Complete UX design studio skill — research, personas, journey maps, IA, heuristic audits, usability testing. Works in Claude Code, Codex CLI, Gemini CLI, Cursor and 30+ agents (open Agent Skills standard)

Evidence-driven Agent Skill for removing generic AI-like UI defaults without turning design into another blacklist.

Seven x402 decision APIs and installable agent skills for GitHub bounties, CI, skill security, and MCP drift

Tool-neutral AI Engineering System: 174 reusable skills (installable as Claude Code plugins) for planning and building software with AI agents. Classify → plan → approve → build under quality gates. Works with Claude Code, Codex, Cursor, Windsurf, Copilot & Antigravity. Canonical in .ai/.

Codex skill for adversarial code review and implementation-plan grilling

Manage Agent Skills across harnesses; Claude Code, Codex, pi, all with symlinks from selected library

A Codex skill that turns repository context into polished logos, bilingual covers, social previews, and promo images.

Portable /graph agent skill for Claude Code and OpenAI Codex — drafts agent graphs (nodes, checkpoints, routes: a state machine) for the jobs you run every week, validated mechanically

Agent skill for Claude Code and Codex: a documentation framework for multi-session, multi-agent development - REQUIREMENTS / as-built ARCHITECTURE / REPORT / living HANDOFF split, START_HERE kickoff files, canonical-source discipline, and task ledgers that double as delegation specs. Bilingual (EN/JA) templates.

Sylvia personal Agent Skills collection following the open Agent Skills specification.

基于状态机的 UI/UX 交互审查 Agent 技能。

Custom RunCat Runners with Claude Code or Codex

Bilingual Agent Skill for exact-title original PDF retrieval and validated Obsidian storage

Official BizMuse agent skills for complete AI music video workflows.

Docs-first project incubation with 34 composable AI Agent skills—from idea and requirements to architecture, acceptance, and implementation handoff.

Reusable agent skills for Codex and other compatible coding agents

Portable Agent Skill for optimizing real estate YouTube transcripts for SEO, AEO, GEO, and machine understanding.

Open-source Codex skill for keeping long-running tasks aligned across context compaction, corrections, and resumed work.

Turn vague needs into structured, bounded, execution-ready plans. Universal and Codex-optimized Agent Skill.

Read-only GoHighLevel browser audit tool with AI-agent friendly docs, safety checks, and offline tests

Privacy-safe Agent Skill for preparing and reviewing Indian income-tax returns

One for all (agents) plugins and packages, standardized through Open Plugin, Agent Skills, compatible with Agent Package Manager

Version-controlled agent skills and cross-platform installers

Git-tree/Google Map interface for vibe coding decisions.

Low-risk Agent Skill for auditing and patching a Windows App UDP copy on macOS

Coordinate persistent Codex App tasks across isolated Git worktrees and reviewed PR/MR delivery.

Portable agent skills. Point Kit at a project, install a pack, wire Claude Code, Grok Build, and Codex.

Skills for repairing math gaps through visual intuition, small simulations, and targeted practice.

Git-backed SSOT and immutable skill projections for Codex, Claude, Pi, and other agents

🔒⚽ LineLock — pay-per-pick World Cup edge API on Injective x402: the USDC receipt IS the pre-kickoff timestamp; free public CLV ledger, losses included. Injective Global Cup 2026.

An open Agent Skill for Codex and XiaoYunque to co-plan, produce, review, and selectively retry AI image/video work through OpenAPI.

Reverse-engineered, generic build framework for adding an enterprise-style CRM sales flow to any Laravel app — usable with Claude Code or any other AI assistant.

Model orchestration doctrine for Claude Code — route tasks across Opus 4.8 / Sonnet 5 / Haiku 4.5 / Fable 5, dispatch parallel subagents, and verify what they report back.

Agent skill for evidence-led editorial infographics and social graphics without generic AI aesthetics

Harness-neutral Agent Skills for safe VS Code crash recovery and project-scoped build cleanup on macOS.

Cross-platform, observable, and safely reclaimable local workers for OpenAI Codex CLI.

Agent skill for Claude Code and Codex: create PRs from a temporary git worktree off origin's default branch when the main checkout is dirty, behind, or shared with other agents - with merge-mode-aware cleanup guards.

Skills for helping beginners find repositories, understand issues, plan PRs, and message maintainers well.

Skills for validating startup ideas with interviews, competitor maps, MVP scopes, and experiment scorecards.

Pure ESM multi-platform social media fetch skill (Weibo, Zhihu, XHS, Douyin, Bilibili, …). Node built-ins by default, no npm required.

house-rules: every folder has house rules — write them down, keep them true. Claude Code plugin & portable Agent Skill (works in Codex too) that documents each directory's file pattern into a short AGENTS.md, kept honest by a pre-push staleness gate.

Portable Agent Skills for non-RAPP systems and launchpads for single-file RAPP agents

A verification deck for checking sources, assumptions, and concrete targets without replacing the result.

A configurable #nohello skill: detects greeting-only chat messages, waits, and nudges the sender to ask their real question. Claude Agent Skill + Slack/Teams adapters.

Daily source-linked product ideas as agent-ready build briefs (zh/en). Public mirror of raytally.com — updated daily by pipeline.

World Cup sideline AI agent on Injective — CCTP, x402, MCP, Agent Skills, and binary options in one workflow.

Agent Skill for evidence-backed memory, reusable procedures, and daily feedback governance inspired by Engineering Cybernetics.

Budget-controlled, evidence-based review and repair for PRs, local diffs, and implementation plans.

🤿 Free AI skill: identify any fish, nudibranch, coral or freshwater critter from a name, description, or photo — verified against WoRMS/FishBase/GBIF, never guessed. Outputs a printable species card. Works with Claude Code/Cowork, Codex, OpenClaw, Hermes.

Compile and audit executable branching-story packages for replayable multi-seat AI games.

The source is public. The live knobs aren't. Evidence-checked claims and an agent skill for X's 2026 For You algorithm.

유튜브 링크로 SEO 분석하고 제목/설명/태그 후보를 뽑아주는 에이전트 스킬

AI tarot reading skills for AI agents — interactive spreads, real randomness, Rider-Waite-Smith imagery

Official agent-agnostic skills for dotenc

Skills for learning investing through thesis logs, bear cases, earnings calls, and risk journals.

Skills for learning APIs through first requests, docs maps, auth debugging, and SDK examples.

A lightweight, interactive meta-skill for composing AI agent skills into task-specific workflows.

YUAN元解密 AI Skills：面向真实内容运营场景的可安装智能体技能

Agent Skills for stealthy, human-like browser automation with Playwright and Camoufox — real-browser agentic browsing that evades bot detection.

Public agent skills maintained by Flamel.ai