Claim this agent
agentCLAWHUBUnverified

competitive-product-research

Dual-track competitive research: experience benchmarking (8 UX dimensions) + strategic diagnostics (SWOT/Five Forces/PESTLE), source-traceable HTML or Markdown report. Use when competitive analysis, benchmarking, differentiation strategy, or when the user says「竞品调研」「对标分析」「和 XX 比差在哪」. Skill: competitive-product-research Owner: chris1wang3 Summary: Dual-track competitive research: experience benchmarking (8 UX dimensions) + strategic diagnostics (SWOT/Five Forces/PESTLE), source-traceable HTML or Markdown report. Use when competitive analysis, benchmarking, differentiation strategy, or when the user says「竞品调研」「对标分析」「和 XX 比差在哪」. Tags: latest:1.4.8 Version history: v1.4.8 | 2026-08-19T07:41:19.408Z |

OpenClaw

Rank

62

Safety

84

Downloads

2.2k

Updated

Oct 9, 2026

Version

1.4.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 9, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 9, 2026
Adoption signal
2.2K downloadsadoption · observed Oct 9, 2026
Latest release
1.4.8release · observed Aug 19, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ehszmyd9ccm7mgt9m7gme69845625:competitive-product-research
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chris1wang3-competitive-product-research/snapshot"

Documentation

CLAWHUB

131,084 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: competitive-product-research
slug: competitive-product-research
version: 1.4.8
displayName: 竞品调研 · CPR
description: >-
  Dual-track competitive research: experience benchmarking (8 UX dimensions) + strategic diagnostics (SWOT/Five Forces/PESTLE), source-traceable HTML or Markdown report.
  Use when competitive analysis, benchmarking, differentiation strategy, or when the user says「竞品调研」「对标分析」「和 XX 比差在哪」.
---

# 竞品调研 · Competitive Product Research

> **EN** Dual-track benchmarking + strategy → source-traceable HTML / Markdown (`SRC-xxx`).  
> **中文** 体验对标 + 战略诊断 → 证据可溯源 HTML / Markdown 报告。

**When / 何时用:** 对标 · 差异化 · SWOT/五力/PESTLE · 评审前材料  
**Not / 不用:** 拍脑袋市场规模 · 纯概念战略 · 违规采集 · 替用户拍板

```text
Our app post conversion is 3% — benchmark Xiaohongshu vs Instagram, first-post funnel.
我们 App 发帖转化率 3%,对标小红书与 Instagram 分析首链路。
```

也可「帮我做 XX 和 YY 竞品调研」/ "benchmark X against Y" — 先清单,再报告。

## 可直接触发的说法

以下口语输入都应触发本技能,不要求用户先按模板填写:

- 帮我拉一版 XX 和 YY 的竞品对标。
- 我们这个功能和小红书/抖音比差在哪?
- 对标一下竞品的首单/发布/开户/投顾链路。
- 我只有几张截图,先帮我做一版体验差异分析。
- 这个 PRD 评审前需要一份竞品材料。
- 帮我判断这个赛道里我们该学谁、不该学谁。
- 竞品最近这么做背后的策略是什么?
- 给我一份能给老板看的竞品 HTML 报告。

## 最小可用输入

**最低可启动**:调研目标 + 至少 1 个明确竞品。若只有 1 个竞品,先询问是否需要补第 2 个;用户不补时,可用“我方方案/行业常见做法”作为对照,并在报告中标注对照口径。

**推荐输入**:调研目标、对标对象、我方现状、核心场景、报告用途、输出格式、可用材料(链接/截图/PRD/数据)。

**可兼容输入**:

- 一句话需求:先提炼目标、对象、场景,再给采集清单。
- 截图/链接/碎片材料:先建证据索引,缺口标 `SRC-GAP`。
- 中英混合或口语输入:保持用户原意,统一为调研参数。
- 用户说“直接生成”:只跳过业务信息追问,用保守假设继续,并在报告首屏标注假设;**不视为跳过输出格式确认**。

## 工作流

```text
1) 提交调研需求  2) 信息采集清单  3) 问题对齐 + 证据建库
4) 双轨分析(体验八维 + 战略四件套)  5) 按用户选择生成 HTML / Markdown 报告
```

### 信息采集清单(第 2 步)

预填 +「待补充」;可说「跳过,直接生成」。

```text
1️⃣ 调研目标  2️⃣ 对标对象(至少 1 个,推荐 ≥2)  3️⃣ 我方现状  4️⃣ 核心场景  5️⃣ 行业
6️⃣ 补充材料  7️⃣ 战略模块(格局/SWOT/五力/PESTLE)  8️⃣ 报告用途(内部/对外脱敏)
9️⃣ 输出格式(HTML / Markdown)  🔟 约束条件
```

