LLM+

Competitor Repo Analyzer

Analyze competitor repositories with evidence-based approach. Use when tracking competitors, creating competitor profiles, or generating competitive analysis. CRITICAL - all analysis must be based on actual cloned code, never assumptions. Triggers include "analyze competitor", "add competitor", "competitive analysis", or "竞品分析".

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.
    Install
    git clone https://github.com/daymade/claude-code-skills.git /tmp/daymade__claude-code-skills && mkdir -p ~/.claude/skills/competitors-analysis-daymade && cp -r /tmp/daymade__claude-code-skills/competitors-analysis/. ~/.claude/skills/competitors-analysis-daymade/

    This copies the whole skill folder into ~/.claude/skills/competitors-analysis-daymade/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    mkdir -p ~/.claude/skills/competitors-analysis-daymade && curl -fsSL https://raw.githubusercontent.com/daymade/claude-code-skills/main/competitors-analysis/SKILL.md -o ~/.claude/skills/competitors-analysis-daymade/SKILL.md
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Analyze competitor repositories with evidence-based approach. Use when tracking competitors, creating competitor profiles, or generating competitive analysis. CRITICAL - all analysis must be based on actual cloned code, never assumptions. Triggers include "analyze competitor", "add competitor", "competitive analysis", or "竞品分析".

What this skill does

Competitors Analysis

Evidence-based competitor tracking and analysis. All analysis must be based on actual code, never assumptions.

CRITICAL: Evidence-Based Analysis Only

在开始分析之前,必须完成以下检查:

Pre-Analysis Checklist

  • 仓库已克隆到本地 ~/Workspace/competitors/{product}/
  • 可以 ls 查看目录结构
  • 可以 cat package.json (或等效配置文件) 读取版本信息
  • 可以 git log -1 确认代码是最新的

如果以上任何一项未完成,停止分析,先完成克隆操作。

Forbidden Patterns (禁止的表述)

禁止原因
"推测..."、"可能..."、"应该..."没有证据支持
"架构图(推测版)"必须基于实际代码
"未公开"、"未披露"如果不知道就不要写
不带来源的技术细节无法验证

Required Patterns (必须的表述)

正确格式示例
技术细节 + (来源: 文件:行号)"使用 better-sqlite3 (来源: package.json:88)"
直接引用 + 来源> "description text" (README.md:3)
版本号 + 来源"版本 1.3.3 (package.json:2)"

Analysis Workflow

Step 1: Clone Repository (必须)

# 创建产品竞品目录
mkdir -p ~/Workspace/competitors/{product-name}

# 克隆竞品仓库 (SSH,失败则重试)
cd ~/Workspace/competitors/{product-name}
git clone git@github.com:org/repo.git

网络问题处理: 中国网络环境可能需要多次重试。

Step 2: Gather Facts (收集事实)

按顺序读取以下文件,记录关键信息:

2.1 项目元数据

# Node.js 项目
cat package.json | head -20      # name, version, description
cat package.json | grep -A50 dependencies

# Python 项目
cat pyproject.toml               # 或 setup.py, requirements.txt

# Rust 项目
cat Cargo.toml

2.2 项目结构

ls -la                           # 根目录结构
ls src/                          # 源码目录
find . -name "*.md" -maxdepth 2  # 文档文件

2.3 核心模块

# 找到入口文件
cat main.js | head -50           # 或 index.js, app.py, main.rs
# 找到核心 helpers/utils
ls src/helpers/ 2>/dev/null || ls src/utils/ 2>/dev/null

2.4 README 和文档

cat README.md | head -100        # 官方描述
cat CHANGELOG.md | head -50      # 版本历史

Step 3: Deep Dive (深入分析)

针对关键技术点,读取具体实现文件:

# 示例:分析 ASR 实现
cat src/helpers/whisper.js       # 读取完整文件
grep -n "class.*Manager" src/helpers/*.js  # 找到核心类

记录格式:

| 文件 | 行号 | 发现 |
|------|------|------|
| whisper.js | 33-35 | 使用 WhisperServerManager |

Step 4: Write Profile (撰写分析)

使用 references/profile_template.md 模板,确保每个技术细节都有来源标注。

Step 5: Post-Analysis Verification (分析后验证)

自检清单:

  • 所有版本号都有来源标注?
  • 所有技术栈都来自 package.json/Cargo.toml?
  • 架构描述基于实际代码结构?
  • 没有"推测"、"可能"等词汇?
  • 对比表中的竞品数据都有来源?

Directory Structure

~/Workspace/competitors/
├── flowzero/              # Flowzero 的竞品
│   ├── openwhispr/        # git clone 的仓库
│   └── ...
└── {product-name}/        # 其他产品

{project}/docs/competitors/
├── README.md              # 索引(标注分析状态)
├── profiles/
│   └── {competitor}.md    # 基于代码的分析
├── landscape/
├── insights/
└── updates/2026/

Templates and Checklists

文档用途
references/profile_template.md竞品分析报告模板
references/analysis_checklist.md分析前/中/后检查清单

关键要求:

  1. 顶部必须标注数据来源路径和 commit hash
  2. 每个技术细节必须有 (来源: 文件:行号)
  3. 引用 README 内容必须标注行号
  4. 无法验证的标记为"待验证"并说明原因
  5. 分析完成后运行检查清单中的验证命令

Tech Stack Analysis Guide

Node.js / JavaScript

信息来源文件关键字段
版本package.jsonversion
依赖package.jsondependencies, devDependencies
入口package.jsonmain, scripts.start
框架package.jsonelectron, react, vite 等

Python

信息来源文件关键字段
版本pyproject.toml[project].version
依赖pyproject.toml / requirements.txtdependencies
入口pyproject.toml[project.scripts]

Rust

信息来源文件关键字段
版本Cargo.toml[package].version
依赖Cargo.toml[dependencies]

Common Mistakes to Avoid

1. 跳过克隆直接分析

❌ 错误: 从 GitHub 网页或 WebFetch 获取信息后直接写分析 ✅ 正确: 必须 git clone 到本地,用 Read 工具读取文件

2. 混合事实和推测

❌ 错误:

## 技术栈
- Electron (推测基于桌面应用特征)
- 可能使用了 React

✅ 正确:

## 技术栈 (来源: package.json)
| 依赖 | 版本 | 来源 |
|------|------|------|
| electron | 36.9.5 | package.json:68 |
| react | 19.1.0 | package.json:96 |

3. 使用过时信息

❌ 错误: 分析时不检查 git log,使用过时的代码 ✅ 正确: 分析前运行 git pull,记录分析时的 commit hash

4. 对比表中竞品数据无来源

❌ 错误:

| 维度 | 竞品 | 我们 |
|------|------|------|
| 支持语言 | 25种 | 58种 |

✅ 正确:

| 维度 | 竞品 | 来源 | 我们 |
|------|------|------|------|
| 支持语言 | 25种 | modelRegistryData.json:9-35 | 58种 (FunASR 官方文档) |

Scripts

See scripts/update-competitors.sh for repository management.

./scripts/update-competitors.sh clone   # 克隆所有竞品
./scripts/update-competitors.sh pull    # 更新所有竞品
./scripts/update-competitors.sh status  # 检查状态

Related skills

G

Generative Code Art

anthropics

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

OfficialComplete terms in LICENSE.txt
P

Poster & Visual Design

anthropics

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

OfficialComplete terms in LICENSE.txt
C

Claude API Helper

anthropics

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

OfficialComplete terms in LICENSE.txt
M

MCP Server Builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

OfficialComplete terms in LICENSE.txt