codex-image
claudeGenerate and edit images from Claude Code by dispatching to Codex CLI's built-in imagegen skill.
3 skills
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Generate and edit images from Claude Code by dispatching to Codex CLI's built-in imagegen skill.
3 skills
Find, read, install and update public Agent Skills from a catalog of about 75,000: a skill, MCP tools and a /skills-atlas command.
1 skill · 1 command · 1 MCP server
Coordinate agents and people on a GitHub repository: who is working on what, issue claims, and merge conflict checks before a pull request.
1 skill · 1 MCP server · hooks
The /callimachus:recall skill, the Callimachus MCP server and the memory hooks for Claude Code.
1 skill · 1 MCP server · hooks
Manage macOS caffeinate to prevent system sleep
1 skill · hooks
An output style that makes what Claude writes easy to take in at reading speed: the point, the ask and the stakes first, for a reader who wasn't in the session.
2 skills
Plan a trip end-to-end and deliver a versioned HTML MASTER itinerary: assessment interview, date-verified attractions and local events, route alternatives, real-geodata SVG maps whose routes follow actual roads, day cards with drive times, Wikimedia photos with credits, a weather widget, and copy-to-clipboard research prompts. Ships the trip-fact-checker agent for the adversarial audit phase.
1 skill · 1 agent
Search across Claude Code and OpenClaw session history
1 skill · 1 command
Operate an explicit Proqi scratchpad session through its JSON CLI, or diagnose a Proqi failure read-only first. Requires the proqi executable.
2 skills
数学建模竞赛助手:审题、数据假设驱动选型、实验验证、科研绘图和论文整理;支持完整流程与局部任务。
2 skills
Strip AI provenance marks from text and files: invisible Unicode, C2PA/Content Credentials, EXIF/XMP and document metadata across 30+ AI tools including ChatGPT, Claude, Gemini, Cursor, Copilot, Midjourney and Stable Diffusion. Runs locally with no service and no dependencies.
2 skills
MCP Server for Metabase with 152 tools for dbt metadata sync, reverse lineage exposures, smart question creator, and enterprise BI
1 MCP server
录音转写、原始稿保护、多平台图文审核包和已授权草稿流程
1 skill
Capture repeatable session workflows into reusable SKILL.md files
1 skill
Get a second opinion from another Claude instance
1 skill
Retired on 2026-11-11. Run /doctor, then /doctor prompt-audit, instead. This last version runs no audit; it only says so and links the retirement post.
1 skill
Lint rules for your AI agent's discipline, not its code. Audits belief-revision logs, decision propagation into CLAUDE.md, memory frontmatter, and index health.
1 skill
Token-efficient persistent memory system with 3-tier architecture, branch-aware context, smart compression, session diffing, session continuation protocol, and recovery mode.
1 skill
Reference for building production applications with the Claude Agent SDK in TypeScript and Python: query(), ClaudeSDKClient, custom MCP tools, subagents, sessions, permissions, hooks, structured outputs, cost tracking and hosting.
1 skill
Execute AI-generated code in secure isolated E2B cloud sandboxes (SDK v2): sandbox lifecycle, code interpreters, running coding agents, git operations, MCP gateway, storage mounting and metrics.
1 skill
macOS security hardening for Claude Code — PreToolUse/PostToolUse hooks that block secret exfiltration, prompt injection, persistence, and self-tampering.
hooks
Query and write the gadak mirror: read-first SQL over issues and wiki pages, views, and the write verbs.
1 skill
Turn a text description of a system architecture into a multi-layered SVG diagram, validated by a 13-dimension quality evaluator, then exported to editable PowerPoint.
1 skill
Retrieve ranked Europe PMC evidence passages for biomedical research questions.
1 skill
A skill that plans, writes, validates, proves, reviews, migrates and publishes Claude Code mods. Plan first with the smallest $ surface, a footprint diffed against the plan, a test seen failing, an isolated load that leaves evidence files, a five-line threat model, and a handoff that names what was and was not proven. Brainstorm mode checks ideas against every mod already on GitHub.
1 skill
UI/UX动效交互:装上后 AI 做界面会按动效库自动选对动效、按标准参数实现。
1 skill
Turn one brief into three complete, comparable design directions (A/B/C) inside your project. Edit one region with snapshots and undo, then integrate the chosen direction with a rollback path. Needs Node.js 22 or later.
1 skill
React and Next.js performance optimization guidelines from Vercel Engineering. Contains 40+ rules across 8 categories for writing, reviewing, and refactoring React/Next.js code.
Games above the Claude Code prompt (snake, Tetris, Doom, 2048, Minesweeper, Flappy, Pong, typing test, Space Invaders) that pause when Claude finishes a turn, and a pet that grows as Claude tests, commits and edits. Clones of the genre, not affiliated with or endorsed by Tetris Holding, Taito, Atari or id Software
Pins every subagent to the fable model by rewriting agent.spawn, with /fable-pin on, off and status. Reach L0: its own store and one command, nothing else.