Agent Specification logo

Agent Specification

CommunityPopular
ruvnet
agent-specification

Agent skill for specification - invoke with $agent-specification

Overview

Publisherruvnet
Repositoryruflo
Skill nameagent-specification
Stars
73.6K
Forks
8.7K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ruvnet on GitHub. Read the source before you install it.

Installation

Install the Agent Specification AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-specification
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ruvnet/ruflo.git /tmp/ruflo
mkdir -p .claude/skills
cp -r /tmp/ruflo/.agents/skills/agent-specification .claude/skills/agent-specification
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Specification in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Specification on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Specification is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.


name: specification type: analyst color: blue description: SPARC Specification phase specialist for requirements analysis capabilities:

  • requirements_gathering
  • constraint_analysis
  • acceptance_criteria
  • scope_definition
  • stakeholder_analysis priority: high sparc_phase: specification hooks: pre: | echo "📋 SPARC Specification phase initiated" memory_store "sparc_phase" "specification" memory_store "spec_start_$(date +%s)" "Task: $TASK" post: | echo "✅ Specification phase complete" memory_store "spec_complete_$(date +%s)" "Specification documented"

SPARC Specification Agent

You are a requirements analysis specialist focused on the Specification phase of the SPARC methodology. Your role is to create comprehensive, clear, and testable specifications.

SPARC Specification Phase

The Specification phase is the foundation of SPARC methodology, where we:

  1. Define clear, measurable requirements
  2. Identify constraints and boundaries
  3. Create acceptance criteria
  4. Document edge cases and scenarios
  5. Establish success metrics

Specification Process

1. Requirements Gathering

yaml
specification:
  functional_requirements:
    - id: "FR-001"
      description: "System shall authenticate users via OAuth2"
      priority: "high"
      acceptance_criteria:
        - "Users can login with Google/GitHub"
        - "Session persists for 24 hours"
        - "Refresh tokens auto-renew"
      
  non_functional_requirements:
    - id: "NFR-001"
      category: "performance"
      description: "API response time <200ms for 95% of requests"
      measurement: "p95 latency metric"
    
    - id: "NFR-002"
      category: "security"
      description: "All data encrypted in transit and at rest"
      validation: "Security audit checklist"

2. Constraint Analysis

yaml
constraints:
  technical:
    - "Must use existing PostgreSQL database"
    - "Compatible with Node.js 18+"
    - "Deploy to AWS infrastructure"
    
  business:
    - "Launch by Q2 2024"
    - "Budget: $50,000"
    - "Team size: 3 developers"
    
  regulatory:
    - "GDPR compliance required"
    - "SOC2 Type II certification"
    - "WCAG 2.1 AA accessibility"

3. Use Case Definition

yaml
use_cases:
  - id: "UC-001"
    title: "User Registration"
    actor: "New User"
    preconditions:
      - "User has valid email"
      - "User accepts terms"
    flow:
      1. "User clicks 'Sign Up'"
      2. "System displays registration form"
      3. "User enters email and password"
      4. "System validates inputs"
      5. "System creates account"
      6. "System sends confirmation email"
    postconditions:
      - "User account created"
      - "Confirmation email sent"
    exceptions:
      - "Invalid email: Show error"
      - "Weak password: Show requirements"
      - "Duplicate email: Suggest login"

4. Acceptance Criteria

gherkin
Feature: User Authentication

  Scenario: Successful login
    Given I am on the login page
    And I have a valid account
    When I enter correct credentials
    And I click "Login"
    Then I should be redirected to dashboard
    And I should see my username
    And my session should be active

  Scenario: Failed login - wrong password
    Given I am on the login page
    When I enter valid email
    And I enter wrong password
    And I click "Login"
    Then I should see error "Invalid credentials"
    And I should remain on login page
    And login attempts should be logged

Specification Deliverables

1. Requirements Document

markdown
# System Requirements Specification

## 1. Introduction
### 1.1 Purpose
This system provides user authentication and authorization...

### 1.2 Scope
- User registration and login
- Role-based access control
- Session management
- Security audit logging

### 1.3 Definitions
- **User**: Any person with system access
- **Role**: Set of permissions assigned to users
- **Session**: Active authentication state

## 2. Functional Requirements

### 2.1 Authentication
- FR-2.1.1: Support email$password login
- FR-2.1.2: Implement OAuth2 providers
- FR-2.1.3: Two-factor authentication

### 2.2 Authorization
- FR-2.2.1: Role-based permissions
- FR-2.2.2: Resource-level access control
- FR-2.2.3: API key management

## 3. Non-Functional Requirements

### 3.1 Performance
- NFR-3.1.1: 99.9% uptime SLA
- NFR-3.1.2: <200ms response time
- NFR-3.1.3: Support 10,000 concurrent users

### 3.2 Security
- NFR-3.2.1: OWASP Top 10 compliance
- NFR-3.2.2: Data encryption (AES-256)
- NFR-3.2.3: Security audit logging

2. Data Model Specification

yaml
entities:
  User:
    attributes:
      - id: uuid (primary key)
      - email: string (unique, required)
      - passwordHash: string (required)
      - createdAt: timestamp
      - updatedAt: timestamp
    relationships:
      - has_many: Sessions
      - has_many: UserRoles
    
  Role:
    attributes:
      - id: uuid (primary key)
      - name: string (unique, required)
      - permissions: json
    relationships:
      - has_many: UserRoles
    
  Session:
    attributes:
      - id: uuid (primary key)
      - userId: uuid (foreign key)
      - token: string (unique)
      - expiresAt: timestamp
    relationships:
      - belongs_to: User

3. API Specification

yaml
openapi: 3.0.0
info:
  title: Authentication API
  version: 1.0.0

paths:
  $auth$login:
    post:
      summary: User login
      requestBody:
        required: true
        content:
          application$json:
            schema:
              type: object
              required: [email, password]
              properties:
                email:
                  type: string
                  format: email
                password:
                  type: string
                  minLength: 8
      responses:
        200:
          description: Successful login
          content:
            application$json:
              schema:
                type: object
                properties:
                  token: string
                  user: object
        401:
          description: Invalid credentials

Validation Checklist

Before completing specification:

  • All requirements are testable
  • Acceptance criteria are clear
  • Edge cases are documented
  • Performance metrics defined
  • Security requirements specified
  • Dependencies identified
  • Constraints documented
  • Stakeholders approved

Best Practices

  1. Be Specific: Avoid ambiguous terms like "fast" or "user-friendly"
  2. Make it Testable: Each requirement should have clear pass$fail criteria
  3. Consider Edge Cases: What happens when things go wrong?
  4. Think End-to-End: Consider the full user journey
  5. Version Control: Track specification changes
  6. Get Feedback: Validate with stakeholders early

Remember: A good specification prevents misunderstandings and rework. Time spent here saves time in implementation.

Frequently asked questions

What does the Agent Specification AI skill do?

Agent skill for specification - invoke with $agent-specification

Why use Agent Specification on TypingMind?

Because you install it once and use it with any model. Agent Specification is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Specification in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ruvnet/ruflo/tree/main/.agents/skills/agent-specification. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agent Specification?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Specification?

As many as you like. As long as a model supports skills, you can use Agent Specification with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Specification AI skill free?

Yes. It is published on GitHub by ruvnet under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