The most popular skills and skill registries in the Hermes ecosystem, ranked by GitHub stars. Skills are reusable capabilities that follow the agentskills.io open standard — from cybersecurity to diagram generation to creative ideation.
A local-first design and prototyping system that integrates directly with Hermes Agent and 15 other coding-agent CLIs. It provides 137 composable skills and 150 design systems with support for multiple export formats including HTML, PDF, and PPTX.
A library of 754 structured cybersecurity skills mapped to major frameworks like MITRE ATT&CK and NIST CSF 2.0. It follows the agentskills.io standard to enable sub-second discovery and execution across 26 security domains.
Enables the generation of .drawio XML diagrams from natural language descriptions with six specialized presets for architecture, UML, and deep learning. It utilizes visual feedback loops to self-check and automatically fix layout issues.
An auditing tool that eliminates detectable AI writing patterns through rewrite, detect, and edit-in-place modes. It uses a 109-entry word replacement table and 47 pattern categories to ensure content compatibility with Hermes and other AI editors.
An agentic evolver that automates skill deduplication and quality improvement through background evolution loops. It unifies skill libraries across different agents and teams while integrating natively with Hermes and OpenAI-compatible APIs.
A cross-platform library offering modular frameworks for UX design, architecture, marketing, and product strategy. These skills are compatible with Claude Code and agentskills.io-compatible agents via a marketplace or npx CLI.
A meta-skill plugin that monitors active workflows to automatically detect and propose reusable skills. It generates Python plugin scaffolds and SKILL.md documentation, manageable via dedicated slash commands.
Provides type-safe agentskills.io support for Pydantic AI, utilizing progressive disclosure to reduce token consumption. It supports both programmatic Python definitions and filesystem-based skill loading.
A suite of tools for extracting transcripts, captions, and timestamps from YouTube without relying on yt-dlp. It enables Hermes Agent and other compatible tools to perform video searches, channel browsing, and playlist extraction.
A community hub for browsing and one-click installation of skills, featuring automated security scanning with over 65 threat detection rules. It includes a creator marketplace with crypto/Stripe payments and an agent-to-agent trust scoring system.
Teaches Hermes Agent to write its own analytical prompts and custom thinking instructions for complex problem solving. It identifies structural conservation laws in codebases and generates constraint reports to highlight analysis blind spots.
A harness for long-running agents that manages shared state locally in .maestro/ without needing a database. It decomposes complex specifications into execution plans and uses JSON handoff envelopes for seamless cross-session transitions.
A literate programming skill that weaves prose, diagrams, and source code into .lit.md files. It includes a tangler to extract runnable source files and automatically syncs edits back to the original literate document.
Implements cross-instance shared memory via markdown-based fabric directories to help agents remember previous work. It features an end-to-end pipeline for extracting training data and fine-tuning replacement models.
A pre-build workflow that transforms rough ideas into structured design documents and implementation handoffs. It offers Lite and Full modes and includes a spec review gate with PASS/FAIL evaluation models.
Standardized skills for interacting with the Chainlink oracle network, including CCIP, Data Feeds, and VRF. It supports local simulations and CRE onboarding, compatible with Vercel's open skills ecosystem CLI.
Converts repositories, documentation, and developer discourse into agentskills.io-compliant instructions. It ensures traceability by linking instructions to specific source file line numbers and uses version-pinning to prevent instruction rot.
The official skill set for FLUX.1 and FLUX.2 image generation, providing standardized prompting guidelines and API integration patterns. It supports JSON structured prompting and precise hex color specifications.
A registry for reusable AI skills based on the AgentSkills specification, featuring an OpenAPI-driven Python SDK and CLI. It supports recursive dependency resolution and monetization via Stripe and the TON blockchain.
Provides autonomous execution for long-running, multi-step tasks with real-time progress tracking. It includes built-in rollback procedures to ensure safe recovery during complex task execution.
A progressive MCP client that uses a three-layer lazy loading architecture to reduce token usage by up to 86%. It employs a socket-based daemon for persistent connections and supports hot-reloading configurations.
Integrates Hermes Agent with Nextcloud to manage files, notes, calendars, and contacts via WebDAV and CalDAV. It ensures secure communication over HTTPS using Nextcloud App Passwords and includes a guided setup script.
A C# / .NET implementation of the agentskills.io specification with MCP integration. It utilizes SKILL.md files for progressive disclosure and integrates with Microsoft.Extensions.AI for tool-based skill loading.