Sponsor Suno AI Music arrow_forward
Slash Command

Specify

Create specs from project briefs with acceptance criteria and testable requirements

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Specify is

Specify is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Specify gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Specify

Claude Code

  1. Download specify.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/attune/commands/specify.md, shared under the repository's MIT license. Read the full file on GitHub.

Transform project briefs into structured, testable specifications with functional requirements and acceptance criteria.

When To Use

Use this command when you need to:

  • Transform brainstorm output into detailed specification
  • Create testable requirements from project brief
  • Define acceptance criteria for implementation
  • Document functional and non-functional requirements
  • Establish scope boundaries before planning

When NOT To Use

Avoid this command if:

  • Still exploring problem space (use /attune:brainstorm first)
  • Already have detailed specification (use /attune:blueprint instead)
  • Need to refine existing spec (edit specification document directly)
  • Making architectural decisions without requirements (brainstorm first)

Usage

# Create specification from brainstorm output
/attune:specify

# Specify with custom input
/attune:specify --input docs/project-brief.md

# Generate specification for specific feature
/attune:specify --feature "user authentication"

What This Command Does

  1. Loads project brief from brainstorm phase
  2. Invokes specification skill with spec-kit integration
  3. Generates detailed requirements using structured format
  4. Creates testable acceptance criteria
  5. Produces specification document for planning phase

Integration with Spec-Kit

When spec-kit plugin is available:

  • Uses Skill(spec-kit:spec-writing) for specification methodology
  • Applies structured requirement templates
  • Ensures testable acceptance criteria

Without spec-kit:

  • Falls back to attune's native specification skill
  • Provides similar step-by-step approach
  • Documents requirements systematically

Workflow

# 1. Invoke specification skill
Skill(attune:project-specification)

# 2. Transform brief into structured spec:
#    - Functional requirements
#    - Non-functional requirements
#    - Acceptance criteria
#    - Technical constraints
#    - Dependencies

# 3. Generate specification document
#    - Saved to docs/specification.md
#    - Includes all requirements with testability

# 4. Workflow auto-continues (see below)

Workflow Continuation Protocol (MANDATORY)

After specification completes successfully, auto-proceed to the next phase unless --standalone was specified:

  1. Verify artifact: Confirm docs/specification.md exists and is non-empty
  2. Checkpoint message: Display brief summary to user:
   Specification complete. Saved to docs/specification.md.
   Proceeding to planning phase...
  1. Auto-invoke next phase:
   Skill(attune:project-planning)

Bypass Conditions (skip auto-continuation if ANY true):

  • --standalone flag was provided
  • docs/specification.md does not exist or is empty
  • User explicitly requests to stop after specification

Specification Structure

Section 1: Overview

  • Purpose: What this project achieves
  • Scope: What's included and excluded
  • Stakeholders: Who cares about this project

Section 2: Functional Requirements

Format per requirement:

### FR-001: [Requirement Name]

**Description**: Clear description of the requirement

**Acceptance Criteria**:
- [ ] Given [context], when [action], then [expected result]
- [ ] Given [context], when [action], then [expected result]

**Priority**: High | Medium | Low
**Dependencies**: FR-002, FR-005
**Estimated Effort**: S | M | L | XL

Section 3: Non-Functional Requirements

Categories:

  • Performance: Response times, throughput, resource usage
  • Security: Authentication, authorization, data protection
  • Reliability: Uptime, error handling, recovery
  • Usability: UX requirements, accessibility
  • Maintainability: Code quality, documentation, testing

Section 4: Technical Constraints

  • Technology stack: Languages, frameworks, tools
  • Integration points: External systems, APIs
  • Data requirements: Storage, schema, migrations
  • Deployment: Environment, CI/CD, hosting

Section 5: Out of Scope

Explicitly document what's NOT included to prevent scope creep.

Arguments

  • --input - Input brief file (default: docs/project-brief.md)
  • --output - Output spec file (default: docs/specification.md)
  • --feature - Specify single feature instead of full project
  • --clarify - Run clarification phase (like spec-kit clarify)
  • --standalone - Run only this phase; do not auto-proceed to planning

Examples

Example 1: Full Project Specification

/attune:brainstorm --domain "web application"
/attune:specify

Output: docs/specification.md

# Technical Debt Tracker - Specification

## Overview

**Purpose**: Provide systematic technical debt tracking integrated with GitHub

**Scope**:
- IN: GitHub issue integration, debt prioritization, reporting
- OUT: Multi-platform support, custom integrations, AI recommendations

**Stakeholders**:
- Development teams (primary users)
- Tech leads (debt review and prioritization)
- Engineering managers (reporting and metrics)

## Functional Requirements

### FR-001: GitHub Issue Discovery
…

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Specify?

Specify is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Create specs from project briefs with acceptance criteria and testable requirements

How do I install Specify in Claude Code?

Download specify.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Specify in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Specify safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.