smart-spec-kit-mcp 2.0.4 → 2.0.5

package/starter-kit/prompts/speckit.specify.md

@@ -1,123 +0,0 @@
----
-description: Create a functional specification from requirements or an Azure DevOps work item. Focus on WHAT you want to build, not the tech stack.
----
-
-# /speckit.specify - Create Specification
-
-## User Input
-
-```text
-$ARGUMENTS
-```
-
-You **MUST** consider the user input before proceeding (if not empty).
-
-## Outline
-
-You are creating a functional specification document. Follow this workflow:
-
-### 1. Setup Check
-
-First, verify the Spec-Kit environment:
-- Check if `.spec-kit/` directory exists
-- If not, inform the user to run `/speckit.init` first
-
-### 2. Parse Requirements Source
-
-Determine the source of requirements from user input:
-
-**Option A: Azure DevOps Work Item**
-- If input contains an ADO work item ID (e.g., "#12345", "AB#12345", "Feature 12345")
-- Use the `fetch_ado_workitem` MCP tool to retrieve work item data
-
-**Option B: Direct Description**
-- If input is a feature description
-- Parse the description for key concepts: actors, actions, data, constraints
-
-### 3. Analyze Requirements
-
-For the provided requirements, identify:
-1. **Core user need** and business value
-2. **Explicit requirements** - what was directly stated
-3. **Implicit requirements** - reasonable inferences from context
-4. **Assumptions** - things that need validation
-5. **Risks and dependencies**
-6. **Edge cases and error scenarios**
-
-### 4. Generate Specification
-
-Load the template from `.spec-kit/templates/functional-spec.md` and fill it with:
-
-1. **Metadata Section**
-   - Title, date, version, status
-   - Link to Azure DevOps work item (if applicable)
-
-2. **Overview**
-   - Purpose (the problem being solved)
-   - Scope (what's in/out)
-   - Background context
-
-3. **Requirements**
-   - Functional requirements with IDs and priorities (Must Have/Should Have/Could Have)
-   - Non-functional requirements (performance, security, etc.)
-   - Acceptance criteria in Given/When/Then format
-
-4. **User Experience**
-   - User personas
-   - User stories (As a... I want... So that...)
-   - User flow descriptions
-
-5. **Technical Considerations**
-   - Dependencies
-   - Constraints
-   - Data requirements
-
-### 5. Handle Ambiguity
-
-For unclear aspects:
-- **Make informed guesses** based on context and industry standards
-- **Document assumptions** in the Assumptions section
-- **Limit clarifications**: Maximum 3 `[NEEDS CLARIFICATION]` markers for critical decisions only
-
-Only use `[NEEDS CLARIFICATION]` when:
-- The choice significantly impacts feature scope or user experience
-- Multiple reasonable interpretations exist with different implications
-- No reasonable default exists
-
-### 6. Save Specification
-
-Save the specification to:
-```
-specs/{context_id}-spec.md
-```
-
-If no context ID is provided, create a timestamped filename or ask for a feature short-name.
-
-### 7. Report Completion
-
-Output:
-- Path to created specification file
-- Summary of requirements captured
-- List of assumptions made
-- Any `[NEEDS CLARIFICATION]` items that need user input
-- Next step suggestion: `/speckit.plan` to create implementation plan
-
-## Quick Guidelines
-
-### Writing Style
-- Use active voice and clear, concise language
-- Include concrete examples for complex requirements
-- Define all technical terms and acronyms
-- Use tables for structured data (requirements, test cases)
-
-### Quality Checks
-- Every requirement should be testable and unambiguous
-- Each requirement should have a unique ID
-- Acceptance criteria should be in Given/When/Then format
-- No undefined placeholders in final output (except intentional `[NEEDS CLARIFICATION]`)
-
-## Handoffs
-
-After completing the specification, suggest:
-- **Clarify requirements**: `/speckit.clarify` - If there are `[NEEDS CLARIFICATION]` items
-- **Create implementation plan**: `/speckit.plan` - Once specification is approved

