Menu
Meta-skill for creating new MADFAM skills following the AgentSkills specification with proper directory structure and validation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Governed campaign copy generation from Tulana SKU packs -- claims-disciplined email subject lines, body copy, and CTAs grounded only in campaign-safe claims, es-MX primary.
Production-ready code implementation following MADFAM coding standards with git worktree workflows, strict type checking, and test-driven development.
Professional email delivery via Resend API — transactional, marketing, and autonomous CRM outreach across 10 verified MADFAM ecosystem domains.
Model Context Protocol server development for building platform extensions and tool integrations.
Refresh the staging database from prod with PII masked. Dump prod → mask-and-copy into staging → flip ArgoCD staging app to reconcile → smoke-test the staging URL → emit a refresh report. HITL-gated at the mask step because the target database is overwritten in place. Per the PhyndCRM PP.5 staging spec.
End-to-end testing with Playwright patterns for office-ui, Phaser scene testing, and comprehensive test coverage.
| name | skill-creator |
| description | Meta-skill for creating new MADFAM skills following the AgentSkills specification with proper directory structure and validation. |
| audience | platform |
| allowed_tools | ["file_read","file_write"] |
| metadata | {"category":"meta","complexity":"low"} |
You create new skills for the MADFAM platform following the AgentSkills specification.
skill-name/
SKILL.md # Required: YAML frontmatter + markdown instructions
scripts/ # Optional: automation scripts
references/ # Optional: reference documents
assets/ # Optional: images, templates, etc.
---
name: skill-name # Must match directory name, kebab-case
description: Brief description of the skill (max 1024 chars)
license: MIT # Optional
compatibility: ">=0.1.0" # Optional
allowed_tools: # Tools this skill grants access to
- file_read
- api_call
metadata: # Optional key-value pairs
category: development
complexity: medium
---
# Skill Title
Instructions for the agent when this skill is activated.
Keep under 5000 tokens for context efficiency.
my-skill-namename field in frontmatter.description is under 1024 characters.allowed_tools lists only valid ActionCategory values.DEFAULT_ROLE_SKILLS if it's a default for a role.