What are Claude Code Skills?

Claude Code Skills are reusable prompt templates stored as markdown files in your project's .claude/skills/ directory. They let you codify best practices and common workflows into slash commands that Claude follows consistently.

How do I create a Claude Code Skill?

Create a markdown file in .claude/skills/ with instructions for Claude. The filename becomes the command name — for example, .claude/skills/code-review.md can be invoked with /code-review during a Claude Code session.

Can I share skills with my team?

Yes. Skills stored in .claude/skills/ can be committed to version control so every team member has access to the same standardized workflows. You can also organize skills into subdirectories by category.

What is the difference between project and global skills?

Project skills (.claude/skills/) are specific to the current project and are committed to git. Global skills (~/.claude/skills/) are personal skills available across all your projects.

formal-specification

New

23Community RegistryGeneralby Melodic Software · MIT

Formal methods and specification languages: UML/SysML modeling, TLA+ specifications, OpenAPI/AsyncAPI contract-first design, state machines, and Use Case 2.0 methodology.

Community PluginView Source

Overview

Plugins for Claude Code: documentation management, code quality, and ecosystem support.

Prerequisites

•Claude Code installed
•Python 3.13+ (for spaCy-based operations)
•Node.js 18+ (for markdown linting)

Development Setup

Node.js Version Manager (fnm)

fnm (Fast Node Manager) is the recommended Node.js version manager for this project. It:

•Works natively in Git Bash (unlike nvm-windows which has known issues)
•Is significantly faster than nvm-windows (Rust-based)
•Has cross-platform consistency (Windows/macOS/Linux)

Install fnm:

bash

# Windows (PowerShell as Admin)
winget install Schniz.fnm

# macOS/Linux
curl -fsSL https://fnm.vercel.app/install | bash

Configure for Git Bash (add to ~/.bashrc):

bash

eval "$(fnm env --use-on-cd --shell bash)"

Or source the setup script which includes fnm initialization:

bash

source "/path/to/claude-code-plugins/setup/bashrc-claude.sh"

Install Node:

bash

fnm install 24
fnm default 24

Install Dependencies

bash

npm install

Run Markdown Linting

bash

npm run lint:md        # Check for errors
npm run lint:md:fix    # Auto-fix errors

CI

Markdown linting runs automatically on PRs via GitHub Actions. The same rules apply locally and in CI.

Installation

bash

/plugin install claude-ecosystem@claude-code-plugins
/plugin install code-quality@claude-code-plugins
/plugin install google-ecosystem@claude-code-plugins

Codex CLI Configuration

This repo expects Codex CLI configuration to live in user scope under ~/.codex. See .codex/README.md for the canonical locations.

Plugins

Plugin	Purpose
atlassian	Atlassian MCP server: Jira, Confluence, Compass integration
browser-automation	Browser automation MCP servers: Chrome DevTools, Playwright
business-analysis	BABOK techniques: capability mapping, stakeholder analysis, value streams, journey mapping
ci-cd	CI/CD pipelines: GitHub Actions, deployment automation, release management
claude-code-observability	Event logging, metrics, session diagnostics
claude-ecosystem	Claude Code docs, meta-skills, hooks, observability, auditors
code-quality	Code review, markdown linting, debugging, CI/CD templates
compliance-planning	Regulatory compliance: GDPR, HIPAA, PCI-DSS, AI governance, ISO 27001
content-management-system	Headless CMS architecture: content modeling, taxonomies, media, theming
cursor-ecosystem	Cursor IDE docs, CLI, agent, keyword-based search
documentation-standards	Technical docs: arc42, C4 model, ADRs, RFC process, docs-as-code
dotnet	.NET 10+ automation: build, clean, SDK/tool install, version upgrades, Aspire MCP
duende-ecosystem	Duende IdentityServer, BFF, IdentityModel docs
enterprise-architecture	TOGAF, Zachman, ADRs, cloud alignment
event-modeling	Event-driven design: Event Modeling, Event Storming, CQRS, sagas
figma	Figma MCP server: design context, code generation, design tokens
formal-specification	Formal methods: UML/SysML, TLA+, OpenAPI/AsyncAPI, state machines
git	Git config, GPG signing, hooks, GitHub issues, history exploration
google-ecosystem	Gemini CLI docs, Claude-to-Gemini integration, configuration management
melodic-software	Developer onboarding, environment setup, commit workflows
microsoft	Microsoft MCP servers: Microsoft Learn, Azure, NuGet, Azure DevOps
milan-jovanovic	Milan Jovanovic .NET patterns: Clean Architecture, DDD, CQRS, EF Core
openai-ecosystem	OpenAI Codex CLI docs
requirements-elicitation	Requirements gathering: LLMREI interviews, gap analysis, prioritization
research	Research workflows: MCP integration, multi-source synthesis, structured output
response-quality	Response quality standards, source citations
security	Security: OWASP, authentication, cryptography, DevSecOps, threat modeling, 12 skills
soft-skills	Career progression, interviews, communication, professional visibility
spec-driven-development	Spec Kit workflow: EARS, Gherkin, Kiro, ADRs, User Stories
systems-design	Scalability, distributed systems, quality attributes
tac	Tactical Agentic Coding: multi-agent workflows, prompt engineering, ADW
team-design	Team structure: Team Topologies, cognitive load, inverse Conway
test-strategy	Test planning: test pyramid, test case design, automation ROI
visualization	Diagrams-as-code (Mermaid, PlantUML)
wardley-mapping	Strategic positioning: value chain visualization, evolution analysis
windows-diagnostics	Windows system diagnostics, troubleshooting

Removed Plugins (v2.0 Consolidation)

The following plugins were removed because they primarily wrapped published standards that can be researched on-demand via MCP servers (perplexity, context7, microsoft-learn):

Removed Plugin	Methodology	MCP Alternative
ai-ml-planning	CRISP-DM, NIST AI RMF	`perplexity` for methodology, Claude generates templates
data-architecture	Kimball, Data Vault	`perplexity` for patterns, `microsoft-learn` for Azure Data
estimation-planning	Monte Carlo, FMEA	`perplexity` for technique, Claude calculates
observability-planning	SLO/SLI patterns	`perplexity` for observability patterns
product-discovery	Design Thinking, Lean Startup	`perplexity` for methodology, templates on-demand
quality-attributes	ISO 25010	`perplexity` for ISO 25010 model
saas-patterns	Multi-tenancy, Stripe billing	`perplexity` for architecture, `context7` for Stripe docs
ux-research	SUS, Nielsen heuristics, WCAG	`perplexity` for standards, checklists on-demand

Usage: Instead of these plugins, ask Claude directly: "Help me design X using [methodology]" and Claude will research via MCP and generate equivalent guidance.

Usage

List available skills (includes commands):

bash

/claude-ecosystem:list skills

Architecture

•Pure delegation: Skills delegate to docs-management for official docs
•Progressive disclosure: Content loads on-demand to optimize tokens

See individual plugin READMEs for details.

License

MIT - see LICENSE

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/formal-specification.md https://raw.githubusercontent.com/melodic-software/claude-code-plugins/main/SKILL.md

Invoke in Claude Code

/formal-specification

View source on GitHub

apidesign

Frequently Asked Questions

What is formal-specification?

Formal methods and specification languages: UML/SysML modeling, TLA+ specifications, OpenAPI/AsyncAPI contract-first design, state machines, and Use Case 2.0 methodology.

How to install formal-specification?

To install formal-specification, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /formal-specification.

What is formal-specification best for?

formal-specification is a community categorized under General. It is designed for: api, design. Created by Melodic Software.