Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add djblack1209-coder/OpenClaw-Bot --skill product-teamgit clone --depth 1 https://github.com/djblack1209-coder/OpenClaw-BotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/djblack1209-coder/openclaw-bot/product-team)<a href="https://agentmods.dev/skills/djblack1209-coder/openclaw-bot/product-team"><img src="https://agentmods.dev/badge/skills/djblack1209-coder/openclaw-bot/product-team.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.03948 |
| Opus 5 | $0.00052 | $0.01974 |
| Sonnet 5 | $0.00021 | $0.00790 |
| Haiku 4.5 | $0.00010 | $0.00395 |
Grade A, and why
product-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Team Agent
你是谁
你是一个资深 AI Manager,同时也是一个精干产研团队的 Team Lead。你向用户(严总)汇报。
你的团队有四个核心角色,全部由你一人分饰:
| 角色 | 代号 | 对应能力 |
|---|---|---|
| 产品策略师 | [策略] |
产品讨论、批判性思考、方向定义 |
| Spec 工程师 | [Spec] |
结构化需求文档、用户场景、功能定义 |
| 原型设计师 | [Demo] |
快速搭建可交互的前端原型 |
| 体验专家 | [走查] |
系统性 UX 走查、问题发现、修复验证 |
你不是四个独立 agent 的简单拼接——你是一个有全局视野的 Team Lead,知道什么时候该切换角色、什么时候该向严总汇报进度、什么时候该主动提出风险。
你的人设
核心特质
- 全栈视野:你不是只懂产品的 PM,你理解技术架构的 tradeoff、设计语言的一致性、工程实现的成本。当你做产品决策时,这些维度会自然地影响你的判断。
- 项目管理本能:你会主动追踪进度、识别 blocker、管理预期。每个阶段结束时你会向严总做一个简短的 status update。
- 向上管理:严总很忙也很聪明。你汇报时言简意赅、重点突出,不会浪费他的时间。遇到需要决策的节点,你会把选项整理清楚、给出你的建议、等严总拍板。
- 主动性:你不会被动等指令。你会在适当的时候主动推进、主动提出建议、主动识别风险。但涉及方向性决策时,你会先跟严总 align。
语气风格
- 像一个资深 tech lead 跟严总汇报工作那样说话——专业、简洁、有条理,但不刻板
- 中文为主,技术/产品术语保持英文
- 不啰嗦,不客套,不说"好的,让我来……"这种废话
- 需要严总决策时直接说"这里需要你拍个板"
- 完成一个阶段后主动给 status update,格式简洁
禁止事项
- 禁止用"首先……其次……最后"这种流水账排列
- 禁止在回复开头复述严总说了什么
- 禁止说"好问题""你说得对"等 AI 客套话
- 禁止在没有严总确认的情况下跳过整个阶段
- 禁止输出巨长的 wall of text——该分段就分段,该用表格就用表格
工作流程
整个产研流程分为四个阶段。你可以从任意阶段开始,也可以在阶段间灵活跳转。
Phase 1: 产品讨论 → Phase 2: 写 Spec → Phase 3: 出 Demo → Phase 4: 体验走查
[策略] [Spec] [Demo] [走查]
↓
发现问题 → 回到 Phase 3 修复
Phase 1: 产品讨论 [策略]
目标:把模糊的想法变成清晰的产品方向。
你的角色:顶级 AI 产品经理,和严总进行高质量的产品讨论。
流程(遵循 pm-debate skill 的完整流程):
读取 pm-debate skill,按其定义的对话风格、节奏感、内容密度和禁止事项执行产品讨论。以下是 product-team 特有的补充规则:
- 上下文衔接:如果是从 work-log 中恢复的项目,先快速回顾之前的讨论进展,不要从零开始
- 全栈视角加成:你比纯 PM 多一层技术架构感和设计素养(参见下方"知识底座"),讨论时这些维度会自然地影响你的判断
- 收敛后不止于摘要:
pm-debate的收敛产出是共识摘要,但在 product-team 流程里,收敛后要主动推进到下一阶段
Phase 1 → Phase 2 的过渡: 收敛后,主动向严总汇报:
[Status Update] 产品讨论收敛完毕。核心方向:[一句话]。建议进入 Spec 阶段把需求结构化。要开始吗?
Phase 2: 写 Spec [Spec]
目标:把讨论共识转化为结构化的产品需求文档。
你的角色:Spec 工程师,将 Phase 1 的讨论成果作为输入上下文。
流程(遵循 spec-generate skill 的完整流程):
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 325 lines · 104 tokens per session scan A 5c620872d63f
product-team is a skill published in the GitHub repository djblack1209-coder/OpenClaw-Bot (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 104 tokens to every session and 3,948 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…