**采集交互(优先使用可操作表单)**:

- **必须复用** [assets/intake-form.html](assets/intake-form.html),不得临时重写表单 UI。
- 将上下文预填为 `prefill` URL 参数(URI 编码 JSON);推断值不得伪装成用户确认值,输出格式保持未选。
- 宿主支持内嵌 HTML 时直接展示;否则复制该资产到当前输出目录并用浏览器打开。提交后读取宿主回传或用户粘贴的结构化参数。回传统一使用 `{schema_version:"1.0", skill, action, data}`;优先 `window.codex.submitForm`,兼容 `window.openai.sendFollowUpMessage`,最后复制 JSON。
- 仅当宿主无法展示或打开 HTML 时退回文本清单;格式未确认不得生成,用户明确委托默认时使用 HTML。

## 方法概要

双轨四层法详规 → [research-playbook.md](references/research-playbook.md)

- **体验轨(八维)**:竞品怎么做、我方差在哪 → D1–D8,先拆最小操作节点
- **战略轨(可选)**:赛道为何如此、我方怎么打 → 格局 · SWOT · 五力 · PESTLE
- **证据**:每条关键结论挂 `SRC-xxx`(U 用户 / P 公开 / H 经验须标验证)

## 输出

按采集表确认的格式生成:HTML 严格使用 [report-template-pro.html](references/report-template-pro.html);Markdown 使用同一分区结构。格式锁、事实边界、文风、自检 → [research-playbook.md](references/research-playbook.md)。

必含:对标表 · Key Findings · 路线图(Owner/优先级)· Source Index · 免责声明。对外分享须脱敏。

HTML 报告中的公开来源证据标签必须可点击并直接打开对应 URL;同一单元格有多个来源时,每个 `SRC-xxx` 分别生成链接,禁止合并成一个不可点击的标签。无 URL 的用户材料、行业推断和证据缺口链接到 Source Index 内对应条目,并明确标注其类型。

## 硬约束

- **信息优先**:禁止编造;缺失标注;推断透明;清单追问优于脑补
- **证据**:关键结论至少一个 `SRC-xxx`;HTML 的公开来源 `SRC-xxx` 必须直接链接来源 URL;体验轨与策略轨不重复
- **输出**:具名、具数、具动作;必有执行建议
- **优先级**:信息优先 > 格式锁 > playbook > 文风护栏

**Rigid**(不可跳过):
- SR

_meta.json

{
  "ownerId": "kn7f3jb3kjvh47ryp89pp9cyzs8306wn",
  "slug": "competitive-product-research",
  "version": "1.4.8",
  "publishedAt": 1787125279408
}

references/research-playbook.md

# 竞品调研方法手册(Research Playbook)

> `SKILL.md` 执行附录:强调可复跑、可追溯、可落地。

---

## A. 方法总览(双轨四层法)

- **四层流程**:信息采集 → 问题对齐 → 证据建库 → 双轨分析 → 决策输出(HTML / Markdown)
- **双轨分工**:
  - 体验对标轨(八维):回答"怎么做、差在哪"
  - 战略诊断轨(可选):回答"为什么竞争、怎么赢"
- **信息采集先行**:始终先输出采集清单,用户确认/跳过后才开始分析,确保信息充分度

避免四种失败:

1. 只有功能对比,没有策略判断
2. 只有战略口号,没有体验动作
3. 信息不充分就硬写报告,导致结论空泛
4. 不做信息采集直接生成,遗漏关键上下文

---

## A1. 信息采集规则

**交互形态优先级**:必须复用 `assets/intake-form.html`;宿主支持时内嵌,否则在浏览器打开。只有 HTML 无法使用时才退回文本清单。表单覆盖全部 10 项,输出格式不得预选;提交后的结构化参数才是确认结果。

**最低可启动输入**:调研目标 + 至少 1 个明确竞品。只有 1 个竞品时,先询问是否补第 2 个;用户跳过时,可用我方方案、行业常见做法或历史版本作为参照,并在报告中标注限制。

**采集清单输出后的用户回复处理**:

| 用户行为 | 处理方式 |
|---------|---------|
| 逐项补充 | 更新所有字段后开始分析 |
| "跳过,直接生成" | 跳过业务信息补充,用推断值启动;若格式未明确,仍须单独确认 HTML / Markdown |
| 只补部分 | 已补字段用实值,其余用推断值 |
| 反问/要求调整 | 修改采集清单后重新确认 |
| 只给 1 个竞品 | 询问补充第 2 个;若跳过,则降级为单竞品对照 |
| 只给截图/链接 | 先建立 Source Index,再补调研参数 |

