Add specification-writer skill for expert SPEC.md creation

- Create new skill at src/fiona/data/llm_wiki/utils/skills/specification-writer/
- Provides comprehensive guidance for writing project specifications
- Integrates with sectionize-markdown skill for consistent formatting
- Includes structure template based on fiona-assistant and agent-cost-estimator patterns
- Emphasizes always sectionizing SPEC files with numbered headings and list items
- Features quality checklist and maintenance guidelines

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
This commit is contained in:
nvaldez
2026-11-03 16:27:05 +01:00
parent 983198b8b4
commit 59d1054e1d
@@ -0,0 +1,286 @@
---
name: specification-writer
description: Load this skill when writing or updating project specifications (SPEC.md). Expert in creating structured, comprehensive, and maintainable specification documents for software projects.
type: skill
version: 1.0.0
created: 2026-11-03
updated: 2026-11-03
---
# Specification Writer
You are an expert in writing software project specifications. This skill provides guidance on creating structured, comprehensive, and maintainable SPEC.md files following best practices established by fiona-assistant and agent-cost-estimator projects.
## When to Load
Load this skill when:
- Creating a new SPEC.md file for a project
- Updating or expanding an existing specification
- Reviewing specification structure and content
- Ensuring specifications follow consistent patterns
## Core Principles
**Always apply sectionize-markdown conventions** to every SPEC.md file. Reference: [sectionize-markdown skill](../sectionize-markdown/SKILL.md)
- **Every heading MUST be numbered**: `## 1.` for sections, `### 1.1` for subsections, etc.
- **Every list item MUST have a bold ID**: `- **1.1.1** Text`
- **TOC MUST be present** under the title with markdown links
- **Anchors MUST follow GitHub-style slugs**
- **Never renumber existing IDs** - they may be cited elsewhere
## SPEC.md Structure Template
Use this structure as the foundation for all project specifications:
```markdown
---
name: <Project Name> Specification
version: <semver>
title: Project Spec Sheet
type: specification
created: <YYYY-MM-DD>
updated: <YYYY-MM-DD>
---
# <Project Name> Specification
<!-- toc-start: headings 2..6 -->
- [1. Product Overview](#1-product-overview)
- [1.1. Purpose](#11-purpose)
- [1.2. Scope](#12-scope)
- [1.3. Non-Goals](#13-non-goals)
- [1.4. Document Conventions](#14-document-conventions)
- [2. Architecture](#2-architecture)
- [3. Core Contracts](#3-core-contracts)
- [4. Package and Runtime](#4-package-and-runtime)
- [5. Feature Requirements](#5-feature-requirements)
- [6. Configuration Files](#6-configuration-files)
- [7. Error Handling](#7-error-handling)
- [8. Testing](#8-testing)
- [9. Deployment](#9-deployment)
<!-- toc-end -->
This document is the build contract for <Project Name>. A reader with
this file, and no source tree, must be able to produce the same
observable software. Status values are `Implemented`, `Partially
Implemented`, `Planned`, and `Not Implemented`.
---
## 1. Product Overview
### 1.1. Purpose
- **1.1.1** Clearly state what problem the project solves
- **1.1.2** Describe the primary value proposition
- **1.1.3** Identify the target users/audience
### 1.2. Scope
- **1.2.1** **In Scope**: List what the project will do
- **1.2.2** **Out of Scope**: List what the project will NOT do
### 1.3. Non-Goals
- **1.3.1** Explicitly state what will not be implemented
- **1.3.2** Clarify boundaries with related projects
### 1.4. Document Conventions
- **1.4.1** Define terminology used throughout
- **1.4.2** Establish status labels (Implemented, Planned, etc.)
- **1.4.3** Specify numbering conventions
- **1.4.4** Define RFC2119 keywords (MUST, SHALL, SHOULD, MAY)
## 2. Architecture
### 2.1. Component Diagram
- **2.1.1** Provide ASCII or Mermaid diagram
- **2.1.2** Label all major components
- **2.1.3** Show data flow between components
### 2.2. Data Flow
- **2.2.1** Describe how data moves through the system
- **2.2.2** Identify key transformations
- **2.2.3** Note persistence points
### 2.3. Module Structure
- **2.3.1** Document the directory structure
- **2.3.2** Describe each module's responsibility
- **2.3.3** Note cross-module dependencies
## 3. Core Contracts
Define the fundamental interfaces and data structures:
### 3.1. <Interface Name> Interface
- **3.1.1** Purpose of the interface
- **3.1.2** Required methods/functions
- **3.1.3** Expected inputs and outputs
- **3.1.4** Error handling expectations
### 3.2. <Data Structure> Format
- **3.2.1** JSON Schema or type definitions
- **3.2.2** Example instances
- **3.2.3** Validation rules
- **3.2.4** Version compatibility notes
## 4. Package and Runtime
### 4.1. Dependencies
- **4.1.1** Runtime dependencies with versions
- **4.1.2** Development dependencies
- **4.1.3** Optional dependencies
### 4.2. Entry Points
- **4.2.1** CLI entry points
- **4.2.2** Library entry points
- **4.2.3** Plugin/extension entry points
### 4.3. Installation
- **4.3.1** Installation methods (pip, source, etc.)
