backup of hermes-agent

backup of hermes-agent

技能宝 SkillHub - 中文AI技能搜索、安装与智能推荐平台

Skills for AI coding agents: code review, debugging, security audits, refactoring, cleaning up AI-written code and text, and more.

Skills for AI coding agents: code review, debugging, security audits, refactoring, cleaning up AI-written code and text, and more.

🧿 Minimal but effective AI agent skill definitions in 100 lines or less.

🧿 Minimal but effective AI agent skill definitions in 100 lines or less.

Cognitive tools for AI agents - like skills.sh but for altered states. 24 skills for task-matched mental modes.

Public repository for Agent Skills

Skills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.

Skills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

Enhance AI coding agents with structured workflows and best practices for building reliable web applications through production-grade engineering skills.

Prompts, skills, and agents that survive contact with real workflows. No vendor loyalty. Occasionally heretical. 🧙🏻‍♀️

Prompts, skills, and agents that survive contact with real workflows. No vendor loyalty. Occasionally heretical. 🧙🏻‍♀️

Provide and maintain a community-driven collection of standardized Agent Skills for Claude AI using the SKILL.md format

Martin's Awesome Skills: public-safe Hermes and OpenClaw agent skills with Telegram approval workflows

Martin's Awesome Skills: public-safe Hermes and OpenClaw agent skills with Telegram approval workflows

Polish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.

MGR — Método Governado por Rastreabilidade (Traceability-Governed Method): spec-driven development framework for coding agents, portable between Claude Code and GitHub Copilot

Portable equal-primary Claude and Codex agent harness for a governed agentic SDLC

Portable equal-primary Claude and Codex agent harness for a governed agentic SDLC

Defensive AI security audit skill for Claude and Codex. Reviews codebases and web apps for OWASP Top 10, auth and authorization flaws, business logic bugs, tenant isolation gaps, insecure defaults, secret leaks, and ORM or N+1 query issues, then produces clear remediation guidance.

Defensive AI security audit skill for Claude and Codex. Reviews codebases and web apps for OWASP Top 10, auth and authorization flaws, business logic bugs, tenant isolation gaps, insecure defaults, secret leaks, and ORM or N+1 query issues, then produces clear remediation guidance.

The world's largest open-source AI agent skill library — 280+ skills across 9 knowledge domains + 46 operational actions. Built on alirezarezvani/claude-skills + OpenSIN-AI.

Full-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.

Full-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

面向多步骤交付任务的可验证 Agent Skill，组合代码、图表、Word、PPT、视频与打包流程。

面向多步骤交付任务的可验证 Agent Skill，组合代码、图表、Word、PPT、视频与打包流程。

面向多步骤交付任务的可验证 Agent Skill，组合代码、图表、Word、PPT、视频与打包流程。

THE UNIVERSAL AGENT SKILLS LIBRARY

THE UNIVERSAL AGENT SKILLS LIBRARY

Curated 14-skill starter set from claude-skills. Performance-optimized for Claude Code.

A Claude Code plugin for an issue/spec-driven development workflow.

AppSec Skills — 15 plug-and-play Claude Code security skills that audit, harden, and fix any website or app before you ship it. OWASP Top 10, auth, API, database, frontend, backend, cloud, dependencies, secrets, and pentest-style checks — all defensive, all evidence-based.

A catered AI toolkit for astronomers

Low-context AI agent project template for Gemini, Codex, Claude, Cline, and more. One canonical AGENTS.md, shared Memory Bank, portable skills, workflows, hooks, and deterministic validation.

Low-context AI agent project template for Gemini, Codex, Claude, Cline, and more. One canonical AGENTS.md, shared Memory Bank, portable skills, workflows, hooks, and deterministic validation.

A comprehensive Claude Code plugin that automates the complete Software Development Lifecycle with 20 role-specific agents, 12 knowledge skills, and 8 commands, all guided by principles.

Ouroboros is an Agent Harness, CLI and Desktop App with Self-Improvement layer

SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

A curated catalog of self-improved agent skills for Hermes and compatible agents

SEO

SEO

The process I experienced firsthand through the https://anthropic.skilljar.com/claude-code-in-action course using real-world daily projects

95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.

95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.

95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.