ajbcoding/claude-skill-eval/moai-alfred-spec-authoring
- community
Checking that the SKILL.md file is still in the repository.
Complete SPEC document authoring guide with YAML metadata structure (7 required + 9 optional fields), EARS requirement syntax (5 patterns including Unwanted Behaviors), version lifecycle management, TAG integration, pre-submission validation checklist, and real-world SPEC examples.
Install
npx vskill@latest install ajbcoding/claude-skill-eval/moai-alfred-spec-authoringSKILL.md
SPEC Authoring Skill (Enterprise v4.0.0)
Level 1: Quick Reference
Core Capabilities
- YAML Metadata Structure: 7 required + 9 optional fields for complete SPEC management
- EARS Requirement Syntax: 5 patterns (Universal, Conditional, Unwanted Behavior, Stakeholder, Boundary)
- Version Lifecycle: draft → active → deprecated → archived with state management
- TAG Integration: SPEC→TEST→CODE→DOC traceability
- Validation Checklist: 25+ pre-submission validation criteria
Quick SPEC Template
EARS Pattern Summary
| Pattern | Syntax | Use Case | |
|---|---|---|---|
| Universal | The [System] SHALL [Action] | Core system behavior | |
| Conditional | If [Condition], then [System] SHALL [Action] | Conditional logic | |
| Unwanted Behavior | The [System] SHALL NOT [Action] | Security constraints | |
| Stakeholder | As a [Role], I want [Feature] so that [Benefit] | User stories | |
| Boundary Condition | [System] SHALL [Action] when [Condition] | Edge cases |
Level 2: Core Implementation
YAML Metadata Structure
7 Required Fields
9 Optional Fields
EARS Requirement Syntax
Pattern 1: Universal (Always True)
Syntax:
Example:
Pattern 2: Conditional (If-Then)
Syntax:
Example:
Pattern 3: Unwanted Behavior (Negative Requirement)
Syntax:
Example:
Pattern 4: Stakeholder (User Role-Specific)
Syntax:
Example:
Pattern 5: Boundary Condition (Edge Cases)
Syntax:
Example:
Level 3: Advanced Features
Version Lifecycle Management
Lifecycle States
State Transitions
DRAFT → ACTIVE:
- All acceptance criteria defined
- At least 2 reviewers approved
- No critical open issues
versionbumped to 1.0.0- Status change commit created
ACTIVE → DEPRECATED:
- Marked with deprecation reason
- Migration path documented
- Replacement SPEC linked
- 30-day notice period
- Status change commit created
DEPRECATED → ARCHIVED:
- No active code references
- All dependent SPECs archived
- Historical record maintained
- No further changes allowed
- Archive commit created
Unwanted Behaviors Section
Critical security and quality constraints that MUST be tested:
Each Unwanted Behavior requires:
- Test case verifying non-occurrence
- Security scanning (where applicable)
- Performance profiling (where applicable)
TAG Integration for Traceability
TAG Structure (SPEC→TEST→CODE→DOC)
TAG Placement Rules
SPEC Document:
Test File:
Implementation:
Documentation:
Level 4: Reference & Integration
Pre-Submission Validation Checklist
Metadata Validation
- [ ]
codefield filled (SPEC-XXX format) - [ ]
titleis descriptive (50-80 characters) - [ ]
statusis one of: draft | active | deprecated | archived - [ ]
created_atis ISO 8601 format (YYYY-MM-DD) - [ ]
updated_atmatches actual update date - [ ]
priorityis one of: critical | high | medium | low - [ ]
effortis between 1-13 (story points)
Requirement Syntax
- [ ] At least 3 REQ patterns used (Universal, Conditional, Unwanted)
- [ ] Each REQ follows EARS syntax strictly
- [ ] Requirements are specific and testable
- [ ] No ambiguous language ("should", "may", "might")
- [ ] All REQs are actionable (have test cases)
Unwanted Behaviors
- [ ] Security constraints listed (if applicable)
- [ ] Performance constraints listed (if applicable)
- [ ] Reliability constraints listed (if applicable)
- [ ] Data integrity constraints listed (if applicable)
- [ ] Each Unwanted Behavior has a test approach
Acceptance Criteria
- [ ] All 5 EARS patterns implemented
- [ ] All Unwanted Behaviors testable
- [ ] Code coverage target ≥85% specified
- [ ] Security scan type specified
- [ ] Performance baseline defined (if applicable)
Final Review
- [ ] No TODO or placeholder text
- [ ] All links are valid (internal and external)
- [ ] Formatting is consistent (markdown syntax)
- [ ] No confidential information exposed
- [ ] Ready for team review
Common Pitfalls & Anti-Patterns
Anti-Pattern 1: Ambiguous Requirements
Bad:
Good:
Anti-Pattern 2: Vague Acceptance Criteria
Bad:
Good:
Anti-Pattern 3: Missing Unwanted Behaviors
Bad:
Good:
When to Use
Automatic Triggers:
/alfred:1-plancommand execution- SPEC document creation requests
- Requirements clarification discussions
- Feature planning sessions
- Change request handling
Manual Invocation:
- SPEC template guidance
- Metadata field clarification
- EARS syntax validation
- Version management questions
- TAG traceability setup
Related Skills
moai-alfred-best-practices- TRUST 5 principles for SPEC authoringmoai-alfred-spec-validation- Automated SPEC validationmoai-foundation-specs- SPEC lifecycle managementmoai-foundation-trust- Security and compliance principlesmoai-alfred-workflow- SPEC creation workflows
TRUST Principles Applied
Test First: All requirements include test cases and validation criteria Readable: Clear EARS syntax with unambiguous language Unified: Consistent structure across all SPEC documents Secured: Unwanted Behaviors section with security constraints Traceable: TAG integration for complete requirement traceability
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/moai-alfred-spec-authoring/SKILL.md
Popularity
- Repository stars
- 4
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 24 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ajbcoding/claude-skill-eval/moai-alfred-spec-authoring)