Plugins

Generates iterable checklist PROMPT files for Ralph Loop from plan files or current context, and provides the /ralph-loop execution command.

from app-vitals/marketplace

from seekayel/agent-skills

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

Interactive self-referential AI loops for iterative development with full cross-platform support (Windows, WSL, macOS, Linux, Git Bash, Cygwin)

from chrismcgraw60/parallel_plot

Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

from king8fisher/claude-code-marketplace

from tuannvm/plugins

from bennoloeffler/maude-claude-vunds-plugins

from rami-code-review/claude-code-marketplace

Raphael — aggressive reviewer, finds the hard problems.

失敗を感染記録→抗体→発火時だけ注入へ変換し、決定的な hook で再発を防止する

Communication and collaboration skills for Claude Code

Ratchet turns coding sessions into self-evolving wisdom for agents and developers. It automatically generates Skills and Strategies from past sessions, curates the right workflows and Cheatmaps from the Wisdom DB based on user intent, and enhances existing Skills through evaluation and ROI analysis. BYOK model with local extraction pipeline.

Audits AI-built and vibe-coded apps from product, systems, frontend, user, and venture perspectives, then optionally records authorized fixes and independent retests in a durable audit ledger.

Domain-neutral Claude Code foundation: 15 specialist agents, 46 skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), Problems & Resolutions view, declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer), and Claude orchestrator escape hatch (/claude-orchestrate). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /reset-plugin-cache.

Plugin from lgtm-hq/ai-skills

Channels Raymond Hettinger, catching the Java in your Python.

from kokuyouwind/claude-plugins

RC workflow skills and slash commands

Configure RevenueCat projects, apps, products, entitlements, and offerings directly from Claude Code. Manage your in-app purchase backend without leaving your development workflow.

Research Consultancy medical research skills organized as expanded skill directories.

Focused RCC-family skills for RCC itself, robots, holotree environments, work items, Action Server packages, and CI maintenance.

Dual-compatible campaign and knowledge management for Claude Code and Codex. Initializes one canonical project profile, host-specific manager overlays, evidence-gated truth, retrospective chronicles, native subagent adapters, and optional external drafter evaluation.

Open-source GTM playbook (core)

Experiments and one-offs

from eliaslecomte/claude-plugin

from minukHwang/claude-plugins

React best practices: lean hooks, component patterns, and performance optimization.