SkillFoxx

Readme.skill

A skill that builds an anonymized developer profile and a vertical poster from local Claude Code and other CLI history

  • 175 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • Reads local tool history and runs SQLite queries
  • Calls gh for public GitHub contributions
All reasons and checks

study8677/readme.skillAuthor:study8677

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/readme-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reads local tool history and runs SQLite queries
  • Calls gh for public GitHub contributions

This is third-party code. Review the repository files before installing.

What it does

The skill reads local usage data from several tools: Claude Code, Codex CLI, Kiro, Trae, Gemini Antigravity and Cursor, computes a set of metrics and produces two outputs: a long markdown report and a vertical SVG poster. The report covers AI-work practices across ten dimensions, and you can set a window: a month, a date range or the last few days. By default everything is anonymized: project names become placeholders, private repos are hidden, and keys, tokens and email are scrubbed. It all runs locally; the only network call is a request for your public GitHub contributions via gh.

Who it is for. For developers who want to show their AI-work experience as a clear profile and poster.

Good fit when

  • You want a profile for the top of your GitHub page
  • You want a monthly or quarterly review of your AI-tool work
  • You want a poster with key numbers for social media

Not a fit when

  • You have no local history from any supported tool
  • You cannot run a local analysis of your work data

Example request

Generate my AI-work developer profile for the last thirty days

Limitations

The skill counts only the tools whose history is on the machine and skips the missing ones. The interface and references are mostly Chinese, with English output on request. GitHub contribution data needs gh installed; the rest runs locally without writing into the agent's directory.

How to disable. Uninstall the readme-skill plugin via /plugin or remove the skill folder from the agent's skills directory.

FAQ

Is any data sent anywhere?

No, the analysis is local and read-only; the only outbound call is for public GitHub contributions via gh.

Can project names be hidden?

By default they are already anonymized, private repos and secrets are scrubbed, and the non-anonymized mode is enabled explicitly.

Discussion

No questions or reviews yet.

Skills

About a hundred skills for Claude Code: meetings, research, publishing, TDD, Telegram, email and personal analytics

PluginBroad access413

Skill that reads your prompt history, finds the asks you repeat and turns each into a short command such as /sent

SkillExtended access134

A desktop app and skm CLI: one copy of each skill in a central hub, symlinked into every AI tool

CLIExtended access1.1K

cafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository

SkillExtended access256

ai-labs-claude-skills installs 24 Claude skills through one npm package: SEO reports, Docker, CI/CD, CSV analysis, resumes, pitch decks and more

SkillExtended access469

A skill that builds one preparation document for a job interview: company research, job description, resume and likely questions.

SkillMinimal access62

README in short

The README describes a skill that quickly turns real AI-tool usage data into an anonymized developer card: a long report and a vertical poster. Six tools are supported and any missing one is skipped automatically. Work is fully local and read-only, without writing into the agent's directory, with anonymization on by default and secret scrubbing via regular expressions. It offers monthly and windowed reports and Chinese or English output. Installation is a few steps and it ships as a plugin with marketplace.json. MIT licensed.

README badge

Original SKILL.md

---
name: readme-skill
description: >
  生成一份对外可分享、脱敏的 AI-Native 开发者 README。
  量化展示我对 Claude Code + Codex CLI + Kiro (AWS) + Trae (ByteDance) +
  Gemini Antigravity (Google) + Cursor 的使用深度、AI 协作风格、
  项目与领域分布、兴趣主题，以及与 GitHub 提交的产出关联。
  Trigger when the user says: "生成我的 AI 档案" / "做一份 AI-native README" /
  "分析我的 Claude / Codex / Kiro / Trae / Antigravity / Cursor 使用情况" /
  "build my AI usage profile" / "build my monthly AI coding report".
  全程本地、只读、默认匿名、不上传任何数据。
license: MIT
---

# Readme.skill — AI-Native 开发者档案生成器

You (the AI agent invoking this skill) will read local Claude Code + Codex CLI
+ Kiro (AWS) + Trae (ByteDance) + Gemini Antigravity (Google) + Cursor data,
compute a fixed set of dimensions, and render both a Markdown profile and a
validated SVG poster under `./output/` in the user's requested language.
**You do all of the work** — read the files with `Read`, query sqlite via
`Bash`, synthesize the prose yourself, then write and validate the SVG.

## Step 1 — 准备

```bash
cd <repo-with-this-skill>
mkdir -p output
DATE=$(date +%Y%m%d)
```

Report a problem