🛠️ carrilloapps/skills

Agent skills for AI coding agents — adversarial analysis, quality gates, and engineering best practices. Compatible with GitHub Copilot, Claude Code, Cursor, Windsurf, Cline, Codex, Gemini CLI and 40+ more.

---

Available Skills

Skill	Description	Version	Domains
🔴 devils-advocate	Mandatory adversarial risk gate — intercepts every plan before execution, blocks all actions until you explicitly approve		Architecture · Security · Performance · Data · Product · UX · Strategy · 12 total

---

Quick Install

# Install a specific skill
npx skills add carrilloapps/skills@devils-advocate

# Install all skills
npx skills add carrilloapps/skills

Target a specific agent

npx skills add carrilloapps/skills@devils-advocate -a github-copilot
npx skills add carrilloapps/skills@devils-advocate -a claude-code
npx skills add carrilloapps/skills@devils-advocate -a cursor
npx skills add carrilloapps/skills@devils-advocate -a windsurf

Global install (all your projects)

npx skills add carrilloapps/skills@devils-advocate -g

---

Skill Details

🔴 Devil's Advocate

The mandatory adversarial analysis gate for 40+ AI coding agents — runs first, before any action.

AI tools are increasingly capable of executing complex, multi-step operations — creating files, calling APIs, running migrations, deploying services. Devil's Advocate adds the adversarial voice that asks: "Should we?"

What it does:

1. Intercepts every plan, proposal, or action — before executing
2. Analyses across 12 risk domains using specialized frameworks
3. Fires alerts mid-sweep on the first High or Critical finding
4. Gates all actions — nothing executes without your explicit ✅ Proceed

Protocol stack:

Protocol	Trigger	Effect
⚡ Immediate Report	First 🟠 High or 🔴 Critical finding	Flash alert + context request mid-sweep
🛑 Handbrake	Any 🔴 Critical finding	Full stop + specialist escalation
📄 Full Report	After context or continue	Structured adversarial analysis
🚦 Gate	After full report	Waits for ✅ / 🔁 / ❌

12 domains covered: Architecture · Security · Performance · Developer/Code · Data & Analytics · Product · UX/Design · Strategy · AI Optimization · Version Control · Vulnerability Patterns · General Analysis

→ Full documentation: skills/devils-advocate/README.md

---

Repository Structure

carrilloapps/skills/
├── AGENTS.md           ← loads DA gate for AI agents
├── CHANGELOG.md        ← version history
├── scripts/
│   └── validate.sh         ← CI quality gate (49 checks)
└── skills/
    └── devils-advocate/    ← install: npx skills add carrilloapps/skills@devils-advocate
        ├── SKILL.md        ← always loaded by agents
        ├── README.md       ← full documentation
        ├── metadata.json   ← skill metadata
        ├── frameworks/     ← 18 domain & protocol frameworks
        ├── checklists/     ← 2 structured risk checklists
        └── examples/       ← 12 real-world analysis examples

Each skill is self-contained and independently installable via @<skill-name>.

---

Contributing

See CONTRIBUTING.md for how to add new skills or improve existing ones. Please read CODE_OF_CONDUCT.md before contributing. Security issues → SECURITY.md.

---

License

MIT — free to use, modify, and distribute. Attribution appreciated.

---

Built by José Carrillo · carrillo.app