HugoLopes45

Aiclair — AI skill for Claude Code

AI community

Community framework for AI assistant hooks — write once, run across Claude Code, Cursor, Codex and more.

How to install Aiclair

This entry records only its repository, not the path inside it, so there is no exact command to give. Open HugoLopes45/aiclair and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Aiclair does

Community framework for AI assistant hooks — write once, run across Claude Code, Cursor, Codex and more.

Alternatives in AI

Embeddedskills — An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and oth 593 ★
HarnessKit — More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across e 416 ★
Registry Broker Skills — AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols 410 ★

README

aiclair

![CI](https://github.com/HugoLopes45/aiclair/actions/workflows/validate.yml/badge.svg) ![Python](https://img.shields.io/badge/python-3.8%2B-blue) ![License](https://img.shields.io/badge/license-MIT%20%2B%20Commons%20Clause-orange) ![Version](https://img.shields.io/badge/version-1.1.0-blue)

Safety guardrails for Claude Code — stop accidental data loss, secret leaks, and dangerous commands before they execute.

Why

Claude Code is powerful. That's the problem.

It will run rm -rf if you ask it to clean up. Sometimes on the wrong directory.
It will write your AWS key into a config file, commit it, and push.
It will ask you twelve questions about a two-word prompt.

aiclair adds three hooks that run silently on every prompt and tool call. They block the dangerous stuff, catch secrets before they land in files, and ask clarifying questions only when a prompt is genuinely vague.

No pip install. No build step. Pure Python stdlib.

![aiclair demo](demo/aiclair-demo.gif)

Install

curl -fsSL https://raw.githubusercontent.com/HugoLopes45/aiclair/main/install.sh | bash

Pick which hooks to install interactively, or use flags:

# Install everything
curl -fsSL https://raw.githubusercontent.com/HugoLopes45/aiclair/main/install.sh | bash -s -- --all

# Install specific hooks
curl -fsSL https://raw.githubusercontent.com/HugoLopes45/aiclair/main/install.sh | bash -s -- --hooks "danger-detector secret-guard"

**Uninstall:**

bash ~/.claude/plugins/aiclair/uninstall.sh

Hooks

Hook	Fires on	What it does
prompt-improver	Every prompt	Asks 1–6 targeted questions when a prompt is vague. Clear prompts pass through immediately.
danger-detector	Bash commands	Blocks destructive and malicious commands before they run.
secret-guard	File writes, Bash commands, Bash output	Blocks secrets