Claude Code Infrastructure Showcase skill
Ready infrastructure for Claude Code: skill auto-activation via hooks, a skill set, agents, slash commands and a wizard that installs it into your project
- 10,056 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Hooks run automatically, execute scripts and read project files and session history
- In the optional smart classification mode prompt text is sent to an external model
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/claude-code-infrastructure-showcaseDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Hooks run automatically, execute scripts and read project files and session history
- In the optional smart classification mode prompt text is sent to an external model
This is third-party code. Review the repository files before installing.
What it does
This is a portable set of Claude Code infrastructure that solves the problem of skills not activating automatically. Hooks on prompt submit and before file edits suggest and, when needed, require the right skills by keywords, intent patterns, file paths and file content, and the skill-rules.json config controls which skills apply. The bundle includes example frontend and backend skills, a skill for building other skills, error tracking, a set of specialized agents, slash commands and a dev-docs system that survives context resets. By default matching runs offline via regular expressions with no keys or network, while an optional smart classification mode can use external models. Installation is handled by the setup.ts wizard, which copies the .claude folder into your project, installs hook dependencies and runs eight checks.
Who it is for. For developers who run a project in Claude Code and want skills and rules to engage on their own.
Good fit when
- Skills in Claude Code do not trigger on time and you keep loading them by hand
- You want hooks, agents and slash commands as a ready base for your project
- You need an example of modular skills with progressive disclosure and the 500-line rule
Not a fit when
- You want a finished application: this is reference infrastructure, not a running product
- You do not work in Claude Code or a compatible client with hooks
Example request
Install this infrastructure into my project and show the verification resultsLimitations
This is a reference library to copy into your own project, not a standalone application. The hooks are bash scripts and run on macOS, Linux or WSL2, need Node.js 18 or newer, and the optional Stop hooks also need jq. Hooks run automatically and read project files and session history, and in smart classification mode they send prompt text to an external model, so that mode is enabled separately and needs a key. By default everything runs offline on regular expressions with no keys.
How to disable. Remove the .claude folder from the project or delete the hook entries from .claude/settings.json. Smart classification can be turned off by setting the mode in skill-rules.json back to disabled.
FAQ
Do I need an API key?
No. By default skills are matched offline via regular expressions, with no keys or network. Smart classification with an external model is a separate optional mode.
Is this a working application?
No. It is a reference infrastructure library: you copy what you need into your project. The setup.ts wizard moves the .claude folder and configures the hooks.
Discussion
No questions or reviews yet.
Related
SkillsA set of Claude Code utilities: background skills, expert agents, slash commands and prompt templates for development
A ready-made Claude Code setup: agents, slash commands, skills, safety hooks, rules and MCP connections in one install
Claude Code Blueprint: 12 agents, 19 skills, 16 hooks and 6 CLAUDE.md rules, copy what you need or install a preset
A CLI that scaffolds Claude skills, validates their size and structure, packages them for Claude.ai and adds activation hooks
One-command Claude Code environment installer: a wizard sets up agents, rules, commands, skills and hooks in three profiles
A starter kit for Claude Code: a CLAUDE.md memory-bank template with ready hooks, subagents and skills you copy into your project
README in short
The README presents a collection of Claude Code infrastructure built over six months of work on a TypeScript project, and stresses that it is a reference library, not an application. Its core purpose is skill auto-activation via hooks, modular skills with progressive disclosure, specialized agents and a dev-docs system. You can install it with the npx tsx setup.ts wizard, manually by copying the .claude folder, or by the agent following the included guide. By default matching runs offline via regular expressions, and smart classification with an external model is enabled separately. It ships an eight-point verification script and a NeoVim editor config, under the MIT license.
README badge
Original SKILL.md
--- name: skill-developer description: Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule. --- # Skill Developer Guide ## Purpose Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern. ## When to Use This Skill Automatically activates when you mention: - Creating or adding skills - Modifying skill triggers or rules - Understanding how skill activation works - Debugging skill activation issues - Working with skill-rules.json - Hook system mechanics - Claude Code best practices - Progressive disclosure - YAML frontmatter - 500-line rule