Generate a specification file from user input/requirements. Use when user says "generate spec", "create spec", "write spec", "spec from requirements", or provides feature requirements and asks to create a spec. (user)
/plugin marketplace add teliha/dev-workflows/plugin install dev-workflows@dev-workflowsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Transform user input (requirements, ideas, feature requests) into a structured specification file.
This skill activates when:
Accept various forms of input:
Use --context or -c to specify files to read as background context:
generate spec -c docs/requirements.md from: ユーザー認証
generate spec -c design/*.md -c notes.txt from: 決済機能
generate spec --context existing-api.yaml from: API拡張
The skill will:
Generate specs/[feature-name]/spec.md with structured content.
Extract from user input:
If input is too vague, ask about:
Create a structured spec file following this template:
# [Feature Name] Specification
## Overview
[Brief description of the feature]
## Purpose
[What problem this solves, business value]
## Scope
### In Scope
- [Feature 1]
- [Feature 2]
### Out of Scope
- [Excluded item 1]
- [Excluded item 2]
## Functional Requirements
### 1. [Feature/Endpoint Name]
**Endpoint**: `METHOD /api/path`
**Request**:
```json
{
"field": "type (constraints, required/optional)"
}
Response (2xx):
{
"data": {},
"meta": {}
}
Validation:
| HTTP | Code | Condition |
|---|---|---|
| 400 | ERROR_CODE | [condition] |
| Input | Expected |
|---|---|
| [case] | [behavior] |
Given [precondition] When [action] Then [expected result]
### Step 4: Write File
1. Create directory `specs/[feature-name]/`
2. Write `spec.md`
3. Report completion
## Precision Levels
The `--precision` or `-p` flag controls spec detail level:
| Level | Detail |
|-------|--------|
| 10-30% | Overview, scope, basic requirements only |
| 40-60% | + API design, validation rules |
| 70-80% | + Edge cases, error codes |
| 90-100% | + Detailed acceptance criteria, test scenarios |
**Default**: 70%
### Usage Examples
generate spec from: ユーザー認証機能が欲しい generate spec -p 30 from: 簡単な TODO アプリ generate spec --precision 100 from: [detailed requirements]
### Precision 30% Output (Quick)
```markdown
# Feature Specification
## Overview
[1-2 sentences]
## Scope
### In Scope
- [3-5 bullet points]
### Out of Scope
- [2-3 bullet points]
## Key Requirements
- [5-10 bullet points of main features]
Full template with:
Full template plus:
generate-spec-docs skill after to create Japanese documentationspec-review skillThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.