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 ZJU-REAL/Easel --skill skill-competitor-analysisgit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/skill-competitor-analysis)<a href="https://agentmods.dev/skills/zju-real/easel/skill-competitor-analysis"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-competitor-analysis/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.
<a href="https://agentmods.dev/skills/zju-real/easel/skill-competitor-analysis"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-competitor-analysis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00123 | $0.01992 |
| Opus 5 | $0.00062 | $0.00996 |
| Sonnet 5 | $0.00025 | $0.00398 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade A, and why
skill-competitor-analysis 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 9d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
竞品内容分析
对同赛道竞品账号做全维度内容拆解：选题分布、发布节奏、爆款规律、格式偏好、互动模式，找出差异化机会，输出可落地的行动建议。
输入
用户 prompt 中提供以下信息（部分可选）：
- 必需：竞品账号名称或链接（1–5 个）、用户所在赛道/细分领域
- 可选：目标平台（小红书/抖音/B站/微博/知乎等）、分析侧重点（选题/格式/涨粉/变现等）、自己的账号名（用于对比）
输出
# 竞品内容分析报告
日期: {date}
赛道: {niche}
分析平台: {platforms}
竞品数: {N}
## 竞品账号画像卡
（每个竞品一张卡片）
- 账号名 / 平台 / 粉丝量级 / 简介定位
- 内容方向关键词 / 更新频率 / 主力格式
- 代表作 Top3（标题 + 数据 + 拆解）
## 选题分布
各竞品的内容主题分类与占比
## 格式与节奏
内容形式（图文/短视频/直播/轮播/合集）占比 + 发布频率与时间规律
## 爆款拆解
近期高互动内容的共性分析：标题模式、封面特征、内容结构、情绪钩子
## 互动模式
评论/点赞/收藏/转发的比例特征 + 评论区运营策略
## 热点借势分析
竞品如何跟热点、借势频率、效果评估
## SWOT 分析
每个主要竞品的内容层面 SWOT
## 差异化机会
竞品未覆盖/做得弱的选题、格式、人设、受众缺口
## 行动建议
按优先级排列的具体行动项，每条引用数据支撑
执行步骤
1. 收集上下文
确认以下信息，缺失的主动追问：
- 竞品账号列表（名称或链接）
- 用户赛道 / 细分领域
- 目标平台（默认覆盖竞品所在的全部平台）
- 分析侧重（默认全维度）
2. 竞品账号画像
对每个竞品账号建立基础画像。数据采集方法与各平台反爬降级方案参照 data-collection.md：
- 用
web_fetch抓取账号主页信息（账号简介、粉丝量级、作品数）；被反爬拦截时降级到web_search取公开信息 - 提取定位关键词、内容方向、人设特征
- 记录粉丝量级区间、账号活跃度
- 拿不到的数据（播放/完播/粉丝增量等创作者后台数据）如实标注"无公开数据"，不编造精确值
3. 选题与主题分析
梳理竞品近期内容（尽量覆盖近 30–90 天）：
- 按主题归类，统计各主题占比
- 识别核心选题方向（常青选题 vs 热点选题 vs 个人经历）
- 标注高频关键词和话题标签
4. 内容格式与发布节奏
分析竞品的格式偏好和发布规律（更新频率指标与涨粉节奏推断方法参照 viral-patterns.md）：
- 格式分布：图文 / 短视频 / 中长视频 / 直播 / 图片轮播 / 合集
- 发布频率：日更 / 周几更 / 不规律
- 发布时间段：集中在哪些时段
- 平台适配：同一内容在不同平台的差异化处理
5. 爆款内容拆解
爆款判定、拆解维度与"爆款密码"反推方法参照 viral-patterns.md。筛选互动量显著高于均值的内容（≥账号中位数 3–5 倍），逐条拆解：
- 标题/封面：用了什么钩子？（数字、悬念、痛点、反常识、情绪词）
- 内容结构：开头留人方式、中间节奏、结尾引导互动的手法
- 选题时机：是否踩中热点、节日、平台活动
- 格式特征：时长、图片数、排版、字体、BGM 等
6. 互动模式分析
分析竞品内容的互动特征：
- 互动结构：点赞/评论/收藏/转发的比例分布
- 评论区特征：用户主要在讨论什么、情绪倾向
- 博主互动：是否回复评论、回复风格、置顶评论策略
- 收藏型 vs 传播型：哪些内容被收藏多（工具向），哪些被转发多（情绪向）
7. 热点借势分析
用 web_fetch 调用热搜 API（参照 hotlist-apis.md）获取当前各平台热点，然后：
- 对比竞品近期内容与热搜话题的重合度
- 分析竞品追热点的频率、速度、角度
- 评估追热点内容 vs 常规内容的互动差异
- 识别竞品擅长借势的热点类型（社会事件/行业动态/平台梗/节日）
8. SWOT 分析
对每个主要竞品做内容层面的 SWOT：
- S（优势）：内容质量、更新频率、人设辨识度、粉丝粘性
- W（劣势）：格式单一、选题窄、互动少、更新不稳定
- O（机会）：未覆盖的受众需求、新兴平台/格式、赛道空白
- T（威胁）：该竞品对用户的直接竞争压力点
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 158 lines · 123 tokens per session scan A f7326a2f97d8
skill-competitor-analysis is a skill published in the GitHub repository ZJU-REAL/Easel (411 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 1,992 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.