Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,846 indexed, measured the same four ways as everything else here.
Evaluate repository or project code quality and produce an evidence-based scorecard. Use when asked to review code quality, score a project, assess maintainability, inspect technical debt, evaluate architecture/readability/refactoring health/engineering practices/code smells, compare project quality, or prepare a…
Create XXD Panel 061 raster artwork from one image or a directory batch while treating the bundled original style brief as the sole aesthetic authority. Supports one or more top-bottom, left-right, design-only, and four-device wallpaper outputs; multiple ratios or exact sizes; prompt-generated, user-exact, or…
A Chinese-language workflow for turning Xiaoyuzhou podcast episodes into transcripts, chapter notes, guest background, and structured summaries. Xiaoyuzhou is a Chinese podcast platform.
A Chinese-language job-application assistant turns a résumé into reusable experience notes and uses them with a job description to draft greeting messages for BOSS Zhipin and similar platforms.
MCP server "claude-code-explorer" as configured in nilupulk/claude-code-free. Runs mcp-server/dist/index.js with node. Needs 1 environment variable to run.
A command-line guide for adding Shadcn-style interface components to Taro projects, which are apps built with the Taro framework. It covers setting up the project and generating components such as buttons and accordions.
This skill turns Claude into your personal brand designer. Through a guided conversation, Claude will ask you everything it needs to know about your brand — your name, personality, colors, fonts, vibe, and more — then generate a complete, beautiful HTML brand kit file you can download and keep forever.
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
A resume-conversion workflow that reads a resume in common file formats or pasted text, extracts its content into structured data, and exports it through BigPengSays/JadeAI templates.
Use when the user wants to pair PocketClaw, install or upgrade ClawPilot, verify host runtime readiness, and generate a pairing code for OpenClaw, Hermes, or cc-connect Coding Agent hosts. Follow a strict pairing workflow and output the final pairing code on its own line when successful.
Cada estilo define TODOS os parâmetros visuais para uma campanha. Selecione o estilo com base no tipo de campanha, personalidade da marca e público-alvo. Combine no máximo 2 estilos se necessário (primário + secundário para acentos).
A communication framework for high-stakes conversations, where people disagree, emotions are strong, and the outcome matters. It focuses on speaking honestly while keeping enough safety for both people to continue the conversation.
A method for rebuilding a damaged raster image from its existing composition. Raster images are pixel-based files such as PNGs and JPEGs; the method preserves the arrangement and subject relationships while replacing degraded visual details.
Diagnose and repair Codex threads where WebSocket reconnecting, stream disconnects, slow hydration, context failures, or "Invalid image in your last message" are caused by oversized rollout JSONL files with embedded image payloads. Use for Codex sessions bloated by data:image, inputimage, or imageurl fields that need…
A set of rules for carrying out authorized black-box penetration tests, where the tester examines a system without access to its source code. It defines testing boundaries, safety limits, and the evidence needed to report a vulnerability.
An installation coordinator for Personal Agent Foundation, a set of shared files and tools for running personal AI-agent projects. It creates a new base, installs its global rules, and guides first-time setup.
A front-end page generation skill for building web pages and applications with React, Vue 3, Next.js, Nuxt.js, or simpler HTML-based tools. It covers visual design, API connections, forms, animations, and icons.
A skill for operating the lottery-predictor-main project for China’s Double Color Ball lottery. It covers prediction requests, updating draw data, backtesting, archived analysis, patch replay, and project commands.
A Chinese-language thinking framework based on more than 200 livestream call transcripts. It analyses situations through realism, power relationships, personal boundaries, and action-oriented pessimism.
Prepare safe GitHub PR workspaces, scan all supported source files in a complete repository, build a lightweight caller-to-callee graph, analyze frontend and backend Git changes with symbol and API references, infer direct and transitive business impact, and produce a prioritized, evidence-backed test scope. Use when…
An image-annotation workflow for creating COCO detection and instance-segmentation labels for selected object categories in one image. COCO is a common format for training and evaluating computer-vision models.
This skill performs comprehensive code quality analysis across multiple dimensions. It evaluates code quality not just by looking for bugs, but by assessing the overall health of a codebase — style consistency, complexity, security posture, maintainability, and performance characteristics.
★not rated 13 5mo agoA121 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: