By Colin4k1024
Role-based Team Skills platform with an ECC-style harness skeleton, specialist agents, layered rules, commands, hooks skeleton, and frontend governance.
> 本文件由 `scripts/build-platform-artifacts.js` 生成,请勿手改。
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
> 本文件由 `scripts/build-platform-artifacts.js` 生成,请勿手改。
Create or verify a checkpoint in your workflow.
Legacy slash-entry shim for the nanoclaw-repl skill. Prefer the skill directly.
你是 Team Skills Platform 中的 `Architect(架构师)`,角色 ID 为 `architect`。
你是 Team Skills Platform 中的 `Backend Engineer(后端开发)`,角色 ID 为 `backend-engineer`。
你是 Team Skills Platform 中的 `DevOps Engineer(运维工程师)`,角色 ID 为 `devops-engineer`。
你是 Team Skills Platform 中的 `Frontend Engineer(前端开发)`,角色 ID 为 `frontend-engineer`。
你是 Team Skills Platform 中的 `Product Manager(产品经理)`,角色 ID 为 `product-manager`。
Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years experience managing hundreds of SKUs. Includes forecasting method selection, ABC/XYZ analysis, seasonal transition management, and vendor negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
Pattern for progressively refining context retrieval to solve the subagent context problem
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
面向团队协作与平台治理的开源 Team Skills Platform,用于把单代理执行模式升级成“Tech Lead 编排 + 专业角色协作”的虚拟研发团队工作模型,并叠加 ECC 风格的 harness layer、specialist 命令与运行时增强能力。当前平台同时支持 team mode 与 solo mode,前者强调多人交接,后者强调单人闭环但保留同样的关键门禁。
English: Team Skills Platform (TSP) is an open-source framework for role-based AI delivery workflows. It packages role prompts, shared skills, commands, rules, hooks, examples, and install tooling for Claude Code, Codex, and OpenCode. Custom extensions can be layered on top via the overlay mechanism; the public repository ships only public capabilities.
适合第一次体验公开能力的最短路径:
node scripts/build-platform-artifacts.js
node scripts/install-apply.js --profile team --target claude
node scripts/install-apply.js --profile full --target codex
node scripts/install-apply.js --profile full --target opencode
crates/oris-claude-bridge 与多平台预构建二进制,安装时按用户操作系统自动选择 bridge,无需本机 Rust 工具链。TSP 采用 角色 + 技能 + Agent + 规则 + Hooks + Workflow 引擎 六层架构:
| 层 | 目录 | 职责 |
|---|---|---|
| 角色定义 | roles/ | 8 个专业角色的 canonical YAML 定义(tech-lead 编排) |
| 技能层 | skills/ | 195+ 平铺技能,覆盖调试、编排、学习、前端、后端、安全等 |
| Agent 层 | agents/specialists/ | 27 个 specialist agents(规划、review、build-fix、语言专项) |
| 规则层 | rules/ | common 规则 + 13 语言规则包(TS/Python/Go/Java/Kotlin/Rust/Swift/C++/C#/PHP/Perl + 中文) |
| Hooks 层 | hooks/ + scripts/hooks/ | 37 个运行时 hook(prompt guard、context monitor、memory persistence 等) |
| 命令面 | commands/ | 80+ 命令(团队主链 8 个 + specialist + 工具链) |
| Workflow 引擎 | workflows/ + scripts/workflow-*.js | YAML DAG 工作流,支持依赖解析、状态持久化、失败恢复 |
安装工具链公开主线支持 3 个 code agent:Claude Code、Codex、OpenCode。其他历史 target 保留为隐藏兼容路径,不再作为公开 onboarding 主线。
TSP 为 OpenCode 提供了完整的适配支持,包括:
opencode.json 配置文件# 安装完整 OpenCode 配置
node scripts/install-apply.js --profile full --target opencode
# 或使用 npm 脚本
npm run install:opencode
安装完成后,OpenCode 配置文件位于 ~/.config/opencode/opencode.json,包含:
{
"$schema": "https://opencode.ai/config.json",
"instructions": ["./AGENTS.md"],
"plugin": ["team-skills-platform"],
"permission": {
"edit": "allow",
"bash": "allow"
}
}
opencode@tech-lead、@frontend-engineer 等方式切换角色/team-intake、/team-plan 等团队命令skill 工具加载 SKILL.md 文件~/.config/opencode/
├── AGENTS.md # 主配置文件(自动生成)
├── opencode.json # OpenCode 配置文件
├── agents/ # Agent 定义文件
│ ├── tech-lead.md
│ ├── product-manager.md
│ └── ...
├── command/ # 命令文件
│ ├── team-intake.md
│ ├── team-plan.md
│ └── ...
└── plugins/ # 插件目录
├── team-skills-platform/ # TSP 插件
│ ├── skills/ # 技能文件
│ ├── rules/ # 规则文件
│ └── ...
└── tsp-hooks.js # Hooks 插件
发布为 npm 包 @colin4k1024/tsp,内置 Rust bridge 预构建二进制,安装零依赖。
TSP 整合了多个社区开源框架的精华能力,而非从零构建:
npx claudepluginhub colin4k1024/tspHarness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.