Agent skill that turns visual questions into live, clickable browser screens - mockups, layout comparisons, diagrams

Context-aware prompt refinement for Pi using GPT-5.6 Luna through a Codex subscription.

Claude Code skill that writes beautiful, professional READMEs that look hand-crafted, not generated. npx skills add evol1228/readme-skill

SuperLoop：把模糊想法编译成可验证目标，并运行可审计、可恢复、可优化的 Agent 循环。

A portable Claude Code skills library (plugin) for a Django 5.2 + Next.js 16 house stack: 30 model-agnostic, tenant-isolation-and-security-first skills.

Agent Skill that reconstructs authorized websites as local React and TanStack Router projects

Autonomous, self-improving AI agent platform for Claude Code — safe capability & skill acquisition, MCP/tool discovery, sandboxed policy gates, and token-efficient learning.

你的私人气步枪射击团队

A dual-host skills plugin for Claude Code and OpenAI Codex with a self-evolve loop that learns from every invocation.

Checklists for everything an app is expected to have and coding agents routinely skip — empty states, delete confirms, undo/redo, loading feedback, AI chat UX, routing, security, legal, i18n. 25 framework-agnostic files. Installs as a Claude Code plugin.

Security scanner for third-party AI agent-skill files (SKILL.md manifests, hooks, bundled scripts). CLI, library, MCP server, and GitHub Action, all reading the same 10 rule packs, including cross-skill privilege chaining and prompt-injection detection. Zero-auth, zero-config npx or pip scan.

私域专家团 · 马甲实战版 — 结构化 Task Runtime + 单步路由 + 四官隔离评审 + 四层质量门（判官/蒙卡走 B 路径零 API），/siyu 一个入口 · v0.7.0

面向 Agent 的研究生/本科生级源码学习 Skill：结合论文、真实代码证据与张量形状，按 Step 深入解析深度学习项目，并通过学习记录、反馈闭环和盲点审计持续复盘

Cursor Agent Skills for preparing portrait LoRA datasets and training them with fal-ai/flux-lora-portrait-trainer

交易日志 Skill：在 Claude / Codex 里一句话记下交易和当时的理由，导入 IBKR / 嘉信流水，FIFO 算清盈亏 —— 数据全程在你自己的 GitHub 私有仓库，零依赖

边淬火个人 IP 的 Agent Skill 工具箱：可通过命令行安装和更新

Evidence-first Agent Skill for surfacing decision-changing unknowns before commitment.

嘴替·甲方包 —— 专治甲方压价/加需求/拖款/无限改稿：把含糊的成本拉回明面。四拿回原则 + 三档回复。Made with 嘴替.skill

🔥捕捉编码提示的灵感火花。将它们组合成可复用的配方。在后续任务中回忆并调整——适用于Claude Code、Codex和任何智能体技能宿主。 Capture coding prompt sparks. Compound them into reusable recipes. Recall & adapt on the next task — for Claude Code, Codex, and any Agent Skill host.

Task Compass Skill: deterministic, auditable task routing for AI agents and OpenClaw

AI agent skill that generates a professional consulting-style scholarship/study-abroad strategy report PDF (tables, radar & bar charts) from a structured applicant questionnaire.

Portable, versioned skills, rules, prompts, and configurations for AI-assisted software development.

Validate, pressure-test, and release-gate SKILL.md packages for OpenAI and portable agent runtimes.

AI copywriting that doesn't sound like AI — a copywriting skill for Claude Code, Cursor, Cline & Copilot. Every line passes three questions: can I visualize it, can I falsify it, can nobody else say it.

Local raw capture layer for agent sessions, preserving decisions and handoffs as wiki/LLM knowledge-base ingestion.

A portable AI-agent skill for finding project blind spots, unknown unknowns, hidden risks, and missing decisions, with a durable ledger for repeat audits across Claude Code, Claude desktop/Cowork, Codex, and OpenCode.

