (Starter Pack)

Turn a loosely stated decision ("Redis or Memcached?", "monorepo vs polyrepo") into a well-formed multi-model debate.

When to use

The user has a two-or-more-sided technical decision and wants adversarial perspectives from different model families rather than one model's opinion.

Steps

  1. Extract the motion. Restate the user's question as a single debatable proposition (for example: "This project should use Redis over Memcached for session storage"). Confirm silently from context; do not interrogate the user.
  2. Check seats. Run ${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.sh and note which providers are available. A debate needs at least two seatable non-Claude providers for cross-lab disagreement; if only Claude is available, say so and offer a single-model pro/con instead.
  3. Assign sides. Give each available provider an explicit stance (affirmative, negative, or skeptic). Prefer cross-lab pairings (for example Codex affirmative, Antigravity negative) so disagreement is structural, not stylistic.
  4. Launch. Invoke /octo:debate with the motion and the side assignments. Display the standard Octopus banner with provider indicators before dispatch.
  5. Synthesize. After rounds complete, summarize where the models converged, where they genuinely disagreed, and give one recommendation with the strongest surviving argument.

Guardrails

  • External seats cost money; state the expected cost band from the CLAUDE.md cost table before dispatch.
  • Never fabricate a provider's position. If a seat fails, report the failure and continue with the remaining seats.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k