Skip to content
Automation
Command

/spec

NLSpec authoring - Structured specification from multi-AI research

From plugin
octo
4.1k53 skills49 agents53 commands18 hooks
Install
> /plugin marketplace add nyldn/claude-octopus

How 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/spec

Context preview

What this command does when you run it.

NLSpec authoring - Structured specification from multi-AI research

Command definition

spec.md
command: spec
disable-model-invocation: true
description: "NLSpec authoring - Structured specification from multi-AI research"
aliases:
  - nlspec
  - specification

Spec - NLSpec Authoring

INSTRUCTIONS FOR CLAUDE

When the user invokes this command (e.g., `/octo:spec <arguments>`):

**CORRECT - Read the explicit workflow source:**

Read ${HOME}/.claude-octopus/plugin/.claude/skills/flow-spec/SKILL.md, then execute it with <user's arguments>

**INCORRECT:**

Skill(skill: "flow-spec", ...)  ❌ Wrong! Octopus skills are model-invocation disabled
Task(subagent_type: "octo:spec", ...)  ❌ Wrong! This is a skill, not an agent type

---

**Auto-loads the spec skill for NLSpec authoring.**

Quick Usage

Just describe what you want to specify:

"Specify a user authentication system"
"Create a spec for real-time chat"
"Define requirements for payment processing"

What Is Spec?

NLSpec (Natural Language Specification) authoring:

  • Structured specification from multi-AI research
  • Question-first approach to understand scope
  • Probe-based research for domain context
  • Validated completeness checking

What You Get

  • Multi-AI research (Claude + Antigravity + Codex) on the domain
  • Structured NLSpec with behaviors, actors, constraints
  • Adversarial completeness challenge from a second provider (surfaces missing requirements and overlooked edge cases)
  • Completeness validation with scoring
  • Saved specification file for downstream workflows

When To Use

  • Starting a new project from scratch
  • Defining requirements before implementation
  • Creating a specification for handoff
  • Establishing acceptance criteria upfront

Natural Language Examples

"Specify an OAuth 2.0 authentication system"
"Create a spec for a REST API gateway"
"Define the requirements for a CI/CD pipeline"
Read more
Ships withocto

Every AI model has blind spots. Claude Octopus supports twelve external provider integrations — Codex, Antigravity CLI, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OrcaRouter, OpenCode, Cursor CLI, Grok, and Kimi Code — alongside the built-in Claude Code

Get the whole plugin

Other commands on octo.