Global persistent memory for OPENCODE sessions. Inspired by Claude Code's auto-memory — your agent remembers what it learns, across every session, globally.

Make coding agents prove their work with tests, builds, runtime checks, and honest evidence before they say “done.”

Portable, evaluated Agent Skills for product, business, and engineering workflows.

Bilingual agent skill for safe, repeatable Cheat Engine CLI workflows｜Cheat Engine CLI 中英双语 Agent Skill

531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.

Make your python CLIs install your agent skills.

Cross-host skill for Codex, Claude Code, and Cursor that orchestrates parallel OpenCode agents with optional iTerm2 split panes.

Windows-safe lean coding skill and plugin package for Codex, Claude Code, and AI agents.

🩺 Audit and refactor Claude Code skills like Matt Pocock's method from "Building Great Agent Skills: The Missing Manual". 5 checks, one prioritized report, fixes only on consent. Lints SKILL.md and proposes execution tags with validation tests.

An ADK 2.0 multi-agent guardrail that screens pull requests for security flaws and AST violations before executing safe LLM code reviews.

Cross-platform Agent Skill and Python CLI for decoding, deduplicating, and reconciling Garmin FIT workout files

Pre-mortems and postmortems for AI coding agents: 261 tagged real-world incidents + a 12-class agentic-AI failure model, shipped as Claude Code skills.

Drop-in agent skills that make an AI appraise medical literature like a reviewer — grade every citation against its source, run reproducible PRISMA searches, pool studies safely, and defend RAG against prompt injection. Framework-agnostic, MIT.

一条 /XGQQ，用同一个 Agent Skill 让 9 种 AI 智能体共同维护 Obsidian 本地第二大脑。

Turn a use case into a grounded agentic system design. An opinionated AI solutions architect as an agent skill.

Why "act as an expert" prompting fails on accuracy — and how procedural SKILL.md files solve it. Research + worked example + honest evaluation.

Privacy-safe forward-deployed engineering skills for Claude Code, Codex, and AGENTS.md-compatible agents

Agent-neutral project orchestration skill from idea to delivery

Claude-Code-Skill, der AI-Slop aus deutschen Texten entfernt: Em-Dashes, Floskeln, erfundene Zahlen. Für Claude Code, Codex und Cursor, inklusive Prüfskript.

An agent skill for detecting, preventing, and removing generic AI-looking web design patterns.

Session-handoff skill for agentic coding assistants — writes a living HANDOFF.md so a fresh agent can continue unfinished work. Checkpoint as you go.

Local-first capability router and safety gate for AI agent tools

Standalone Liuyao skill for deterministic charting, interpretation prompts, and multi-agent runtimes

A project-local, git-tracked execution record for coding agents: crash recovery, handoff, branch isolation, and safe squash — portable across Codex, Claude Code, Antigravity, Gemini CLI, and Cline

Turn Bilibili and YouTube learning videos into detailed, timestamped Obsidian study notes with a mandatory quality gate.

Agent-agnostic software engineering skill for implementation, debugging, testing, refactoring, security boundaries, verification, and code review.

发抖音、小红书、视频号、快手、B站、微博或知乎之前，先让 AI 审一遍。检查违禁词、AI标注、版权、广告合规和跨平台名称，给出能不能发、问题在哪、怎么改。附合规评分卡、发布前自检清单和 AIGC 标识指南。

Agent Skill for source-grounded STORM research artifacts and prompt-native Co-STORM exploration.

Meta skill to design production-quality agent skills.

Bilingual, searchable Agent Skills for reproducible scientific research across Claude Code, OpenAI Codex, and OpenCode.

Skills that let a coding agent delegate work to another coding CLI, and keep itself in sync from git.

Agent Skills that design minimalist app and OSS package icons from a text brief or project context - symmetric logos on dark grey, Apple-style rounded-rectangle backgrounds.

Auditable self-running critique loops for AI agents and plan review

A universal collection of Agent Skills