Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By bobmaertz
General-purpose Claude Code plugin: orchestrator-worker pipeline (/spec → /plan → /implement), parallel review agents (peer-review, security-review), test generation (/gen-tests), targeted refactoring (/refactor), research, repository exploration, documentation, git commit generation, and git worktree management.
npx claudepluginhub bobmaertz/prompt-library --plugin generalGenerate a context-aware commit message that matches this project's existing commit style. Reads git history and staged diff to produce a ready-to-run commit command.
Document a recently solved problem to compound team knowledge. Captures root cause, solution, and prevention strategies in docs/solutions/ while context is fresh.
Look up documentation for any topic or generate missing documentation. Searches local project docs (README, docs/, docstrings, JSDoc) first, then fetches external official documentation. Also generates documentation for undocumented code — use "generate: <target>" syntax.
Map the current repository's architecture, conventions, entry points, and patterns. Runs as a background sub-agent and returns a structured codebase report. Useful before implementing a feature in an unfamiliar codebase or when onboarding to a new project.
Generate unit tests, integration tests, and regression tests for existing or new code. Detects the project's test framework and conventions automatically. Runs as an isolated background agent. Invoke after implementation to ensure new code has coverage.
Reviews or guides implementation of a 12-factor cloud-native application. Audits an existing codebase for 12-factor compliance, or provides concrete implementation guidance when building a new service. References patterns from well-structured microservices like gomods/athens.
Decomposes a feature request or problem into a structured implementation plan with clear task boundaries, file ownership, and acceptance criteria. Writes a MULTI_AGENT_PLAN.md that downstream implementation workers can consume without ambiguity. Read the codebase first, plan second.
Documentation lookup and synthesis skill. Searches local project documentation (README files, docs/, docstrings, JSDoc, type stubs), fetches official external documentation, and synthesizes answers. Also used for generating missing documentation. Loads project best-practices context automatically.
Analyzes staged changes and recent commit history to generate a well-formatted commit message that matches the project's existing commit style. Produces the commit command ready to run.
Manage git worktrees for AI agent workflows. Use when creating, listing, removing, or pruning worktrees, especially for ticket-based development where the agent needs to create isolated working directories for feature branches. Supports creating worktrees in .worktrees/ subdirectory, automatic branch creation from base branch (main), and cleanup of stale worktrees.
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Takazudo's personal Claude Code resources: skills, commands, agents, hooks, and scripts.
5 methods to retrieve code context: DeepWiki, Context7, Exa, git clone, and web search+fetch
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
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
Backend development tooling for Claude Code: LSP server configuration and linter templates for TypeScript, Python, Go, Rust, and Shell.
Long-running application development harness for Claude Code: initializer agent to decompose goals into a tracked feature list, incremental coding agent to make per-session progress, and an evaluator agent to assess quality through a generator-evaluator loop.
A collection of Claude Code plugins for everyday development workflows. Each plugin is self-contained with commands, skills, and hooks that extend Claude Code for a specific domain.
| Plugin | Description |
|---|---|
general | Research, repo exploration, docs, code review, security review, and git workflow |
backend | LSP server configuration and linter templates |
First add this repository as a Claude Code marketplace, then install the plugins you want:
# Add this repo as a marketplace (one-time)
/plugin marketplace add https://github.com/bobmaertz/prompt-library
# Install plugins
claude plugin install general
claude plugin install backend
# Or install to project scope to share with your team
claude plugin install general --scope project
Uninstall with claude plugin uninstall <name>.
If you want edits to sync back to the repository automatically, clone it and use the install script instead. This symlinks each plugin directory into the Claude Code plugin cache rather than copying it.
git clone https://github.com/bobmaertz/prompt-library.git ~/.claude-plugins
cd ~/.claude-plugins
./scripts/install.sh
| What | Where |
|---|---|
| Plugin symlinks | ~/.claude/plugins/cache/<plugin-name> |
| Settings entry | ~/.claude/settings.json → enabledPlugins |
# Uninstall
./scripts/uninstall.sh
# Override the default ~/.claude path
CLAUDE_DIR=/custom/path ./scripts/install.sh
claude --plugin-dir ./plugins/general
Every plugin follows this layout:
<plugin-name>/
├── .claude-plugin/
│ └── plugin.json # Required: name, version, description, author
├── commands/ # Slash commands (/command-name.md)
├── skills/ # Invokable skills
│ └── <skill-name>/
│ └── SKILL.md
├── hooks/
│ └── hooks.json # Event hooks (PreToolUse, TaskCompleted, etc.)
└── README.md
plugins/<plugin-name>/.claude-plugin/plugin.json:
{
"name": "my-plugin",
"description": "What this plugin does",
"version": "1.0.0",
"author": { "name": "your-name" },
"license": "MIT"
}
commands/, skills/, and/or hooks/ as neededREADME.md describing commands and usage./scripts/install.sh to pick up the new pluginBecause the cache entries are symlinks, edits made through Claude Code write back to this repository. To sync across machines:
# Push from one machine
git add -A && git commit -m "Update plugins" && git push
# Pull on another machine
git pull
./scripts/install.sh # only needed when adding new plugins
MIT