KS
Killer-Skills

create-specification — how to use create-specification how to use create-specification, create-specification setup guide, what is create-specification, create-specification alternative, create-specification vs Kuniumi, create-specification install, generate structured specification documents, create-specification workflow creation, create-specification and Go language

v1.0.0
GitHub

About this Skill

Ideal for Development Agents requiring automated documentation generation and project status tracking. create-specification is a skill that creates structured specification documents from user-provided ideas and requirements, utilizing a workflow with specific scripts and directory structures.

Features

Generates structured specification documents in Markdown format
Utilizes scripts/utils/show_current_status.sh for status checks
Extracts phase, branch, and next_idea_id from JSON output
Determines output location based on phase and directory structure
Supports creation of ideas and requirements in a portable format

# Core Topics

axsh axsh
[0]
[0]
Updated: 2/25/2026

Quality Score

Top 5%
29
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add axsh/kuniumi/create-specification

Agent Capability Analysis

The create-specification MCP Server by axsh is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use create-specification, create-specification setup guide, what is create-specification.

Ideal Agent Persona

Ideal for Development Agents requiring automated documentation generation and project status tracking.

Core Value

Empowers agents to create structured specification documents in Markdown format, utilizing shell scripts like show_current_status.sh for dynamic status checks and output location determination, and supports JSON output for seamless integration.

Capabilities Granted for create-specification MCP Server

Automating specification document generation
Determining output locations based on project phase and branch
Extracting project status information using JSON output

! Prerequisites & Limits

  • Requires execution of shell scripts like show_current_status.sh
  • Dependent on specific directory structure and file naming conventions
Project
SKILL.md
3.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Create Specification Workflow

This skill creates a structured specification document (.../ideas/.../XXX-{Name}.md) from user-provided ideas and requirements.

1. Preparation: Check Status and Context

  1. Get status:
    • Run scripts/utils/show_current_status.sh.
    • Extract phase, branch, next_idea_id from the JSON output.
    • Refer to these as [Phase], [Branch], [NextID] below.

2. Determine Output Location

  1. Directory:
    • Base path: prompts/phases/[Phase]/ideas/[Branch]/
    • Example: prompts/phases/001-webservices/ideas/main/
    • Create the directory if it does not exist.
  2. File name:
    • Format: [NextID]-[Name].md
    • [Name] should be a concise label that describes the spec (e.g. Tokenizer, RateLimit-GlobalManagement).

3. Specification Content Structure

The specification must include at least the following sections:

  1. Background: Why this feature or change is needed. Current problems or challenges. May be omitted if unknown.
  2. Requirements: Features to implement and conditions to satisfy. Concrete behaviors and constraints. Clearly distinguish mandatory vs optional requirements.
  3. Implementation Approach: Technologies and architecture to use. Overview of major components/modules. Key design decisions.
  4. Verification Scenarios:
    • IMPORTANT (Preserve Details): If the user provides specific steps, conditions, or test scenarios (e.g. "(1) do X then (2) do Y"), transcribe them here at full granularity. Do NOT summarize or fold them into "Requirements".
    • This section shares the concrete image of "what constitutes done".
    • Recommended format: numbered chronological lists.
  5. Testing for the Requirements:
    • Describe automated verification steps for each requirement.
    • IMPORTANT (Mandatory Automated Verification): Manual-only plans ("visually confirm the screen") are NOT allowed. Always specify verification commands using project-standard scripts:
      • scripts/process/build.sh
      • scripts/process/integration_test.sh
    • Map each requirement to the script/test case that verifies it.

4. Create and Save

  1. User dialogue: Listen carefully, ask clarifying questions. Organize information along the four axes: Background, Requirements, Implementation Approach, and Verification Scenarios.
    • WARNING: If the user provides concrete steps (Scenarios), do NOT silently convert them into abstract "functional requirements" and discard the steps. Always preserve them under "Verification Scenarios".
  2. Markdown formatting: Use headings, lists, tables, code blocks, and optionally Mermaid diagrams.
  3. Save the file to the determined directory.

5. Completion Check

  1. Review: Confirm the spec covers Background, Requirements, and Implementation Approach.
  2. Present file path: Show the user a link to the created file.
  3. Suggest next step: Propose creating an implementation plan if appropriate (but do NOT proceed without explicit user instruction).

Related Skills

Looking for an alternative to create-specification or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication