Specification-Driven Development methodology from GitHub spec-kit. Use when users ask to create specifications, plan features, define requirements, write user stories, decompose tasks, establish project constitution, or follow SDD workflow.
/plugin marketplace add leobrival/topographic-studio-plugins/plugin install dev@topographic-plugins-officialThis skill is limited to using the following tools:
LICENSE.txtreference/constitutional-articles.mdreference/workflow-guide.mdComprehensive implementation of GitHub's spec-kit methodology where specifications become executable, directly generating functional implementations.
Source: This skill is based on the official GitHub spec-kit project - an open-source toolkit that implements Specification-Driven Development.
When a user needs to develop a feature or start a project, follow this workflow:
/speckit.constitution)/speckit.specify)/speckit.clarify - optional)/speckit.plan)/speckit.tasks)/speckit.implement)Note: The official spec-kit includes slash commands for Claude Code integration. This skill provides the same workflow without requiring the CLI installation.
SDD Request → What stage?
│
├─ New Project / Feature
│ ├─ Create constitution.md (principles)
│ ├─ Write spec.md (requirements)
│ ├─ Run clarification (5 questions)
│ ├─ Generate plan.md (technical)
│ ├─ Create tasks.md (breakdown)
│ └─ Implement according to tasks
│
├─ Existing Specifications
│ ├─ Analyze consistency across artifacts
│ ├─ Identify gaps or ambiguities
│ └─ Suggest improvements
│
└─ Documentation Only
├─ Extract specifications from code
└─ Generate reverse-engineered docs
Spec-Kit inverts traditional development:
Specifications are the first artifact, and code is their expression in a particular language.
For complete details on each article with implementation examples and validation checklists, see Constitutional Articles.
Summary:
Critical: Article III (Test-First) is non-negotiable. Write failing tests first, verify they fail, then implement.
For complete details on each phase with templates, examples, and best practices, see Workflow Guide.
Establish immutable project principles in constitution.md.
Define WHAT to build and WHY (not HOW) in spec.md. Include:
Use [NEEDS CLARIFICATION] markers for ambiguities.
Ask 5 targeted questions to eliminate ambiguity before planning.
Define HOW to implement in plan.md with:
Ensure plan completeness:
Generate tasks.md with sequential phases:
Execute tasks following Test-First approach:
Automatically apply SDD methodology when users:
If the user has the spec-kit CLI installed, they can use these slash commands in Claude Code:
Core Workflow Commands:
/speckit.constitution - Establish governing principles and development guidelines/speckit.specify - Define functional requirements and user stories (focus on what, not how)/speckit.plan - Create implementation strategy with architecture and tech stack/speckit.tasks - Generate ordered task lists with dependencies and parallel execution markers/speckit.implement - Execute implementation following task breakdownEnhancement Commands:
/speckit.clarify - Resolve ambiguities with structured questioning (recommended before planning)/speckit.analyze - Validate cross-artifact consistency across specs, plans, and tasks/speckit.checklist - Generate quality validation checklist for requirement completenessInstallation:
# Install spec-kit CLI
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git
# Initialize in current project
specify init . --ai claude
Note: This skill provides the same methodology without requiring the spec-kit CLI installation.
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 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 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.