**推断逻辑**:

| 信息 | 推断方式 | 推断失败时 |
|------|----------|-----------|
| 行业 | 从需求关键词推断(拼团→电商;投顾→金融) | 标"待补充" |
| 核心场景 | 从调研目标中推断最小核心链路 | 标"待补充" |
| 战略模块 | 涉及赛道/定位/定价→开启;纯体验问题→关闭 | 默认关闭 |
| 报告用途 | "评审""排期"→内部;"客户""伙伴"→对外 | 预填内部评审 |
| 约束条件 | 从需求中提取时间、资源限制 | 标"待补充" |

**信息缺失处理**:

- 只有"调研目标 + 对标对象"时可以启动,但必须先列出 ≤3 条关键假设
- 只有 1 个竞品时可以启动,但报告标题区必须标注"单竞品对照"
- 缺少我方现状 → 不编造内部数据;报告中对应章节标注「假设」,段首加"基于假设:……"
- 缺少核心场景 → 选择最能回答调研目标的单一核心链路,报告 Hero 区标注"聚焦单一链路"
- 公开来源不可访问 → 记录为 `SRC-GAP`,写清楚缺口影响和下一步补证动作
- 行业未确认 → 从对标对象推断,推断值在报告标签区加 `[推断]`
- 跳过的项目将按保守判断处理,报告中明确标注哪些结论基于假设

**保守判断原则**:

- 用户未提供的信息,分析时给保守判断,evidence 注明"用户未提供,保守处理"
- 推断来的信息在报告中标注「推断」,用户可纠正
- 宁可结论保守,不可凭空脑补

---

## A2. 问题对齐(Layer A)

基于采集清单确认后的信息,整理最终执行参数:

1. 目标问题
2. 对标对象
3. 我方现状
4. 核心场景
5. 是否启用战略模块(竞争格局 / SWOT / 五力 / PESTLE)
6. 报告用途

合并规则:

`用户明确修改 > 用户确认推断 > 已预填推断 > 未提供字段`

---

## B. 证据建库(三层证据法)

统一编号:`SRC-xxx`

| 类型 | 说明 | 可信度 |
|---|---|---|
| SRC-U | 用户材料(截图/录屏/内部文档) | 高 |
| SRC-P | 公开来源(官网/公开文档/权威媒体) | 中高 |
| SRC-H | 行业经验(需标"建议验证") | 低 |

规则:

- 每条关键结论至少挂 1 个来源
- 含数字结论必须可追溯
- 无公开价格时,不写具体价位
- 不可核实的数据不写具体数值
- 公开来源不可访问时记录为 `SRC-GAP`
- 网上检索只可作为线索,不得把搜索摘要直接当事实;关键事实优先交叉核对官网、年报、公开文档、权威媒体或用户材料
- 区分三类表述:已核实、官方口径、推断/行业常识;推断不得伪装成已核实事实
- 若对标物是社区方案、示意图、多产品组合,必须写明“非单一 SKU”或“无统一官网定价”,避免与正式产品作不对等比较
- HTML 报告中,所有结构化 Evidence 字段里的公开来源 `SRC-Pxxx` 必须使用 `<a>` 直接链接其来源 URL,并设置 `target="_blank" rel="noopener"`
- 一个 Evidence 单元格引用多个来源时,每个 `SRC-xxx` 必须拆成独立标签;不得把 `P002/U001` 等多个编号合并为一个不可点击 pill
- 没有外部 URL 的 `SRC-U`、`SRC-H`、`SRC-GAP` 使用页内锚点跳转到 Source Index 对应条目;Source Index 条目必须有与证据编号一致的 `id`

---

## C. 体验对标轨(八维详细规则)

### C1. 八维检查清单

| 维度 | 核心检查点 |
|------|-----------|
| D1 信息架构 | 入口可发现性、层级合理性 |
| D2 交互流程 | 步骤流畅度、中断恢复 |
| D3 视觉表达 | 信息层级、可读性、反馈显著性 |
| D4 文案设计 | 指令清晰度、错误文案可行动性 |
| D5 行为驱动 | 激励机制、首任务完成支持 |
| D6 异常边界 | 空态、弱网、权限拒绝等处理 |
| D7 跨端一致 | 多端与主题下的一致性 |
| D8 合规可及 | 隐私提示、可访问性、审计友好度 |

