competitor-research

competitor-research is a skill for Claude Code from mayuemarsha-del/pm-skills. It costs 123 tokens per session (4,267 once invoked), scanned A, original, MIT.

A skill for maintaining documents about competing products and AI research. It covers product features, agent modules, and framework comparisons, with rules for organizing facts, judgments, screenshots, and follow-up items.

In plain words
What is it for?
Use it when documenting a competitor, an AI application, an agent component, or a framework, including its menus, features, comparisons, and research findings.
Why use it?
It gives research notes a consistent structure and explains unfamiliar terms so readers can understand them without opening the original source.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the pm-skills plugin — 7 skills shipped together

Good fit Use it when documenting a competitor, an AI application, an agent component, or a framework, including its menus, features, comparisons, and research findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mayuemarsha-del/pm-skills/competitor-research
Install

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.

Any agent
npx skills add mayuemarsha-del/pm-skills --skill competitor-research
Clone the repo
git clone --depth 1 https://github.com/mayuemarsha-del/pm-skills

Made for: Claude Code.

Or install pm-skills, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for competitor-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/mayuemarsha-del/pm-skills/competitor-research/github.svg)](https://agentmods.dev/skills/mayuemarsha-del/pm-skills/competitor-research)
Your own site
<a href="https://agentmods.dev/skills/mayuemarsha-del/pm-skills/competitor-research"><img src="https://agentmods.dev/badge/skills/mayuemarsha-del/pm-skills/competitor-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for competitor-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/mayuemarsha-del/pm-skills/competitor-research"><img src="https://agentmods.dev/badge/skills/mayuemarsha-del/pm-skills/competitor-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.04267
Opus 5 $0.00062 $0.02133
Sonnet 5 $0.00025 $0.00853
Haiku 4.5 $0.00012 $0.00427

Measured 11d ago against content hash 087fd1667797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

competitor-research scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. `curl -sL <src> -o <路径>`,`file` 校验为 PNG/JPG。
skills/competitor-research/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  1. Competitor & Research Accumulation

    竞品与调研知识长期积累。排版套 prd skill 通用规则(短句 ≤30、全有序序号无 bullet、标题无括号、事实与〔判断〕分列、不杜撰、不确定标待补)。

    标题无括号 + 标题简洁是反复出错点

    1.1. 标题不塞备注:反面 ### 4.5 Monitors(Pro add-on),正面 ### 4.5 Monitors,备注下沉到标题下方第一行。 1.2. 标题不塞总结句:反面 #### 自动分两个队列,团队只看这两堆,正面 #### 两个队列,解释句下沉。 1.3. 标题不塞冒号 + 内容枚举:反面 #### 两个核心对象:Monitor 和 Scorecard,正面 #### 两个核心对象,对象名进正文。 1.4. 经验值:H4 标题尽量 ≤ 10 字,超过先想能不能拆掉 ", / 与 / + / 的" 后面那截。

  2. 输出路径

    2.1. AI 应用 / 行业产品<COMPETITION_DIR>/<分类>/<产品>/_现状.md。 2.2. Agent 模块 / 框架<RESEARCH_DIR>/<模块|AI框架/框架>/_现状.md

    <COMPETITION_DIR><RESEARCH_DIR> 由用户在 CLAUDE.md 中配置。

  3. 〇、写给产品经理看,不写给论文读者看

    文档读者是产品经理,不是论文作者。论文 / 基准 / 框架 / 模块条目一律遵守,写完不达标要重写:

    3.1. 不留裸术语:英文词、论文里的代号(如 c1 / aware-tool-only)、缩写,一律翻成中文说法,并在首次出现处就地一句话解释——读者不看原论文也能懂。 3.2. 开头先给一句话:每个 #### 条目第一条用大白话 + 生活化比方说清它到底在干嘛,再展开机制。例:DecisionBench 开头先写"像主管把活分给专长不同的下属"。 3.3. 多条件对比用表格:并列的方案 / 档位 / 实验条件(如"5 种递法各得几分"),用表格,不用多层嵌套编号。 3.4. 自检:写完通读一遍,凡"不看原论文就看不懂"的句子重写;宁可啰嗦,不留黑话。

  4. 一、两类对象

    4.1. AI 应用 / 行业产品 → <COMPETITION_DIR>/<分类>/<产品>/_现状.md。 4.2. Agent 模块 / 框架 → <RESEARCH_DIR>/<模块|AI框架/框架>/_现状.md。 4.3. 文件名一律 _现状.mdH1 标题不写「现状」: 1. 产品:# <产品> 汇总。 2. 模块:# Agent <模块>模块汇总。 3. 框架:# <框架> 框架汇总

  5. 二、AI 应用产品文档(硬性)

