By tabers77
23 reusable skills, 2 agents, and smart hooks for architecture mapping, code review, safe refactoring, learning, and quality gates — works in any project.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Persistent learning coach for all learning skills. Tracks progress, weak areas, and mastery across sessions. Use when any learning skill runs with context fork.
Implement inference endpoints consistently. Use when adding new API endpoints, building REST APIs, or implementing inference routes with consistent patterns for models, errors, logging, and config.
Build a mental model before touching code. Use when joining large repos, legacy systems, before refactoring, or when you need to understand how a codebase is structured.
Find bugs, anti-patterns, and refactoring opportunities in existing code. Use when you want a targeted scan of a specific module, file, or area — not a full repo audit.
Update docs, check test gaps, and commit. Git-driven — detects what changed, discovers and updates affected documentation, analyzes test coverage gaps, then commits cleanly. Use when you're ready to commit, wrapping up a session, or before pushing.
Algorithm and coding interview prep for data scientists. Covers DSA, SQL challenges, pandas/numpy problems, statistics, and ML implementation. Claude presents problems, you solve, Claude corrects. Use when you want to practice algorithms, prep for interviews, or drill coding problems.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A reusable Claude Code plugin of skills, agents, hooks, and rules that connects to any project. No file copying needed.
Setting up Claude Code effectively requires more than just installing it. You need:
This library provides all of these, extracted from real-world usage patterns documented in the playbook.
From any project, pass the plugin path directly:
claude --plugin-dir /path/to/claude_experiments
Skills are namespaced:
/claude-library:architecture-arch # Build mental model of codebase
/claude-library:meta-project-setup # Analyze project & get recommendations
--plugin-dir needed)Instead of typing the full --plugin-dir path every time, create a shell alias that does it for you. Follow the guide for your OS below.
Why not
settings.json? Claude Code'sextraKnownMarketplacesconfig is for marketplace directories (folders containing multiple plugins in subdirectories). A single plugin repo like this one doesn't fit that format. The--plugin-dirflag is the intended way to load a single plugin, and a shell alias is the cleanest way to avoid retyping it.
This is what most VS Code users on Windows will use.
Step 1: Check if you already have a PowerShell profile
Open a terminal in VS Code (or any PowerShell window) and run:
Test-Path $PROFILE
True → you already have a profile, skip to Step 3.False → continue to Step 2.Step 2: Create the profile file
New-Item -Path $PROFILE -Type File -Force
Step 3: Open the profile in Notepad
notepad $PROFILE
Step 4: Add the alias function
In Notepad, add this line (update the path to match where you cloned this repo):
function claude-lib { claude --plugin-dir "C:\Users\YOUR_USERNAME\path\to\claude_experiments" $args }
Save the file and close Notepad.
Step 5: Reload the profile
Back in your terminal, run:
. $PROFILE
If you get a script execution error, run this first, then retry:
Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned
Step 6: Verify it works
Navigate to any project and run:
claude-lib
You should see Claude Code start with all plugin skills available. Done!
Step 1: Open your shell config
# For Zsh (default on macOS)
nano ~/.zshrc
# For Bash (default on most Linux)
nano ~/.bashrc
Step 2: Add the alias
Add this line at the end of the file (update the path to match where you cloned this repo):
alias claude-lib='claude --plugin-dir /path/to/claude_experiments'
Save and exit (Ctrl+O, Enter, Ctrl+X in nano).
Step 3: Reload
source ~/.zshrc # or source ~/.bashrc
Step 4: Verify it works
Navigate to any project and run:
claude-lib
claude-lib doesclaude-lib is identical to claude — same features, same flags, same behavior. The only difference is it automatically adds --plugin-dir for you.
| You type | What actually runs |
|---|---|
claude-lib | claude --plugin-dir "/path/to/claude_experiments" |
claude-lib --model sonnet | claude --plugin-dir "/path/to/claude_experiments" --model sonnet |
claude-lib --resume | claude --plugin-dir "/path/to/claude_experiments" --resume |
# Set up local symlinks so skills work without --plugin-dir
bash setup-local.sh
# Then use skills directly
/architecture-arch map the codebase
Skills are organized by development phase — find the phase you're in, pick the skill you need.
Essential = don't skip this. If needed = reach for it when the situation fits.
Joining a project, assessing health, understanding what exists.
npx claudepluginhub tabers77/claude_experimentsAnalyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use
Meta-tools for Claude Code configuration and customization
Meta-skills infrastructure for Claude Code plugin ecosystem - skill authoring, hook development, modular design patterns, and evaluation frameworks
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.