composio-community/awesome-codex-skills
Plugin Claude Code
A curated marketplace of practical Claude Skills for enhancing productivity across Claude.ai, Claude Code, and the Claude API.
125 tagged codex-cli, measured the same way as everything else here.
Browse within: claude-code-plugin 25gemini-cli 18skills 15agents 14cursor 12claude-plugin 7codex-plugin 7claude-agents 6cli 6mcp-server 6agent-skill 5ai-coding 5
composio-community/awesome-codex-skills
Plugin Claude Code
A curated marketplace of practical Claude Skills for enhancing productivity across Claude.ai, Claude Code, and the Claude API.
Plugin Claude Code
Bundles 8 skills, 20 commands, 10 agents, 9 hooks · 1,412 tokens together
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Control the Collaborator spatial canvas from your terminal. Open, arrange, and manage tiles.
Plugin Claude Code
Bundles 2 skills, 8 hooks · 138 tokens together
Keep Claude Code tasks bounded and reduce defensive wording with local-first guardrails and two Skills.
Plugin Claude Code
Bundles 4 skills, 7 commands, 1 hook · 397 tokens together
Repository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.
ShadowAqueduct/watermark-remover
Plugin Claude Code
Bundles 2 skills, 1 hook · 256 tokens together
Local hygiene for owned content: strip hidden Unicode (Layer A), weaken sampling watermarks via rewrite (Layer B), and drop C2PA/EXIF/XMP provenance from images, documents, and media. Bundles the HTTP-backed remove-ai-marks skill and the self-contained clean-user-facing-text skill.
Plugin Claude Code
Bundles 6 skills, 18 commands · 492 tokens together
LLM-powered knowledge base from Claude Code and Codex CLI sessions. Follows Karpathy's LLM Wiki pattern.
Plugin Claude Code
Parallel task orchestration for AI coding agents - dispatch work to Codex or Claude Code workers in isolated git workspaces.
niaka3dayo/agent-skills-vrc-udon
Plugin Claude Code
Bundles 2 skills · 431 tokens together
VRChat UdonSharp skills, rules, and validation hooks for correct code generation.
u-ichi/reviewable-html-workbench
Plugin Claude Code
Bundles 3 skills, 1 hook · 780 tokens together
Generate reviewable HTML documents, serve previews, collect comments, and feed review outcomes back into agent workflows.
Plugin Claude Code
Bundles 15 skills · 466 tokens together
Complete GRACE methodology: semantic markup, knowledge graphs, module contracts, testing, and log-driven verification for AI-driven engineering.
Plugin Claude Code
Bundles 39 skills · 3,051 tokens together
26 domain skills + 5 verification tools for security-first full-stack engineering. Covers security, architecture, DevOps, AI, mobile, office docs, frontend design, and multi-agent coordination.
Plugin Claude Code
Bundles 1 skill · 250 tokens together
Generate an AI-Native developer profile or monthly/time-window report from local Claude Code + Codex CLI + Kiro (AWS) + Trae (ByteDance) + Gemini Antigravity (Google) + Cursor composer metadata, GitHub contributions, and git log. Local-only, read-only, anonymized by default.
CodeAlive-AI/ai-driven-development
Plugin Claude Code
Bundles 22 skills, 1 agent · 2,651 tokens together
An umbrella collection of 23 skills + 1 hook for AI-driven development: agent self-configuration (MCP / hooks / settings / skills / plugins / cross-agent repository readiness / safe CLI installation), engineering practices (maintainable complexity, prompt engineering, FPF problem solving, bug-fix protocol, planning…
Plugin Claude Code
Bundles 23 skills, 9 agents, 8 hooks · 1,965 tokens together
Modular Agentic Planner (MAP) - Cognitive architecture for AI agents with 11 specialized agents and professional code review integration.
Plugin Claude Code
Bundles 29 skills, 1 command · 5,238 tokens together
Agent skills for Neo4j — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, Aura provisioning, and more.
Plugin Claude Code
Bundles 11 skills, 1 agent · 693 tokens together
Autonomous AI coding loops — orchestrate coding agents to build software from specs automatically.
vbcherepanov/total-agent-memory
Plugin Claude Code
Bundles 6 skills, 7 hooks, 2 MCP servers · 454 tokens together
Persistent local memory for Claude Code — temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. Installs the MCP server, the memory-protocol skill and the capture hooks in one step.
Plugin Claude Code
Bundles 17 commands · 279 tokens together
Skill synchronization and management for Claude Code, Codex, GitHub Copilot, and Cursor. Provides 36 core MCP tools for validation, sync, intelligence, research, and tracing.
Plugin Claude Code
Bundles 1 skill, 7 commands · 44 tokens together
Team context, session recording, and AI coworker coordination for collaborative development.
Plugin Claude Code
Bundles 1 skill · 92 tokens together
Hand token-heavy mechanical work (batch edits, scaffolding, refactors, test generation, plotting scripts) from Claude to Codex CLI.
Plugin Claude Code
Bundles 24 skills, 34 agents · 1,721 tokens together
Agentic engineering done right — 57 structured workflows, 17 specialist agent personas, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.
Plugin Claude Code
Bundles 12 skills, 1 hook · 1,462 tokens together
A caring skill pack for vibe coders. Encodes engineering discipline — refactor verification, minimal security audit, repo rot detection, AI-friendly docs, CI/CD basics, secrets lifecycle, project conventions, repo bloat diagnosis, and design-system unification — as a set of portable agent skills, plus two…
Plugin Claude Code
Bundles 1 skill, 1 command · 181 tokens together
Native diff review window (Monaco + Glimpse) for AI coding agents. Browse changes since the merge-base with your base branch (or last commit / uncommitted), leave inline + file-level + overall comments on the slop, and have the agent address each item.