jessepwj/CCteam-creator
286 stars · Last commit 2026-04-13
Multi-agent team orchestration skill for Claude Code. Set up parallel AI agent teams with file-based planning and role-based collaboration.
README preview
# CCteam-creator > Multi-agent team orchestration skill for [Claude Code](https://code.claude.com/). **One skill, a full engineering team.** CCteam-creator turns a single Claude Code session into a coordinated team of 2-6 AI agents — with built-in CI enforcement, code review, doc-code sync, and a taste feedback loop that encodes your preferences into automated checks. Human steers, agents execute. [English](./README.md) | [中文](./README_CN.md) ## Standing on the Shoulders of Giants CCteam-creator is built upon outstanding open-source projects and engineering practices: | Source | What We Learned | |--------|-----------------| | [**planning-with-files**](https://github.com/OthmanAdi/planning-with-files) | Manus-style persistent markdown planning — the 3-file pattern (task_plan.md / findings.md / progress.md) that survives context compression. The "context window = RAM, file system = disk" philosophy. | | [**everything-claude-code**](https://github.com/affaan-m/everything-claude-code) | Agent harness optimization by Anthropic hackathon winner. 13 expert agents, 40+ skills. Inspired our role-based agent design and skill structure. | | [**mattpocock/skills**](https://github.com/mattpocock/skills) | TDD vertical-slice philosophy, "design it twice" parallel sub-agent pattern, interface durability principles, and plan stress-testing methodology. | | [**OpenAI Harness Engineering**](https://openai.com/index/harness-engineering/) | The discipline of designing constraints, feedback loops, and documentation systems that make AI agents reliable at scale. Inspired our docs/ knowledge base, invariant-driven review, Doc-Code Sync, failure-to-guardrail loop, and anti-bloat principles. | | [**Anthropic Harness Design**](https://www.anthropic.com/engineering/harness-design) | Anthropic Labs' research on multi-agent architectures for long-running autonomous coding. Three key lessons absorbed into CCteam-creator: (1) **Evaluator calibration** — out-of-the-box LLMs are poor QA agents that rationalize away issues; the fix is few-shot calibration anchors with concrete STRONG/WEAK examples, which shaped our Review Dimensions system. (2) **Every harness component is an assumption** — each mechanism encodes a belief about what the model can't do alone, and these assumptions go stale as models improve; this became our Assumption Audit checklist. (3) **Generator-evaluator separation** — separating the agent doing the work from the agent judging it is more tractable than making a generator self-critical, validating our existing dev/reviewer split and motivating the anti-leniency rule. |