package/starter-kit/prompts/speckit.tasks.md

@@ -1,137 +0,0 @@
----
-description: Generate actionable task breakdown from the implementation plan. Creates a tasks.md file with ordered, dependency-aware tasks.
----
-
-# /speckit.tasks - Generate Task Breakdown
-
-## User Input
-
-```text
-$ARGUMENTS
-```
-
-You **MUST** consider the user input before proceeding (if not empty).
-
-## Outline
-
-You are generating an actionable task list from the implementation plan. Follow this workflow:
-
-### 1. Load Design Documents
-
-Read from the feature's spec directory:
-- **Required**: `plan.md` (tech stack, libraries, structure)
-- **Required**: `spec.md` (user stories with priorities)
-- **Optional**: `data-model.md` (entities)
-- **Optional**: `contracts/` (API endpoints)
-- **Optional**: `research.md` (decisions)
-
-If required files are missing, inform user to run `/speckit.plan` first.
-
-### 2. Extract Implementation Context
-
-From the documents, identify:
-- User stories with their priorities (P1, P2, P3)
-- Tech stack and frameworks
-- Database entities and relationships
-- API endpoints
-- External dependencies
-
-### 3. Generate Task Breakdown
-
-Create `specs/{feature}/tasks.md` with this structure:
-
-```markdown
-# Tasks: {Feature Name}
-
-**Input**: Design documents from `/specs/{feature}/`
-**Generated**: {Date}
-
-## Task Format
-
-- [ ] T### [P?] [Story?] Description - `path/to/file.ext`
-
-Legend:
-- T###: Task ID (sequential)
-- [P]: Can be executed in parallel with other [P] tasks
-- [Story?]: Associated user story ID (if applicable)
-```
-
-### 4. Phase Structure
-
-Organize tasks into these phases:
-
-**Phase 1: Setup (Shared Infrastructure)**
-- Project initialization
-- Dependency installation
-- Configuration files
-- Development environment setup
-
-**Phase 2: Foundational (Blocking Prerequisites)**
-- Database schema and migrations
-- Base models/entities
-- Authentication/authorization framework
-- Core utilities and helpers
-- Error handling infrastructure
-
-⚠️ **CRITICAL**: No user story work begins until Phase 2 is complete.
-
-**Phase 3+: User Stories (One Phase per Story)**
-For each user story in priority order:
-- Tests (if requested) → Models → Services → Endpoints → Integration
-- Each phase should be independently testable
-- Include checkpoint validation
-
-**Final Phase: Polish & Cross-Cutting**
-- Code cleanup and refactoring
-- Documentation updates
-- Performance optimization
-- Security hardening
-
-### 5. Task Generation Rules
-
-Each task MUST:
-- Be completable in 1-3 days by a single developer
-- Have a clear verb + object title
-- Include the file path(s) affected
-- Have explicit dependencies noted
-
-Mark with `[P]` if the task can run in parallel with others at the same level.
-
-### 6. Generate Dependency Graph
-
-Add a section showing:
-- Task dependencies (which tasks must complete first)
-- Parallel execution opportunities
-- Critical path identification
-
-### 7. Report Completion
-
-Output:
-- Path to generated `tasks.md`
-- Total task count
-- Task count per user story
-- Parallel execution opportunities identified
-- Suggested MVP scope (typically User Story 1 only)
-
-## Task Template
-
-```markdown
-## Phase 3: User Story 1 - {Title} (Priority: P1) 🎯 MVP
-
-**Goal**: {User story goal}
-**Independent Test**: {How to verify this story works alone}
-
-- [ ] T010 [US-1] Create {model} entity - `src/models/{model}.ts`
-- [ ] T011 [P] [US-1] Create {model} repository - `src/repositories/{model}.ts`
-- [ ] T012 [P] [US-1] Create {model} service - `src/services/{model}.ts`
-- [ ] T013 [US-1] Create {endpoint} API endpoint - `src/api/{endpoint}.ts`
-- [ ] T014 [US-1] Add integration tests - `tests/integration/{feature}.test.ts`
-
-**Checkpoint**: Story 1 complete - run `npm test` and verify {criteria}
-```
-
-## Handoffs
-
-After completing the tasks, suggest:
-- **Analyze plan**: `/speckit.analyze` - Cross-check consistency
-- **Implement**: `/speckit.implement` - Start executing tasks