Craft reliable prompts for everyday tasks, tool agents, and software work.

Evidence-grounded Codex skills for writing, polishing, reviewing, reviewer responses, and figures for top CS conferences.

An Agent Skill for turning any topic into a dependency-free interactive HTML lesson with a single-sided fan poker deck animation.

🧇 One batter, every repo — reusable AI agent & skill definitions rendered into harness-native files (.claude/, .codex/, .agents/)

Turn 14 days of AI work into one cash-first route, then work it to a receipt.

A standard agent skill to adopt & sustain the harness-engineering paradigm on any project — scaffold the .harness/ loop, keep it alive, make it self-improving. 在任意项目落地并持续运转 harness engineering 范式的标准 skill。opencode / Claude Code / Codex / Trae.

Compact coding-discipline skill for AI agents on small/local models — Karpathy guidelines × Superpowers loop in <500 words

Open bilingual UI motion recipes for humans and agents.

A methodology-first fixed-income credit analysis engine for global markets — delivered as Agent Skills (SKILL.md). Six international paradigms, four-layer architecture, S&P/Moody's/Fitch aligned. Installable in Claude Code, Codex, Cursor, Gemini, and OpenCode.

PhysisAI: trusted, local-first personal and project memory for Codex and Claude Code.

Create software that is truly your own.

Stop replaying hours of YouTube interviews. Get continuously updated, timestamped KOL transcripts, exact quote retrieval, and a portable Obsidian knowledge base for strategy, investment, product, and AI research.

**劈瓜 / AI PM JD Analyzer** 是一个面向 AI 产品经理求职场景的工程型 MVP。把原始 JD 转为岗位业务建模、核心 判断、风险质检和面试准备线索。它不把自己定位为泛用简历润色工具，也不声称已产生用户增长或商业转化。

Skills modulares para asistentes de codificación por IA. Define reglas, flujos de trabajo y estándares técnicos mediante archivos Markdowm.

Platform-aware Agent Skill for original social covers, layered typography, color systems, and quality-gated image generation.

Практики senior-разработчика для AI-агентов: спека → TDD → отладка → рефакторинг → ревью → PR. 6 skills для Cursor, Claude Code, Codex и 70+ агентов.

Context-injection skill that keeps academic agents within an MLSys x computer networks research scope

专为许愿式编程设计的skills，注重明确需求

LLM prompt engineering for agent pipelines · Write, refine, and evaluate · 3 output styles: Anthropic · Google · OpenAI · Works with Claude Code, Cursor, Codex CLI, Gemini CLI & more · MIT

Original Chinese songwriting skill for Suno with grounded lyrics, bitter-love and grassland styles, copy-ready outputs, and quality gates.

Agent Skills for professional GitHub repos - brief, structured, SEO-friendly READMEs that convert visitors into users, plus complete OSS scaffolding: community health files, templates, and discoverability best practices.

🔥 The AI stops answering and starts asking. Universal interrogation & brainstorm skill for Claude (Code / web / desktop): 7 lenses, depth ladder D1-D5, anti-deflection, evidence grounding, session briefs. Speaks your language.

Agent Skill for Codex and Claude Code to manage Volcengine ML Platform development instances, SSH workflows,training jobs, Slurm tasks, logs, and monitoring with the volc CLI.

AI-assisted MATLAB lab for optical imaging: catalog, learn, and improve scripts with guided documentation. Template only — no proprietary lab code included.

Governed, replay-tested agent skills for Codex-style maintainer workflows.

Loop-engineered goal mode for AI coding agents: visible previews, verification levels, checkpoints, delegation bounds, and terminal states.

SKILL.md-standard proofreading skill — code & document review with real, verified formal-verification backends for C, Python, Rust, Java, and C++

One skill to bring Spec-Driven + Test-Driven Development (SDD+TDD) to any AI coding agent - OpenSpec x Superpowers bridge for Cursor, Claude Code, Codex, OpenCode, Gemini CLI and more

A collection of reusable agent skills for AI coding agents

Evidence-first software-engineering workflows for Codex and Claude.

Trustworthy developer communication for AI-assisted open source.

Shareable skills for clankers

A context-light Codex Agent Skill for explicit, long-running Alpha ticket workflows.

Production-grade engineering skills for Cursor and Claude Code, full-stack architecture, TDD, security, Docker, queues, caching, and consistent UI.

Bilingual Claude Agent Skill + examples that route every LLM call (OpenAI, Claude, Gemini, DeepSeek, Grok, Perplexity) through one OpenAI-compatible Bifrost gateway for central logging. Python/PHP/Laravel/JS/curl.

每天检查沪深300股债性价比排名，按纪律返回买/卖/不动信号 · Claude/agent skill for CSI300 valuation buy-sell-hold signal

Compact repository design-system memory Agent Skill for AI coding agents

A bilingual, cross-platform AI skill suite for reflective thinking and teacher research, compatible with WorkBuddy, Codex, and Claude Code.

Open AI skills for customer reviews: analyze by lens, build case studies, spot trends. Agent Skills standard - works in Claude, Cursor, Codex, Gemini CLI, or any MCP client.

Claude Code plugin: zero-tolerance audit-and-fix pass for visual polish and code quality. Measures rendered output, fixes every violation, reports tersely.

Open Agent Skills for reliable Clickalong guided tours

The design cat that claws AI slop out of your frontend.

A grounded operating system for AI coding agents

AI Model Advisor — выбирает оптимальные LLM под задачу, считает стоимость. 41 платформа. Автообновление бенчмарков.

The first full visual reverse-engineering skill for AI agents — screenshots, runtime debugging, design tokens, and cloning.

Loopkit for Claude Code - guardrails, hooks, and two loop modes that won't let a task "finish" until it's actually done.

AI agent skills and evidence-backed workflows for understanding unfamiliar codebases, assessing change impact, and growing developers into confident maintainers.

An open-source Codex skill for creating English hand-drawn wisdom videos from fables, Chinese idioms, historical anecdotes, and the Thirty-Six Stratagems.

Evidence-based Agent Skill for project viva preparation and mock questioning.

漫画书名一报，剩下的，有请老赵。自动研究、判断、写作并交付网页漫画书评的 Codex Skill。

Agent Skill for the Octopus Deploy CLI — works in Claude Code, Codex, Copilot, Gemini CLI and Cursor: releases, deployments, runbooks, task logs, plus the REST escape hatch for what the CLI has no command for

Seven tiny agent skills that burn down the gap between your prompt and reality — through one shared unknowns ledger

A playful, modular design workflow for building thoughtful websites with Codex and Claude Code.

Agent Skill + CLI for competitive content gap analysis — sitemap research, content strategy reports, and competitor gaps

面向 Codex、Claude Code、Gemini CLI 与 Grok Build 的完整中文学术论文解析 Agent Skill

Private, read-only escalation for coding agents: consult Codex GPT-5.6 Sol Max, preserve exact follow-up threads, and isolate history per caller conversation.

Evidence-first academic writing, citation integrity, revision, peer review, and bilingual scholarly style for AI coding agents.

Make Chinese and mixed Chinese-English text sound more natural by removing formulaic GPT-style phrasing.

逐题规划AI短剧路线，生成第一集制作包、赚钱验证路径与正推倒推进度表

Evidence-backed, resumable skill ecosystem auditing for the Codex app and CLI.