spec-driven-development
Use Cautionnpx machina-cli add skill Bosh-Kuo/awesome-agent-toolkit/spec-driven-development --openclawSpec Driven Development
This skill implements an AI-Spec-Driven Development workflow that emulates "Antigravity Planning Mode". Ideally suited for complex, multi-step engineering tasks, it drastically reduces "hallucinated" solutions by forcing a structured "Think, Plan, then Act" lifecycle.
Trigger
IMPORTANT: This skill is ONLY triggered when the AI model is explicitly requested by the user (e.g., "Use spec-driven-development", "Activate planning mode", "Create a spec for this").
- Do NOT auto-trigger this skill for simple Q&A or minor bug fixes.
- It is designed for tasks requiring architectural thought, multiple file changes, or a defined implementation strategy.
Directory Structure
The workflow isolates its artifacts in a hidden directory to keep the workspace clean.
<PROJECT_ROOT>/
├── .spec-driven-development-tasks/ # Hidden directory for all tasks
│ ├── {YYYYMMDD}-{TASK_TITLE}/ # Specific task folder
│ │ ├── spec.md # "The WHAT": Requirements, Context, Scope
│ │ ├── implementation.md # "The HOW": Architecture, File Changes, Steps
│ │ ├── task.md # "The WHEN": Real-time checklist & logs
│ │ └── walk-through.md # "The SUMMARY": Verification Guide, Handover
│ └── ...
├── .gitignore # Excludes .spec-driven-development-tasks
└── ...
Workflow Diagram
graph TD
Start((Start)) -->|User Request| Phase1[1. Initialization Phase<br/>Run init_task.sh]
Phase1 -->|AUTO-PROCEED| Phase2[2. Research & Planning Phase<br/>Analyze, Scan Code, Draft Docs]
Phase2 --> Docs[Drafted Docs:<br/>spec.md, implementation.md, task.md]
Docs -->|STOP & REPORT| Review{User Review}
Review -->|2.1 Direct Execute| Phase3[3. Execution Phase<br/>Implement & Update task.md]
Review -->|2.2 Adjust & Execute| AdjustDirect[Adjust Docs]
AdjustDirect -->|AUTO-PROCEED| Phase3
Review -->|2.3 Adjust & Review| AdjustConfirm[Adjust Docs]
AdjustConfirm -->|STOP & REPORT| Review
Phase3 --> AllDone{All Tasks Done?}
AllDone -->|No: Continue Work| Phase3
AllDone -->|Yes: AUTO-PROCEED| Phase4[4. Completion Phase<br/>Write walk-through.md]
Phase4 -->|STOP & REPORT| End((Task Complete))
End -.->|New Requirements| Phase2
Workflow Phases
1. Initialization Phase
Input: The user's natural language request (e.g., "Help me refactor the authentication module"). The user does not provide a specific task title; the Agent must analyze the request to generate one.
Process:
- Generate a Task Title (e.g.,
refactor-auth-module). - Run Script: Call
skills/spec-driven-development/scripts/init_task.sh <TASK_TITLE>.- Ensures
.spec-driven-development-tasksexists and is added to.gitignore. - Note: The user must have "Gitignore Access" enabled for the AI tool to modify
.gitignoreand files within ignored directories. - Creates
{YYYYMMDD}-{TASK_TITLE}directory with 4 empty template files.
- Ensures
Output: A clean, isolated workspace for the task.
Transition: AUTO-PROCEED to Phase 2. Do not stop to report "Initialization Complete".
2. Deep Research & Planning Phase
Input: The initialized workspace and user requirements.
Process:
- Deep Research: Scan relevant code/docs to understand the current system (avoid blind full-repo scans).
- Draft Documentation: Fill the empty files using templates:
spec.md: Context, Requirements, Scope (fromtemplates/spec-template.md).implementation.md: Architecture, Implementation Steps (fromtemplates/implementation-template.md).task.md: TODO Checklist (fromtemplates/task-template.md).
Output: Drafted specification and planning documents.
Transition: STOP & REPORT. Present the plan to the user with exactly these 3 options:
- 2.1. Execute Immediately: User agrees -> Proceed to Phase 3.
- 2.2. Adjust & Execute: User gives minor feedback -> Update docs -> Proceed to Phase 3 (no second confirmation).
- 2.3. Adjust & Review: User gives major feedback -> Update docs -> STOP & REPORT (ask for confirmation again).
3. Execution Phase
Input: Approved spec.md, implementation.md, task.md.
Process:
- Execute: Write code according to
implementation.md. - Real-time Update: Mark items in
task.mdas[x]immediately upon completion. - Check Completion: Continue until all items in
task.mdare checked.
Output: Completed implementation and updated task.md.
Transition: AUTO-PROCEED to Phase 4 immediately after all tasks are done. Do not stop to ask "Ready for next phase?".
4. Completion & Archiving Phase
Input: Finished code and completed task.md.
Process:
- Summarize: Create
walk-through.mdusingtemplates/walk-through-template.md. - Iterative Requirement Handling:
- If user provides New Requirements after this phase:
- Return to Phase 2 (Option 2.2 Trigger) workflow.
- Retain old content in docs.
- Append new scope to docs.
- Resume at Phase 3.
Output: Final project summary.
Transition: STOP & REPORT. Inform the user the task is fully complete and present the walk-through.md.
Source
git clone https://github.com/Bosh-Kuo/awesome-agent-toolkit/blob/main/skills/spec-driven-development/SKILL.mdView on GitHub Overview
Spec-driven development is an AI workflow that emulates Antigravity Planning Mode for complex, multi-step tasks. It emphasizes a Think-Plan-Act lifecycle with a strict Spec -> Implementation -> Task Tracking progression, activated only when explicitly requested. This reduces hallucinations and improves architectural rigor by isolating work in a hidden, organized workspace.
How This Skill Works
When triggered by user request, the agent generates a task title, initializes a hidden workspace under .spec-driven-development-tasks, and transitions into Deep Research & Planning. It drafts spec.md, implementation.md, and task.md using templates, then proceeds through iterative execution with user reviews, updating task.md and walk-throughs as work progresses.
When to Use It
- When the user explicitly asks to activate planning mode or use spec-driven-development
- For architecture-level tasks that require multi-file changes or a defined implementation strategy
- When tasks are complex and susceptible to hallucinations without a formal spec-first approach
- When creating a formal spec for handover or external review
- When tasks require traceable verification and a documented workflow from spec to implementation to task logs
Quick Start
- Step 1: User requests planning mode (e.g., 'Use spec-driven-development' or 'Activate planning mode')
- Step 2: Agent generates a task title and runs init_task.sh <TASK_TITLE> to create the hidden workspace with template files
- Step 3: Agent enters Deep Research & Planning, drafting spec.md, implementation.md, and task.md, then awaits user review
Best Practices
- Require an explicit user trigger to engage the spec-driven workflow
- Generate a precise, URL-safe Task Title (e.g., refactor-auth-module)
- Keep all artifacts isolated under a hidden directory: .spec-driven-development-tasks
- Populate spec.md and implementation.md from templates to ensure consistency
- Use task.md and walk-through to capture real-time progress, verification steps, and handover notes
Example Use Cases
- Refactor authentication module to add a multi-factor flow with minimal API surface changes
- Design a new user analytics microservice with defined data contracts and event schemas
- Migrate a relational schema to a backward-compatible version with data migration scripts
- Implement a cross-service feature flag system with centralized configuration
- Consolidate logging and observability across multiple modules for unified dashboards