alanl1234/xiaohongshu-matrices-cli
Skill Claude CodeCodex
A command-line guide for Xiaohongshu, also called Little Red Book, a Chinese social-media platform for notes, profiles, and interactions.
Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 268,996 indexed, measured the same four ways as everything else here.
alanl1234/xiaohongshu-matrices-cli
Skill Claude CodeCodex
A command-line guide for Xiaohongshu, also called Little Red Book, a Chinese social-media platform for notes, profiles, and interactions.
reshadat/first-principles-destructor
Skill Claude CodeCodex
First principles destructor — strips any statement, business model, product idea, process, or industry belief down to its physics/math/logic floor. Calculates the convention tax (what you pay because of habit vs necessity). Rebuilds from reality. Use when evaluating pricing, hiring timelines, product approaches, team…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
A Chinese-language framework for judging decisions through practical constraints, evidence, returns, risks, and ordinary people's circumstances. It is associated with the direct analytical style of Hu Chenfeng.
Skill Claude CodeCodex
A tool for carrying out one Git operation that has already been selected, such as fetch, rebase, commit, push, or commit and push. Git is the system that records code history and shares it with remote repositories.
1killermouse/vibe-coding-prd-skill
Skill Codex
A guide for turning product requirements, competitor research, ideas, or documents into a short Markdown plan that coding agents can follow.
Skill Claude CodeCodex
Control Claude Code via MCP protocol. Trigger with "plan" to write a precise execution plan then feed it to Claude Code. Also supports direct commands, persistent sessions, agent teams, and advanced tool control.
Skill Claude CodeCodex
Provides institutional coding knowledge ("Coding Bible") covering architectural decisions, coding standards, framework-specific rules, security expectations, performance guidelines, and approved patterns for AI-assisted development. Guides code generation, refactoring, architecture decisions, database query authoring…
MCP server Claude CodeCodexCursor +2
One of 5 in claude_desktop_config.json
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.
Skill Claude CodeCodex
Skill "device-use" from zvadaadam/deus-machine, covering device-use, commands, simulator lifecycle, apps and permissions.
Skill Claude CodeCodex
Manage skills with the skillbox CLI.
Skill Claude CodeCodex
Generates Figma Code Connect mappings for React or Angular repos, validates them with pre-checks and the Figma CLI, and can publish via figma connect. Use when a user provides a Figma file URL and a component repo and asks for Code Connect files, figma.config.json, or validation.
Skill Claude CodeCodex
Compress images, long prompts, conversations, and RAG documents locally via Ollama before consuming LLM tokens. Reduces token usage by 80% on images and 85% on text. Use proactively when: the user uploads images, processes long context, works with multiple RAG sources, or when approaching token limits.
NVIDIA-Omniverse/usd-convert-cad
Skill Claude CodeCodex
Convert supported CAD files to OpenUSD with the standalone usd-convert-cad Python wheel.
Skill Codex
Use only when the user explicitly asks for CWF, a dynamic workflow, a reusable workflow.js harness, or a bounded multi-agent run with independent workers and verification. Not for ordinary coding, routine review, generic repo audits, planning, /goal writing, status checks, reminders, external-model routing, or work…
Skill Claude CodeCodex
Edit and review docx-style documents.
Skill Claude CodeCodex
How to add RMS/Peak metering at any point in a Faust DSP for debugging with MCP.
Skill Claude CodeCodex
Use when interacting with Ghostty terminals — listing, peeking, sending text, managing windows/tabs/splits, or controlling Claude Code teammates.
arthurzhuhan/one-person-capital
Skill Codex needs its repo
Technical guide for creating a new OnePersonCapital agent adapter. Use when building a new adapter package, adding support for a new AI coding tool (e.g. a new CLI agent, API-based agent, or custom process), or when modifying the adapter system. Covers the required interfaces, module structure, registration points…
Skill Claude CodeCodex
Run R8/ProGuard on Android APK without Gradle — shrink, obfuscate and minify DEX using R8 that's already inside d8.jar.
Skill Codex
Integrate the Embinder WebMCP SDK into an existing product and make its browser experience AI-native. Use when a coding agent must inspect any web application or platform, inventory every page and user-facing function, expose real actions and live context through Embinder, add the resident agent, cursor, spotlight…
Skill Codex
Route work to the correct Pretty Good Prompts (PGP) document and produce structured, artifact-oriented outputs for Claude workflows. Use when tasks in this repository (or repositories consuming these prompts) require high-quality analysis, modernization planning, documentation updates, or implementation guidance…
Skill Claude CodeCodex
Name: skillmaxxer-3000 Purpose: Intelligently architect Claude Skills with appropriate structure based on purpose and requirements Type: Meta-skill (builds other skills) Status: Production Ready Version: 4.0 Archetype: Complex/Interview (this skill uses its own framework).
Skill Claude CodeCodex
You are running an autonomous experiment loop that optimizes a system prompt for an AI agent evaluated on SimLab tasks. You will modify system-prompt.md, run the agent against tasks, measure the average reward, and iterate.
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: