corp
Structured AI team inside your repository, always aligned
❌ Coordinating complex tasks across multiple AI agents without clear context switching or decision hierarchy wastes time and produces inconsistent results.
✅ Users get organized multi-agent collaboration with clear domain ownership and a single entrypoint dispatcher that routes tasks to the right specialist.
- ✓CEO agent handles scope and product prioritization
- ✓Domain-specific agents for dev, design, QA, architecture
- ✓Single entrypoint dispatcher in CLAUDE.md file
- ✓Persistent agent definitions loaded from .claude/agents/
👁 2 views · 📦 0 installs
Free to install — no account needed
Copy the command below and paste into your agent.
Instant access • No coding needed • No account needed
What you get in 5 minutes
- Full skill code ready to install
- Works with 1 AI agent
- Lifetime updates included
Run this helper
Answer a few questions and let this helper do the work.
▸Advanced: use with your AI agent
Description
--- name: corp description: Multi-agent org structure for any repo. Loads a CEO, DEV, DESIGN, QA, and ARCH agent from .claude/agents/. Use when a task spans multiple domains, when you need to prioritize before building, or when working in a repo that contains corp agents. Dispatcher lives in CLAUDE.md — always read first. --- # corp > A company in a folder. Referential multi-agent org for AI coding assistants. ## Entrypoint Always start at `.claude/CLAUDE.md`. It dispatches to the right agent. ## Agents | File | Domain | Call when | |---|---|---| | `agents/CEO.md` | Scope, priorities, product decisions | Before building anything non-trivial | | `agents/DEV.md` | Code, backend, database | Writing or fixing anything | | `agents/DESIGN.md` | UI, components, CSS, interactions | Touching the frontend | | `agents/QA.md` | Quality gate, ship/no-ship | Before declaring done | | `agents/ARCH.md` | Schema, API contracts, system boundaries | Before touching data layer | ## Usage Pattern ``` Task arrives → Read CLAUDE.md → Identify domain → read that agent → Agent may call another → follow it → Implement → QA.md checklist → Ship ``` ## Token Protocol - Load agents on demand, never all at once - Tag all output: [CEO] [DEV] [DESIGN] [QA] [ARCH] - Prefer targeted edits over rewrites - Summarize before acting ## Setup 1. Copy `.claude/` to repo root 2. Edit `[PROJECT]` block in `CLAUDE.md` 3. Update entity/contract section in `ARCH.md` 4. Update file paths in `DEV.md` KNOWS section 5. See `CONTRIBUTING.md` for full guide ## Version 0.1.0
Security Status
Scanned
Passed automated security checks
Related AI Tools
More Save Money tools you might like
Family History Research Planning Skill
FreeProvides assistance with planning family history and genealogy research projects.
Naming Skill
FreeName products, SaaS, brands, open source projects, bots, and apps. Use when the user needs to name something, find a brand name, or pick a product name. Metaphor-driven process that produces memorable, meaningful names and avoids AI slop.
Profit Margin Calculator
$7.99Find hidden profit leaks — see exactly where your money goes
guard-scanner
Free"Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning, A2A contagion, secret leaks, supply-chain abuse, and dangerous tool calls with 364 static th
Life OS · Personal Decision Engine
Free"A personal decision engine with 16 independent AI agents, checks and balances, and swappable cultural themes. Covers relationships, finance, learning, execution, risk control, health, and infrastructure. Use when facing complex personal decisions (c
bbc-skill — Bilibili Comment Collector
FreeFetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (senti