### C2. 场景拆解

把核心任务拆成最小操作节点:

```text
启动应用 → 找到入口 → 进入编辑 → 内容填写 → 提交发布 → 反馈确认
```

每个节点记录 5 项:入口、操作、反馈、出口、异常。

先拆"最小操作节点",再做逐产品对照。

### C3. 对标总览表(列定义)

| 列 | 填写原则 |
|---|---|
| 产品 | 统一命名,不混版本噪音 |
| 场景节点 |

skill-card.md

## Description:

Dual-track competitive research for experience benchmarking and strategic diagnostics that produces source-traceable HTML or Markdown reports.

This skill is ready for commercial/non-commercial use.

## Publisher:

[chris1wang3](https://clawhub.ai/user/chris1wang3)

### License/Terms of Use:

MIT-0

## Use Case:

Product managers, UX researchers, and strategy teams use this skill to collect competitive research inputs, benchmark product experiences across eight UX dimensions, run optional strategic diagnostics, and deliver evidence-traceable HTML or Markdown reports.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Internal materials entered into the intake form or reports may contain sensitive competitive, product, or customer information.

Mitigation: Review and redact internal materials before adding them to the intake form or generated report, and use the skill's external-sharing desensitization guidance for public outputs.

Risk: Competitive conclusions can be misleading when source evidence is missing, inaccessible, or based on assumptions.

Mitigation: Require SRC evidence labels for key claims, mark evidence gaps explicitly, and avoid specific unsupported numbers.

Risk: The optional Chrome-based regression script is intended for developer testing rather than routine agent execution.

Mitigation: Treat the local Chrome test script as a developer-only tool and run it only in a controlled local environment.

## Reference(s):

- [Research Playbook](references/research-playbook.md)
- [HTML Report Template](references/report-template-pro.html)
- [Intake Form](assets/intake-form.html)

## Skill Output:

**Output Type(s):** [text, markdown, code, configuration, guidance]

**Output Format:** [HTML or Markdown report with source index and evidence labels]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Reports include benchmark tables, key findings, a prioritized roadmap with owners, a source index, and a disclaimer.]

## Skill Version(s):

1.4.8 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

claw.json

{
  "name": "competitive-product-research",
  "version": "1.4.8",
  "tagline": "Dual-track competitive research: experience benchmarking + strategic diagnostics / 竞品调研:双轨四层法,体验对标+战略诊断,输出证据可溯源报告",
  "description": "Competitive analysis shouldn't be a feature checklist. What you need is structured judgment — what to follow, what to leapfrog, and what to ignore. CPR uses an original dual-track method — experience benchmarking (8 UX dimensions) + strategic diagnostics (SWOT, Five Forces, PESTLE) — collects sufficient context via a structured checklist, then produces a source-traceable professional HTML or Markdown report with actionable recommendations. 竞品调研不应是观点合集。双轨四层法,体验+策略同时跑,先通过信息采集清单收集充分上下文,再输出带证据编号、动作、责任人、复杂度的专业 HTML 或 Markdown 报告。",
  "category": "productivity",
  "tags": [
    "product-management",
    "competitive-analysis",
    "ux-research",
    "benchmarking",
    "html-report",
    "product-strategy",
    "chinese"
  ],
  "license": "MIT",
  "author": "Chris1Wang3",
  "pricing": "free",
  "entry": "SKILL.md",
  "support_url": "https://github.com/Chris1Wang3/Idea-on-Trial/issues",
  "homepage": "https://github.com/Chris1Wang3/Idea-on-Trial/tree/master/competitive-product-research"
}
Github ReposUpdated 1h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/chris1wang3/skills/competitive-product-research",
      "sourceUrl": "https://clawhub.ai/chris1wang3/skills/competitive-product-research",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:16:01.329Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-chris1wang3-competitive-product-research/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-chris1wang3-competitive-product-research/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:16:01.329Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.2K downloads",
      "href": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceUrl": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:16:01.329Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.4.8",
      "href": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceUrl": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-19T07:41:19.408Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-chris1wang3-competitive-product-research/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-chris1wang3-competitive-product-research/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.4.8",
      "description": "Clickable evidence links: public sources open directly; multiple sources are split; non-URL evidence links to Source Index.",
      "href": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceUrl": "https://clawhub.ai/chris1wang3/competitive-product-research",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-19T07:41:19.408Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

Sponsored

Ads related to competitive-product-research and adjacent AI workflows.