Source-install a uv-based agent CLI and hand-wire its Claude Code hook integration without the init wizard

An Agent skill that helps get a research paper added to curated GitHub paper-lists (awesome-*, surveys, benchmark indexes).

Copy of user-scope agent skills

Crawl any documentation site into clean, local markdown for coding agents and RAG — with source-first repo cloning.

Digital-Marketing-Agent_Skills

Agent skill for reliable Stable Diffusion, LoRA, ControlNet, and multi-character prompt workflows.

Portable live football notification agent with goal alerts, match memory, and legal where-to-watch guidance.

Turn repeatable prompts, SOPs, and niche workflows into GitHub-ready AI agent skills.

Agent skills to track brand mentions, ranks & citations across ChatGPT, Claude, Gemini & Perplexity — AI brand monitoring + GEO for Claude, Cursor & any agent

Parse and analyze AI agent skills (SKILL.md) — deterministic folder-to-JSON analysis library

Agent Skill that detects and rewrites the tells that make text read as AI-generated (SKILL.md + zero-dependency linter).

Public Hermes skill export prepared from a private Hermes skill.

Codex skill and helper workflow for syncing LaTeX projects to Overleaf with LeafLink

My agent skills

Useful subagents, skills, commands, hooks, and more.

Korean K-12 (초중고) educational content maker - curriculum-aligned video/poster/HTML/PPT/game/audio past a deterministic education-fit gate. Claude Code skill mirroring superdesign.

Curated registry of Agent Packs — packs, skills, and plugins for AI coding agents

A lightweight behavioral frame that keeps AI coding agents grounded in repo reality - dormant guardrails, plan index + stages, evidence-based verification.

Computational ideonomy: Gunkel's science of ideas as inference-time machinery — a 37-primitive organon, an MDL-ratcheted respiratory engine, and 14 gated agent skills (Claude Code plugin)

Find and vet the strongest agent-usable skill, tool, MCP server, workflow, package, or capability stack for a real task.

The AI operating stack behind a real luxury travel advisory: editor-layer architecture + sanitized production Claude Code skills

Blockchain Philosophy Audit

Public Hermes skill export prepared from a private Hermes skill.

OpenClaw / Claude Code skill for Matrix Client-Server API via curl+jq | 通过 curl+jq 操作 Matrix API 的 AI agent 技能

Claude Code skill: criar vídeos de apresentação animados narrados com Remotion + OpenMontage (UIs nativas, sync narração↔animação, legendas, PT, sound design)

Portable skill that teaches an LLM agent to improve from its own measured outcomes — no fine-tuning, LLM as reader not author. Works with Claude Code, Codex, Cursor, Gemini, Copilot, and any agent that reads AGENTS.md.

Agent Skill: audit a SaaS for conversion, activation, retention & expansion using Revenue Centric Design (RCD) and behavioral science.

台灣企業 ESG 合規與人才職能診斷技能 (Vercel Skills 規範相容)

Public Hermes skill export prepared from a private Hermes skill.

ESLint for AI agent skills and MCP tools — audit SKILL.md files and MCP tool schemas for token bloat, weak descriptions, schema errors and duplicate tools. Zero dependencies.

Agent skill for writing, drafting, and revising Statements of Purpose, grad-school essays, fellowship statements, and MFA personal statements

AI agent skill for managing Microsoft Outlook via CLI — email, calendar, tasks, notes. COM automation, no Azure/OAuth required.

Turn a working agent skill into a clean, standalone, provider-agnostic GitHub repo ready to publish — leak-scrubbed, demo-forward, installable.

🛰️ Claude Code / Codex skill 驱动 xray-xhttp-relay 一键 VLESS+XHTTP+REALITY 中转脚本(SSH 非交互操作 16 项菜单)· A CC/Codex skill that deploys & operates the xray-xhttp-relay script over SSH

Cross-DEX arbitrage + quant-execution + risk harness skill for Solana (Claude Code / Codex): funding-basis/spatial/triangular strategies, gRPC streaming, simulate-first Jito execution. MIT.

Release-readiness skill for AI agents: verified facts, risks, and fix feed before shipping.

「演读 DECK」Claude Code Skill —— 把文章做成一屏一镜、可翻页/自动播放的沉浸式演示网页（暖黑/米白两套主色），自托管中文字体子集化，一键发布到 Cloudflare Pages。 如果嫌长想要更短的一句： 「演读 DECK」Claude Code Skill：把文章做成可翻页/自动播放的沉浸式演示网页，自托管字体，一键发布到 Cloudflare Pages。 Website 字段保持 hekouwang.pages.dev 不变即可。

Free, open-source Claude Code Agent Skills for personal finance — FIRE planning, rent-vs-buy, tax optimization & gain-harvesting, equity comp, retirement income (pensions/annuities, bond ladders), debt & student loans, relocation, and self-employed/business-owner planning. Powered by the public planfi MCP (no auth). Not financial advice.

Author, evaluate, security-review, and autonomously improve Claude agent skills - 21-check harness, behavioral/trigger/value-add evals, self-tested + CI

Local-first CLI and Agent Skill for sanitizing logs, configs, and support notes before pasting into AI tools.

A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.

Serenity-style supply-chain chokepoint analysis skill for AI infrastructure, semiconductors, and news-to-alpha research.

🛰️ Claude Code / Codex skill:搭 VLESS-XHTTP-REALITY 中转 + WireGuard 落地多出口代理链(playbook+脚本,非一键),出口 IP 为落地机 · A CC/Codex skill that builds a VLESS-XHTTP-REALITY relay backhauled over WireGuard to landing VPS (SNAT multi-exit), so the exit IP is the landing's

Reusable Agent Skills for Claude Code

A trust-rated index of public AI-agent skills, organized by job. Tells your agent which skills to load for a task — and whether to trust them (source, reputation, freshness).

Reusable AI-agent skills maintained by quiet-build. Install: npx skills@latest add quiet-build/skills

Open-source agent workflow skills and governance templates

Thin routing skill for Codex agents — one primary route per request, bounded repair loops, verification-gated completion

Global business-law radar agent skill for AI — official sources, India lens, saved briefs. By LawAired.

Harsh evidence-first POTATO review skill for academic, source, document, code, and project audits

The run-trust layer for MCP agent skills: content-addressed, Ed25519-signed, scanned, sandboxed, behaviorally trust-scored, transparency-logged. Local-first, zero-dependency. A signal, not a guarantee.

删前 Skill：清醒状态下的低防御元认知提取 Skill

Japanese solo-founder agent skills for SEO, CRO, LP, sales outreach, and KDP operations.

Hands-on git coaching skills for AI coding agents: real commands, plain-English why, undo-first recovery, and safe practice drills.

The all-seeing, multi-agent, vision-verified auditor for Claude Code. Tests every control for real, adversarially verifies, ranks fixes. Ships /customer-audit and /overnight.

Agent skills for UnoPim — domain-specific context for AI agents (Claude Code, Cursor, Windsurf) working in an UnoPim PIM codebase. Install: npx skills add unopim/agent-skills

Agent skills for platform, back-office, workflow, and fintech product teams: PRD writing, PRD review, MVP scope control, and cross-system collaboration.

Skills to orchestrate coding agents to do long horizon tasks with little to no steering