debate-kickoff SKILL.md skillA

debate-kickoff from nyldn/claude-octopus is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nyldn/claude-octopus/debate-kickoff@git:20260813.14437ae

Pins git:20260813.14437ae in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
nyldn/claude-octopus
Path
skills/octopus-starter-pack/debate-kickoff/SKILL.md
Versions recorded
2
Latest version
git:20260813.14437ae, committed Aug 13, 2026
First version recorded
Jul 8, 2026
Size
1,865 bytes
Repository stars
4,409
License
MIT

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

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nyldn/claude-octopus/debate-kickoff@sha256:0408325c9f4e720c

The line at the top of this page pins the label git:20260813.14437ae, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_g55knzblp7nass2s.svg)](https://markdownregistry.com/a/art_g55knzblp7nass2s)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 8, 2026 and Aug 13, 2026, about one every 36 days.

versioncommittedcommitsizeaudit
git:20260813.14437ae latest2026-08-13 14437ae 1,865 BA view · diff
git:20260708.7f668892026-07-08 7f66889 1,834 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1865 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

nyldn/claude-octopus · 4,409 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_g55knzblp7nass2s
GET https://markdownregistry.com/api/v1/resolve?ref=nyldn/claude-octopus/debate-kickoff
GET https://markdownregistry.com/api/v1/blob/0408325c9f4e720ce266fa1cc144c6f521592a6e4edd3821a5cd92ef23602c08

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nyldn/claude-octopus

skill-extract SKILL.md skill
nyldn/claude-octopus · .claude/skills/extract-skill/SKILL.md · Reverse-engineer design systems, tokens, and components from live products or screenshots
git:20260813.14437ae · audit A · 4,409 stars
flow-define SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-define/SKILL.md · Multi-AI requirements scoping using available external providers (Double Diamond Define phase). Priority triggers: octo…
git:20260929.dbf6863 · audit A · 4,409 stars
flow-deliver SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-deliver/SKILL.md · Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)
git:20261108.8380d65 · audit A · 4,409 stars
flow-develop SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-develop/SKILL.md · Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code…
git:20261002.5c257fc · audit A · 4,409 stars
flow-discover SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-discover/SKILL.md · Multi-AI research using available external providers (Double Diamond Discover phase)
git:20260929.dbf6863 · audit A · 4,409 stars
flow-parallel SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-parallel/SKILL.md · Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
git:20261007.9f7aada · audit A · 4,409 stars
flow-spec SKILL.md skill
nyldn/claude-octopus · .claude/skills/flow-spec/SKILL.md · NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
git:20261002.5c257fc · audit A · 4,409 stars
skill-agent-topology SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-agent-topology/SKILL.md · Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels…
git:20260813.14437ae · audit A · 4,409 stars
octopus-architecture SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-architecture/SKILL.md · Review system architecture, simplify boundaries, or compare interface designs from repository evidence
git:20260907.4febbb1 · audit A · 4,409 stars
skill-audit SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-audit/SKILL.md · Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
git:20260907.4febbb1 · audit A · 4,409 stars
skill-authoring SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
git:20261108.8380d65 · audit A · 4,409 stars
skill-code-review SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-code-review/SKILL.md · Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
git:20261108.8380d65 · audit A · 4,409 stars

Every file in nyldn/claude-octopus

Browse by kind, by grade A, or by owner.