Get the FREE Ultimate OpenClaw Setup Guide →
npx machina-cli add skill athola/claude-night-market/project-specification --openclaw
Files (1)
SKILL.md
10.4 KB

Table of Contents

Project Specification Skill

Transform project briefs into structured, testable specifications with acceptance criteria.

Delegation

For detailed specification writing workflows, this skill delegates to spec-kit:spec-writing as the canonical implementation. Use this skill for quick specification needs; use spec-kit for comprehensive specification documents.

When To Use

  • After brainstorming phase completes
  • Have project brief but need detailed requirements
  • Need testable acceptance criteria for implementation
  • Planning validation and testing strategy
  • Translating business requirements into technical specs
  • Defining scope boundaries and out-of-scope items

When NOT To Use

  • Still exploring problem space (use Skill(attune:project-brainstorming) instead)
  • Already have detailed specification (use Skill(attune:project-planning) instead)
  • Refining existing implementation (use code review skills)
  • Making strategic decisions (use Skill(attune:war-room) for complex choices)

Integration

With spec-kit:

  • Delegates to Skill(spec-kit:spec-writing) for methodology
  • Uses spec-kit templates and validation
  • Enables clarification workflow

Without spec-kit:

  • Standalone specification framework
  • Requirement templates
  • Acceptance criteria patterns

Specification Structure

1. Overview Section

  • Purpose: What the project achieves (1-2 sentences)
  • Scope: IN/OUT boundaries
  • Stakeholders: Who cares and why

2. Functional Requirements (FR-XXX)

Format per requirement:

### FR-001: [Requirement Name]

**Description**: Clear, unambiguous description

**Acceptance Criteria**:
- [ ] Given [context], when [action], then [expected result]
- [ ] Given [context], when [action], then [expected result]

**Priority**: High | Medium | Low
**Dependencies**: FR-002, FR-005
**Estimated Effort**: S | M | L | XL

Verification: Run the command with --help flag to verify availability.

Validation Rules:

  • Description has no ambiguous words (might, could, maybe, probably)
  • At least 2 acceptance criteria (happy path + error case)
  • Criteria use Given-When-Then format
  • Criteria are testable (observable outcomes)
  • Dependencies are explicit

3. Non-Functional Requirements (NFR-XXX)

Categories:

  • Performance: Response times, throughput, resource limits
  • Security: Authentication, authorization, data protection, compliance
  • Reliability: Uptime, error handling, recovery, fault tolerance
  • Usability: UX requirements, accessibility, documentation
  • Maintainability: Code quality, testing, observability

Format:

### NFR-001: [Category] - [Requirement]

**Requirement**: [Specific, measurable requirement]

**Measurement**: [How to verify]
- Metric: [What to measure]
- Target: [Specific threshold]
- Tool: [How to measure]

**Priority**: Critical | High | Medium | Low

Verification: Run the command with --help flag to verify availability.

4. Technical Constraints

  • Technology stack selections with rationale
  • Integration requirements
  • Data requirements (schema, migrations)
  • Deployment constraints
  • Regulatory/compliance requirements

5. Out of Scope

Explicit exclusions to prevent scope creep:

## Out of Scope (v1.0)

- [Feature explicitly NOT included]
- [Capability deferred to later version]
- [Integration not planned]

**Rationale**: [Why these are excluded]

Verification: Run the command with --help flag to verify availability.

Clarification Workflow

Ambiguity Detection

Scan specification for:

  • Vague quantifiers (many, few, several, most)
  • Ambiguous terms (user-friendly, fast, scalable)
  • Missing dependencies
  • Untestable criteria
  • Conflicting requirements

Question Generation

For each ambiguity:

**Question [N]**: [Reference to FR/NFR]

**Ambiguity**: [What is unclear]

**Impact**: [Why this matters]

**Options**:
- Option A: [Interpretation 1]
- Option B: [Interpretation 2]

**Recommendation**: [Preferred option with rationale]

Verification: Run the command with --help flag to verify availability.

