Mxkey
macOS dev-secrets workflow via mxkey (a Keychain wrapper). Use whenever the user handles an API key, token, password, or 2FA backup / recovery code — setting up a new API, running a command that needs a key, editing a .env file, spotting a hardcoded secret in code, or storing single-use recovery codes. Secrets never enter chat, shell history, or plaintext files. macOS only.
Install
npx skills add maxmealing/mxkey --skill mxkeygit clone --depth 1 https://github.com/maxmealing/mxkey.git /tmp/mxkey
mkdir -p ~/.claude/skills
cp -r /tmp/mxkey/. ~/.claude/skills/mxkeyPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# mxkey — macOS dev-secrets workflow Store API keys and tokens in the macOS Keychain so you and agents like Claude, Cursor, or Codex can load them on demand — never pasted into chat, shell history, `.env` files, or source code. **What this skill does:** wraps the macOS `security` CLI with an `mxkey` command for setting, reading, and injecting secrets into dev commands, plus a `backup` subcommand for single-use 2FA recovery codes. Secrets are named `<category>.<name>` (categories by convention: `api`, `db`, `oauth`, `project`, `infra`, `backup`). Encrypted at rest by the OS Keychain, unlocked by your login password. **After this skill**, you can run `mxkey run -- <cmd>` to inject secrets into any process, edit `.env` files safely with placeholder refs, and stop worrying about hardcoded keys. macOS only. ## Why Keychain Every Mac already ships with a secrets vault: the login Keychain. It's encrypted at rest, unlocked by your login password, access-controlled per app, and battle-tested for decades. `mxkey` reuses it — adding a naming convention for dev secrets and a safe way to inject them into commands — rather than inventing a new storage layer. ## How it works The core workflow is two commands: - `mxkey set <name> <ENV_VAR>` — prompts for the value at a hidden terminal read, stores it in Keychain. - `mxkey run <name>... -- <cmd>` — reads the value back and launches `<cmd>` with the env var set. The secret lives in that process's memory only.
Details
- Skill name
mxkey- Repository
- maxmealing/mxkey
- License
- MIT
- Repo updated
- 4 June 2026
FAQ
What does the Mxkey skill do?
macOS dev-secrets workflow via mxkey (a Keychain wrapper). Use whenever the user handles an API key, token, password, or 2FA backup / recovery code — setting up a new API, running a command that needs a key, editing a .env file, spotting a hardcoded secret in code, or storing single-use recovery codes. Secrets never enter chat, shell history, or plaintext files. macOS only.
How do I install the Mxkey skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add maxmealing/mxkey --skill mxkey. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Mxkey popular?
It lives in maxmealing/mxkey, which has 6 GitHub stars and 0 forks.
Related skills
Power Coding
6APareek89/power-coding
Mindful-coding OS for any LLM coding agent — faster, quality, scalable output. One invoke configures seven layers (0–6): (0) BRIEF — optional one-page PRD.md (skipped if design.MD/README already covers it, or on request), plus git init, gitignore, and a day-one security baseline; (1) HARNESSING — Handoff.MD (user-picked sections, one magic phrase chains sessions, updated on concrete events — before every commit / end of every phase — with a line/item compaction cap and a last-synced sha for concurrent-session reconcile) + auto Learning.MD for bugs and flow changes; (2) LOOP ENGINEERING — Loop.
Leetcode Helper
6Zephyrex21/claude-leetcode-helper
Expert LeetCode problem solver for optimized C++ coding interview solutions. Use when: the user pastes a LeetCode problem, asks for an optimized algorithm, wants C++ LeetCode code, needs a dry run, asks for line-by-line explanation, wants a hint before the solution, wants brute force to optimized progression, wants pattern recognition, C++ pitfall warnings, interview tips, or wants help understanding data structures and algorithms for coding interviews.
Shipwright
6saadjangda/shipwright
The only skill you need to build and ship world-class software — from idea to production. Covers the COMPLETE lifecycle: architecture design, domain modeling, service boundaries, data architecture, implementation with TDD, distinctive frontend design (anti-AI-slop), exhaustive QA across all layers, security hardening, scalability and load balancing, reliability engineering, performance optimization, accessibility (WCAG 2.1 AA), CI/CD, observability, and operational excellence. Applies Airbnb/Stripe/Meta-level engineering standards. Use this skill whenever: building something new ('let's build
Khaow Friend Roleplay
513D4C/kewmajiroon8888
Roleplay as a friend named "khaow" — a quirky programmer who solves problems in weird, roundabout ways but is extremely confident in his own ideas. Use this skill whenever the user mentions their friend khaow, asks to roleplay as khaow, wants to talk to khaow, or asks "how would khaow do this?" / "what would khaow build?" — even if the word "roleplay" isn't used directly.
Skillize Any Lib
6pointerliu/skillize-any-libs
Generate SKILL.md for any library by analyzing its source and real-world usage. Supports Rust, Python, JavaScript, Go, C/C++, and more.
Icode
5ayukyo/icode-skill
ICODE 端到端编码工作流，适配 Claude Code、Codex、CodeBuddy、WorkBuddy。用户调用 /icode、$icode，或说“使用 ICODE”“用 icode 帮我”“让 ICODE”“Use ICODE”完成开发、日志分析、设计/代码审查、证据验证、独立复评、文档/Word/PPT、学习、工单管理等任务时使用；也用于已绑定 ICODE 工单的续接。Use when users explicitly request ICODE for an AI coding workflow, ticket-based development, code review, log analysis, documentation, or evidence verification; also use to resume a bound ICODE ticket. 支持自然语言目标与限制，不要求背命令；能力咨询只解释不执行。保留全部 /icode 子命令，复用既有步骤与安全门禁，不接管未指定 ICODE 的普通请求。
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.