Skills

Reusable skills for AI coding agents. Works with pi, Claude Code, Cursor, and any agent that supports the Agent Skills standard.

Available Skills

Category	Skill	Description
☁️ Azure	azcli	Azure CLI with agent safety model — hub + reference files
☁️ Google Cloud	gcloud	GCP CLI with agent safety model — hub + 7 reference files
🔧 Maintenance	repo-hygiene	Periodic repo health check — deps, git, CI, code quality, docs, security
⚙️ Process	pm2	Process management — keep services alive, auto-restart, monitoring, ecosystem configs
🚀 Release	pre-release	Pre-release checklist + AI-written changesets via @changesets/cli
🔍 Search	web-search	Web search + content extraction via ddgs — no API keys
📊 Modeling	sheet-model	Headless spreadsheet engine for financial modeling, scenario analysis, .xlsx with live formulas
🎬 Terminal	vhs	Record terminal sessions as GIF/MP4 with VHS

Install

One command (39+ agents)

npx skills add marcfargas/skills

Installs to Claude Code, Cursor, Copilot, Amp, Cline, Windsurf, Gemini CLI, and 30+ more agents automatically.

pi

pi install npm:@marcfargas/skills

Or add to ~/.pi/agent/settings.json:

{
  "packages": ["npm:@marcfargas/skills"]
}

Manual (any agent)

Copy the skill directory into your agent's skill folder:

cp -r google-cloud/gcloud ~/.claude/skills/gcloud

How We Build Skills

Multi-Model Review

Every skill is reviewed by 3+ models (Claude, Gemini, GPT) before publishing — structure, agent usability, safety, and real-world scenario testing. If an agent can misinterpret an instruction, we find out before you do.

Safety Classification

Every operation is classified: READ / WRITE / DESTRUCTIVE / EXPENSIVE / FORBIDDEN. Destructive and expensive operations are gated — the agent must confirm before executing, and costs are flagged upfront.

Progressive Discovery

Skills use a hub + spoke architecture. The SKILL.md hub is ~140 lines — just enough to match the right skill and know what's available. Detailed per-topic reference files are loaded on demand, keeping your context window lean.

Also

• Agent-native — --format=json everywhere, idempotent patterns, structured error handling
• Portable — no hardcoded paths, no personal config, works on any machine
• Spec-compliant — validated against the Agent Skills specification using skills-ref in CI
• Continuous validation — agentskills validate on every push (validate.yml), pre-release checklist with AI-written changesets, npm Trusted Publishing with provenance

Structure

skills/
├── azcli/               # Azure CLI — hub + 7 reference files
├── gcloud/              # GCP CLI — hub + 7 reference files
├── repo-hygiene/        # Periodic repo health check
├── pm2/                 # Process management
├── pre-release/         # Pre-release checklist + changesets
├── web-search/          # Web search + content extraction
├── sheet-model/         # Headless spreadsheet engine
├── vhs/                 # Terminal session recording
└── README.md

External Skills

Some skills live in their own repositories — install them directly or via their npm packages:

Skill	Description	Install
go-easy	Gmail, Drive, Calendar for AI agents — npx go-gmail, npx go-drive, npx go-calendar	npx skills add marcfargas/go-easy
holdpty	Detached PTY sessions — launch, attach, view, record terminal processes	npx skills add marcfargas/holdpty
odoo	Odoo ERP integration — connect, introspect, automate	npx skills add marcfargas/odoo-toolbox

Contributing

Skills follow the Agent Skills specification. Requirements:

• SKILL.md with YAML frontmatter (name, description)
• name matches parent directory (kebab-case, max 64 chars)
• description present (max 1024 chars)
• No hardcoded paths or credentials
• Destructive operations clearly marked

Validation

Use skills-ref (Python — the official reference implementation from the spec authors) to validate skills locally:

pip install skills-ref

# Validate a skill directory
agentskills validate path/to/skill

# Read parsed properties as JSON
agentskills read-properties path/to/skill

# Generate <available_skills> XML prompt block
agentskills to-prompt path/to/skill-a path/to/skill-b

CI runs agentskills validate on every push — see .github/workflows/validate.yml.

Sponsor

Building high-quality, multi-model-reviewed agent skills takes serious token budget. If these skills save you time, consider sponsoring:

License

Code (scripts, tooling): MIT

Skill content (**/SKILL.md and reference docs): CC0 1.0 Universal — public domain, no attribution required.

Why CC0 for skills: Skill docs are consumed by AI agents and freely incorporated into any workflow. Attribution requirements create friction in agent contexts where provenance tracking is impractical.