- **4.3.2** Platform requirements
- **4.3.3** Verification steps
## 5. Feature Requirements
Organize by major feature areas:
### 5.X. <Feature Name>
- **5.X.1** Status: Implemented/Planned/Not Implemented
- **5.X.2** Purpose and user stories
- **5.X.3** Functional requirements
- **5.X.4** Non-functional requirements
- **5.X.5** Acceptance criteria
## 6. Configuration Files
### 6.1. <Config File>
- **6.1.1** Location (relative and absolute paths)
- **6.1.2** Purpose
- **6.1.3** Structure/format
- **6.1.4** Default values
- **6.1.5** Customization options
## 7. Error Handling
### 7.1. Error Classification
- **7.1.1** Transient vs permanent errors
- **7.1.2** Recoverable vs unrecoverable errors
- **7.1.3** User-facing vs internal errors
### 7.2. Error Reporting
- **7.2.1** Logging strategy
- **7.2.2** User notifications
- **7.2.3** Error codes and messages
### 7.3. Recovery Strategies
- **7.3.1** Automatic recovery mechanisms
- **7.3.2** Manual recovery procedures
- **7.3.3** Data consistency guarantees
## 8. Testing
### 8.1. Test Strategy
- **8.1.1** Testing pyramid (unit, integration, system)
- **8.1.2** Test coverage targets
- **8.1.3** Test environments
### 8.2. Test Cases
- **8.2.1** Critical path tests
- **8.2.2** Edge case tests
- **8.2.3** Regression tests
## 9. Deployment
### 9.1. Release Process
- **9.1.1** Versioning scheme
- **9.1.2** Release checklist
- **9.1.3** Rollback procedures
### 9.2. Distribution
- **9.2.1** Package repositories
- **9.2.2** Installation methods
- **9.2.3** Update mechanisms
## Best Practices from Reference Projects
Study these existing SPEC.md files for patterns:
- [Fiona-Assistant SPEC.md](https://gitea.nolivaldeziii.com/nvaldeziii/fiona-assistant/src/branch/master/SPEC.md)
- [Agent Cost Estimator SPEC.md](https://gitea.nolivaldeziii.com/nvaldeziii/agent-cost-estimator/src/branch/master/SPEC.md)
### Patterns to Emulate
- **Fiona-Assistant**: Comprehensive violation rule catalog, clear status tracking
- **Agent Cost Estimator**: Modular harness adapter documentation, detailed integration steps
## Sectionize-Markdown Integration
**CRITICAL**: Every SPEC.md file you create or modify MUST follow sectionize-markdown conventions.
Before finalizing any SPEC.md:
1. Apply numbered headings (## 1., ### 1.1, #### 1.1.1)
2. Add bold IDs to all list items (- **1.1.1**)
3. Generate/update the TOC with markdown links
4. Ensure all anchors resolve correctly
5. Verify no duplicate IDs exist
Use the sectionize-markdown skill as a reference for detailed conventions.
## Quality Checklist
Before marking a SPEC as complete:
- [ ] **Structure**: All required sections present
- [ ] **Numbering**: All headings and list items numbered correctly
- [ ] **TOC**: Table of contents present and accurate
- [ ] **Status**: Every feature section has a status line
- [ ] **Examples**: Code/config examples provided where applicable
- [ ] **Cross-references**: Links to related sections/files work
- [ ] **Consistency**: Terminology and formatting consistent throughout
- [ ] **Completeness**: All acceptance criteria defined
- [ ] **Sectionized**: Follows sectionize-markdown conventions completely
## Maintenance Guidelines
- **Versioning**: Increment version in frontmatter with each update
- **Changelog**: Maintain updated/created dates in frontmatter
- **Review**: SPEC should be reviewed before major implementation
- **Sync**: Keep SPEC in sync with implementation (status updates)
## Tools and Automation
When working with SPEC files:
- Use scripts to verify section numbering
- Automate TOC generation
- Validate all internal links
- Check for duplicate IDs
- Lint markdown formatting
## Common Pitfalls
- **Unnumbered items**: Every list item MUST have a bold ID
- **Broken anchors**: Verify all TOC links resolve
- **Inconsistent status**: Use consistent status labels throughout
- **Missing examples**: Always include examples for data formats
- **Ambiguous requirements**: Requirements must be testable