Clarification Session

Run interactive Q&A:

  1. Present all questions
  2. Gather stakeholder responses
  3. Update specification
  4. Re-validate for new ambiguities
  5. Iterate until clear

Quality Checks

Before completing specification:

  • ✅ All requirements have unique IDs (FR-XXX, NFR-XXX)
  • ✅ All functional requirements have ≥2 acceptance criteria
  • ✅ All criteria use Given-When-Then format
  • ✅ No ambiguous language detected
  • ✅ Dependencies documented
  • ✅ Effort estimates provided
  • ✅ Out of scope explicitly stated
  • ✅ Success criteria defined

Output Format

Save to docs/specification.md:

# [Project Name] - Specification v[version]

**Author**: [Name]
**Date**: [YYYY-MM-DD]
**Status**: Draft | Review | Approved | Implemented

## Change History

| Version | Date | Author | Changes |
|---------|------|--------|---------|
| 0.1.0 | 2026-01-02 | Alex | Initial draft |

## Overview

**Purpose**: [1-2 sentence purpose]

**Scope**:
- **IN**: [What's included]
- **OUT**: [What's excluded]

**Stakeholders**:
- [Stakeholder 1]: [Their interest]
- [Stakeholder 2]: [Their interest]

## Functional Requirements

[FR-XXX sections]

## Non-Functional Requirements

[NFR-XXX sections]

## Technical Constraints

[Technology, integration, data, deployment]

## Out of Scope

[Explicit exclusions with rationale]

## Dependencies

[External dependencies, third-party services]

## Acceptance Testing Strategy

[How requirements will be validated]

## Success Criteria

- [ ] [Measurable success indicator 1]
- [ ] [Measurable success indicator 2]

## Glossary

[Domain terms and definitions]

## References

[Related documents, research, prior art]

Verification: Run pytest -v to verify tests pass.

Acceptance Criteria Patterns

Given-When-Then

Given [initial context/state]
When [action occurs]
Then [expected outcome]

Verification: Run the command with --help flag to verify availability.

Examples:

  • Given unauthenticated user, when accessing dashboard, then redirect to login
  • Given valid credentials, when logging in, then create session and redirect to dashboard
  • Given expired session, when making API request, then return 401 Unauthorized

Error Cases

Always include error scenarios:

  • Invalid input handling
  • Authentication/authorization failures
  • Network/service failures
  • Resource exhaustion
  • Edge cases and boundaries

Performance Criteria

Make performance requirements testable:

  • "Dashboard loads in < 2 seconds" (measurable)
  • NOT "Dashboard is fast" (vague)

Security Criteria

Make security requirements verifiable:

  • "All API endpoints require authentication" (testable)
  • NOT "System is secure" (vague)

Post-Completion: Workflow Continuation (REQUIRED)

Automatic Trigger: After Quality Checks pass and docs/specification.md is saved, MUST auto-invoke the next phase.

When continuation is invoked:

  1. Verify docs/specification.md exists and is non-empty
  2. Display checkpoint message to user:
    Specification complete. Saved to docs/specification.md.
    Proceeding to planning phase...
    
  3. Invoke next phase:
    Skill(attune:project-planning)
    

Bypass Conditions (ONLY skip continuation if ANY true):

  • --standalone flag was provided by the user
  • docs/specification.md does not exist or is empty (phase failed)
  • User explicitly requests to stop after specification

Do NOT prompt the user for confirmation — this is a lightweight checkpoint, not an interactive gate. The user can always interrupt if needed.

Related Skills

  • Skill(spec-kit:spec-writing) - Spec-kit methodology (if available)
  • Skill(attune:project-brainstorming) - Previous phase
  • Skill(attune:project-planning) - AUTO-INVOKED next phase after specification
  • Skill(attune:mission-orchestrator) - Full lifecycle orchestration

Related Commands

  • /attune:specify - Invoke this skill
  • /attune:specify --clarify - Run clarification workflow
  • /attune:blueprint - Next step in workflow

Examples

See /attune:specify command documentation for complete examples.

