Browse plugins

Hookify creates custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions, using simple markdown configuration files with regex pattern matching. It supports four hook events (PreToolUse, PostToolUse, UserPromptSubmit, Stop) and provides commands to generate rules, list configurations, and interactively manage hook behavior without requiring restarts.

Pro Workflow is a complete AI coding system with self-correcting memory, persistent SQLite-indexed research wikis, and an auto-research loop that learns from corrections across sessions. It provides 41 skills, 8 agents, 23 commands, and intelligent hooks that inject relevant knowledge and enforce quality gates without requiring API keys or external services.

Claude-mem is a memory compression system that persists context across Claude Code sessions using 18 skills, 6 hooks, and an MCP server integration. It intercepts session and tool-use events to manage and compress conversation history, enabling continuity between separate coding sessions.

Ars Contexta generates a personalized knowledge management system through conversational setup, creating markdown vaults with wiki links, processing pipelines, automation hooks, and domain-native documentation—all derived from how you describe your thinking and work. The plugin provides 10 skills for extracting insights, finding connections, and maintaining your vault, plus a 6-phase pipeline that mirrors Cornell note-taking with a meta-cognitive layer for continuous system evolution.

Ponytail injects a minimalist decision ladder into Claude Code sessions, forcing the agent to question whether code is needed at all before building solutions. It works by hooking session start and prompt submission to apply YAGNI principles, prefer stdlib, and avoid unrequested abstractions.

This plugin provides five core skills for ecosystem navigation, skill creation, research pattern analysis, session reflection, and plugin development, with a UserPromptSubmit hook that forces skill evaluation on user input. It integrates via a shell-based activation script to enable automated skill assessment workflows.

memsearch automatically captures and indexes your Claude Code session history as semantic memories, allowing Claude to recall past work across sessions without manual saving. It runs entirely locally using ONNX embeddings and shell hooks, integrating with Claude Code's native skill and hook system.

Hivemind provides cloud-backed persistent memory using Deeplake, allowing you to read, write, and share memory across Claude Code sessions and agents through hooks that capture session events and tool usage. The plugin integrates with your workflow via Node.js commands and skills, enabling collaborative memory management across multiple Claude instances.

This skill provides expert Git workflow patterns including branching strategies (Git Flow, GitHub Flow, trunk-based), commit conventions, pull request processes, and CI/CD integration through a portable Agent Skill. It includes a `/pr-finish` command to automate pull request merge workflows and pre-commit hooks for validation.

This agent skill automatically detects missing CLI tools (77+ supported) and installs them via optimal package managers, while also providing proactive environment auditing and batch tool updates. It reacts to "command not found" errors and user requests to maintain development environments across multiple platforms.

Engram is a learning system that turns your AI assistant into an evidence-based tutor using first-principles Socratic questioning, blind-graded recall verification, and FSRS-based spaced repetition scheduling to ensure you retain knowledge. The plugin stores your learning state locally as plain JSON, works across six agentic platforms, and requires only Python 3 (no external APIs or accounts).

The `/retro` command analyzes the current Claude Code session transcript to detect friction (tool errors, repeated mistakes, convention violations) and routes each finding to one of six destinations—user memory, project rules, skill PRs, checkpoints, or harness artifacts—with explicit per-proposal approval before any writes. It replaces continuous background hooks with a single efficient LLM pass that returns ≤10 actionable proposals grouped by destination.

This plugin provides idiomatic development assistance across eight major programming languages and frameworks: C#/.NET, Go, Java/Kotlin, Python, Rust, TypeScript, shell, and web technologies. It bundles one AI agent with eight skills to help developers follow language-specific best practices and conventions.

This skill automates migration of code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5, updating model strings, beta headers, and configuration details. It helps ensure compatibility with the latest model version and can be used iteratively to refine prompts after migration.

This toolkit provides seven specialized skills and a guided workflow command for building Claude Code plugins, covering hooks, MCP integration, plugin structure, settings, commands, agents, and skills. The /plugin-dev:create-plugin command guides users through an 8-phase process from discovery to documentation, with best practices, examples, and validation utilities included.

This TYPO3 upgrade effort model provides per-version risk multipliers, breaking-change baselines, and a 7-phase assessment workflow to estimate the effort required for TYPO3 LTS major version upgrades. It supplies technical risk factors and compatibility matrices but requires pairing with your team's historical project data to produce calibrated effort estimates.

This plugin provides three independent agentic skills for Matrix/Synapse: matrix-communication enables sending, reading, editing, and reacting to chat messages with full E2EE support; matrix-administration operates Synapse homeserver functions; and matrix-announcement helps compose structured announcements. All skills work with any Matrix/Synapse homeserver and require no external API keys or paid services.

