Agent skill · software engineering · aradotso
citadel-agent-orchestration
citadel-agent-orchestration — an agent skill for coding agents.
Why this skill is useful
Adds executable scripts for autonomous coding campaigns and multi-tier orchestration that extend the AI's capabilities significantly.
What it needs
Requires node installed locally. Requires claude account access. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash 1. Clone Citadel once (global install — works across all projects) git clone https://github.com/SethGammon/Citadel.git ~/citadel 2. Launch Claude Code with the plugin loaded claude --plugin-dir ~/citadel 3. Run first-time setup inside any project /do setup /plugin marketplace add ~/citadel /plugin install citadel@citadel-local /reload-plugins /do fix the typo on line 42 → Direct edit (zero overhead) /do review the auth module → /review (5-pass code review) /do why is the API returning 500 → /systematic-debugging /do add payments to my app → /create-app tier 5 /do build me a recipe app → /prd → /architect → /archon /do overhaul all three services → /fleet (parallel agents) /do continue → resumes active campaign /prd "a recipe sharing app with user accounts and ratings" → Generates a full Product Requirements Document /architect → Converts active PRD into file tree, build phases, end conditions /create-app → End-to-end creation (5 tiers: blank → guided → templated → generated → feature addition) /review src/auth/ # 5-pass: correctness, security, performance, readability, consistency /test-gen src/payments.ts # Generates runnable tests; detects framework; retries up to 3x /doc-gen src/api/ # Function/module/API reference docs; matches your style /refactor src/legacy/ # Safe multi-file refactor; typechecks before/after; reverts on failure /scaffold "UserService" # Project-aware file generation; reads your conventions /create-skill # Turns a repeating pattern into a reusable Citadel skill /research "best approach for rate limiting in Express" /research-fleet "compare auth strategies: JWT vs sessions vs OAuth" # parallel scouts /experiment "optimize this function" fitness="benchmark score" # isolated worktree loops /systematic-debugging # 4-phase root cause; stops after 2 failed fixes /design # Generates/maintains design manifest for visual consistency /qa # Playwright-based browser interaction testing (optional dep) /postmortem # Auto-generates structured postmortem …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/citadel-agent-orchestration