Troubleshooting

Common Issues

Command not found Ensure all dependencies are installed and in PATH

Permission errors Check file permissions and run with appropriate privileges

Unexpected behavior Enable verbose logging with --verbose flag

Source

git clone https://github.com/athola/claude-night-market/blob/master/plugins/attune/skills/project-specification/SKILL.mdView on GitHub

Overview

Transforms project briefs into structured specs with acceptance criteria for requirements translation, spec creation, and pre-implementation planning. It can delegate to spec-kit for comprehensive documents, while handling quick spec needs. This skill helps define scope and validation upfront.

How This Skill Works

The skill analyzes the project brief, establishes an Overview, Scope, and Stakeholders, then formats Functional (FR-XXX) and Non-Functional (NFR-XXX) requirements with clear Acceptance Criteria. It follows a structured format and can delegate to spec-kit:spec-writing for deeper, template-driven documentation, enabling a ready-to-implement spec.

When to Use It

  • After brainstorming phase completes
  • Have project brief but need detailed requirements
  • Need testable acceptance criteria for implementation
  • Planning validation and testing strategy
  • Translating business requirements into technical specs

Quick Start

  1. Step 1: Gather the project brief and identify the key stakeholders
  2. Step 2: Draft the Overview, Scope, and initial FRs (FR-001, FR-002, ...)
  3. Step 3: Add Acceptance Criteria using Given-When-Then and validate with stakeholders

Best Practices

  • Start with a concise Overview (Purpose, Scope, Stakeholders)
  • Define FR-XXX and NFR-XXX blocks with explicit Acceptance Criteria
  • Use Given-When-Then style for clear test cases within criteria
  • Leverage spec-kit:spec-writing when a full spec is required
  • Ensure traceability with Dependencies, References, and Change History

Example Use Cases

  • Spec for a mobile checkout flow with payment gateway integration and rollback criteria
  • API authentication and token refresh mechanism with security constraints
  • Admin dashboard permissions and role-based access control requirements
  • User onboarding wizard steps with validation rules and analytics events
  • Data export feature specifying formats, scheduling, and performance constraints

Frequently Asked Questions

Add this skill to your agents

Related Skills

ab-test-setup

ranbot-ai/awesome-skills

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

decisive-action

athola/claude-night-market

Guidance on when to ask clarifying questions vs proceed with standard

session-management

athola/claude-night-market

Manage Claude Code sessions with naming, checkpointing, and resume strategies.

multi-review

Pamacea/smite

MANDATORY gate BEFORE merging PR or deploying to production in smite project. Invoke FIRST when 'comprehensive review', 'check security', 'performance review', 'test coverage review', 'code quality audit' - orchestrates parallel review by 4 specialized agents (security, performance, testing, documentation) with consolidated report and scoring. Specific phrases: 'review this PR', 'security audit', 'performance check', 'test review'. (user)

pattern-capture

Pamacea/smite

Invoke AFTER successful feature implementation when 'that went well', 'save this pattern', 'document this approach', 'capture this solution' - captures reusable code patterns with context (before/after, steps, benefits, trade-offs) for future team knowledge sharing. Auto-triggers on multi-file refactors or complex problem solutions. Specific phrases: 'save pattern', 'document approach', 'capture solution'. (user)

progressive-build

Pamacea/smite

Invoke BEFORE building complex features requiring both speed AND quality in smite project - progressive enhancement workflow using Haiku (MVP in 2min) → Sonnet (quality in 5min) → Opus (excellence in 10min). Triggers on 'complex feature', 'optimize and build', 'production-ready feature', 'build with optimization'. Total: 17min, 9.5/10 quality, 73% cost savings vs Opus-only. Specific phrases: 'progressive build', 'enhance this', 'iterate and improve'. (user)

Sponsor this space

Reach thousands of developers