This plugin provides 12 product strategy skills and 5 commands covering frameworks essential for product managers—including Business Model Canvas, Lean Canvas, SWOT, PESTLE, Porter's Five Forces, Ansoff Matrix, and value proposition design. It enables PMs to analyze markets, design pricing strategies, and develop comprehensive product strategies without requiring external APIs or services.

This skill enforces natural German technical register for Jira comments, internal documentation, and team messages by catching anglicisms and false cognates while preserving accepted Denglisch loanwords. It applies domain-specific lexicons and register conventions for German-language technical artifacts.

This plugin reformats Claude Code output for ADHD-friendly reading by leading with actionable next steps, numbering tasks, suppressing tangents, and making progress visible. It uses 10 specific rules—like matter-of-fact tone, capped lists, and concrete time estimates—to eliminate preamble and bury-the-answer patterns.

This Agent Skill automates DDEV environment setup for TYPO3 extension development, automatically detecting extension metadata and generating configuration for testing across multiple TYPO3 versions (11.5, 12.4, 13.4, 14.3 LTS). It creates pre-configured Docker environments with TYPO3 installations, custom commands, and a branded landing page dashboard for quick multi-version testing.

This skill provides GitLab CLI (glab) expertise to help manage merge requests, issues, CI/CD pipelines, and repositories from the command line. It requires the GitLab CLI tool to be pre-installed and authenticated locally.

The pm-toolkit provides four core skills for product managers: resume review and tailoring against PM best practices, NDA drafting with jurisdiction-specific clauses, privacy policy generation covering compliance requirements, and grammar/flow checking with targeted fixes. It runs entirely locally without external API dependencies or third-party services.

Theme Factory provides a single skill that applies professional, pre-configured styling to artifacts like slides, documents, reports, and HTML landing pages. It includes 10 preset themes with coordinated colors and fonts, eliminating the need for manual design work.

Harness is a Claude Code plugin that transforms a domain description into a coordinated agent team architecture and supporting skills by applying one of six pre-defined team patterns: Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, or Hierarchical Delegation. It automatically generates agent definitions and skills tailored to your domain through a structured six-phase workflow spanning domain analysis, architecture design, agent/skill generation, integration, and validation.

This plugin provides 13 product discovery skills for PMs to run ideation, experiment design, assumption testing, feature prioritization, and customer interview workflows. It includes commands to brainstorm ideas, run full discovery cycles, manage metrics dashboards, and synthesize customer interviews without requiring any external APIs or tools.

This skill teaches Claude Code agents when and how to use structured data tools (jq, yq, dasel, qsv, mlr) instead of fragile text processing for JSON, YAML, TOML, XML, CSV, and JSONL formats. It includes comprehensive cookbooks and patterns to avoid common antipatterns like grep/sed/awk on structured data.

This plugin analyzes your Claude Code chat history to identify coding patterns, development gaps, and skill areas, then generates a personalized growth report with curated learning resources from HackerNews. It works entirely with local data and requires no external API keys or third-party services.

This plugin provides Git worktree management through a single skill that creates, lists, and deletes worktrees for working on multiple branches simultaneously. It automatically activates when you mention worktree tasks and organizes worktrees in a sibling directory pattern using the naming convention `../<project>-<branch>`.

spec-flow provides a lightweight spec loop that guides you through planning a slice, executing a task, and then checkpointing progress or closing out work. It consists of two agents and one skill to streamline iterative development cycles.

This skill breaks down complex feature implementations into structured phases—Setup, Research, Finalize, Tasks, Implement, Review—with clear task dependencies and success criteria tracked in `.plans/` directories. It guides users through iterative approach selection and integrates with TodoWrite for progress tracking across phased implementation workflows.

A plugin providing Claude Code workflow patterns focused on prompting strategies, CLAUDE.md documentation maintenance, and multi-agent orchestration techniques. It offers 4 reusable skills to streamline agent coordination and collaborative coding workflows.

This plugin provides 3 agents and 7 skills for research, documentation lookup, utility routing, and skill authoring, along with instruction review and agent configuration auditing capabilities. It enables developers to audit reasoning processes and review agent configurations without requiring external API keys or services.

Handbook Reflect provides three skills for analyzing Claude Code sessions: a reflection dashboard that identifies wrong turns, a summary tool that generates an interactive HTML recap, and a quest tree visualizer that maps session flow with retries and reversals. These tools help developers turn development sessions into reusable artifacts and insights.

This plugin equips product managers with structured frameworks for launching products, including GTM strategy, growth loops, competitive positioning, and customer segmentation. It provides six skills and three commands covering everything from identifying beachhead segments and ideal customer profiles to designing growth mechanisms and sales-ready battlecards.

This plugin provides 2 skills for setting up and optimizing development environments, including git worktrees management and terminal configuration. It requires no external APIs or tools and runs entirely within Claude's sandboxed environment.