    无一例外按产品「功能菜单」梳理全部功能,类 Shulex。禁止只列「核心功能」简表。 这是高级 PM 基本功。

    5.1. 有账号:登录后台按产品自身菜单逐项走查,字段级(Shulex / Intercom 范式)。 5.2. 无账号:去帮助中心 / 官方文档 / 博客反推出功能菜单,不许偷懒只写几条。Sierra 是无账号菜单化范本。 5.3. 结构: 1. 主要作用(解决什么,3 类问题)。 2. 功能菜单(产品自身导航 / 模块树,尽量全)。行业专项范式:若产品无明确系统菜单(非账号实操、靠帮助中心反推),按你所在行业的标准能力树固定顺序拆。例如客服行业:① 接入渠道 ② 机器人功能 ③ 人工功能;机器人功能再细分配置 / 问答 / 转人工 / 训练调优 / 主动外呼;人工功能含工单 / 坐席工作台 / 坐席辅助 / 质检 / 排班 / 协作 等。这套统一框架让同行业竞品可横向比;有真实系统菜单(如账号走查)则按其本身菜单,不套此框架。 3. 各模块详解(每个 #### 写 作用 / 子功能 / 说明 / 链接)。「子功能」必须列到帮助中心能查到的具体能力 / 设置项级,不许只写一句话模块描述(反面例:Zendesk「工单」只写"跟踪归类解决"不合格;正面:列出 视图 / 触发器 / 自动化 / 宏 / SLA / 字段表单 / 状态 / 旁路会话 / 路由 / 轻量坐席 …)。帮助中心一定有,必须翻出来。 4. 〔判断〕对自家产品的启示。 5. 待补。 6. 参考(链接内联在所属内容旁)。 5.4. 达不到这个菜单深度,不算完成。

  6. 三、帮助中心必须真抓,不靠通识

    WebFetch 抓 JS 帮助中心多为空壳 / 404,不可靠。必须用真渲染浏览器抓:

    6.1. 用 chrome-devtools MCP(默认)或可选高速工具 browser-cap(装了 BROWSER_CAP_DIR 才有)。打开帮助中心首页,evaluate 取分类 / section 导航(a[href]/categories|sections|articles/)。 6.2. 逐层导航每个 section,取全部文章标题。 6.3. 明细要求:每篇帮助中心文章 = 一个功能项,逐条列出。禁止「N 篇:一句概括」(如「Train 9 篇:训练」不合格;要列出 添加内容 / 管理内容 / 启停内容 / 同步 URL / 管理商品信息… 9 条)。文章标题即功能名,逐条进各模块详解。关键配置篇再深入正文取设置项 / 字段。 6.4. 链接填对应 section / 文章真实 URL。文章 URL 模式各站不同(Zendesk = /hc/en-us/articles/<id>,Gorgias = /en-US/<slug>-<id>,非 /articles/)—— 先 dump 全 a 看真实 href 模式再写 filter。 6.5. 找不到帮助中心 URL:先打开官网首页,取含 help / support / docs 的链接定位真实文档站(如 Gorgias = docs.gorgias.com)。 6.6. 站点纯 JS 且无公开结构化帮助中心:据官博 / 公认能力梳理 + 标待补,建议登录后台按菜单实走

  7. 四、功能截图

    7.1. 只放真实产品 UI 图:从官方文档 / 帮助中心 / 博客提取 <img> 下载,存 <产品>/screenshots/。 7.2. 整页营销首页截图无用,禁用。 7.3. 取不到就写「功能截图待补 + 建议来源 URL」,不塞废图、不杜撰。 7.4. 抓取技法: 1. 浏览器打开目标页。 2. evaluate 取页面最大内容图 src(滤掉 logo / icon / avatar / banner)。 3. curl -sL <src> -o <路径>file 校验为 PNG/JPG。 4. 站点纯 JS 取不到图就用第 3 条。

  8. 五、账号截图:视口截图 + 等加载完成

    直接抓全页 contentSize(最多 12000px),在留白多的页面 / 弹窗会出 2000px+ 长图,文档读起来像翻书。

    改用 1440×900 视口截图:用 chrome-devtools MCP 的 setViewportSize 或 browser-cap 的 Emulation.setDeviceMetricsOverride 强制视口大小,截图时 captureBeyondViewport: false

    视口高度按内容决定:

    8.1. 窄信息页 / 简单弹窗 = 900(一屏)。 8.2. 多卡片页(如 Shulex 数据分析 9 卡 / Intercom Deploy/Email 整页配置) = 14001800(要看全 3 行内容)。 8.3. 长滚动页(如 Knowledge 全表) = 18002400。 8.4. 别用 captureBeyondViewport: true,会把 contentSize 整个抓下来。

    加载完成前不要截图(否则截到 spinner 占位 / 骨架屏):

    8.5. 导航后 sleep ≥ 5 秒(Intercom / 复杂 SPA 通常要 5–10 秒)。 8.6. 截前先 evaluate 校验:取 document.body.innerText 看是不是只有菜单 + 模块名(说明主体还在 loading),或检查 document.querySelector('[class*=spinner], [class*=loading]') 是否消失。 8.7. 截后立即 Read 看图,发现是 spinner / 白屏 / 骨架屏立刻重抓。 8.8. 弹窗截图前一步只 click 一次,不要连续 click 多个 button 触发竞态;不确定就在 click 后插入 sleep 1–2 秒再 evaluate 确认 modal 已出现。 8.9. 文件名 + 上下文匹配:弹窗 / 详情页用模块前缀(如 08c-Agent-工具详情-输入设置.png);同一交互的多个状态用同前缀 + 状态后缀。

Read the full file on GitHub · 158 lines

Changes

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.

  1. 11d ago First seen · 158 lines · 123 tokens per session scan A 087fd1667797

Subscribe to this mod's changes

competitor-research is a skill published in the GitHub repository mayuemarsha-del/pm-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 4,267 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.