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 enables Hermes Agent to generate prototypes, motion graphics, and decks. It integrates with over 150 design systems and 22 local CLIs to bridge the gap between coding agents and visual design.
A comprehensive library of 754 structured cybersecurity skills mapped to major industry frameworks like MITRE ATT&CK and NIST CSF 2.0. It uses the agentskills.io standard to bring professional security domains to agentic workflows.
This skill converts natural language and codebases into .drawio XML diagrams. It supports a wide array of presets including UML, ERD, and Architecture, utilizing over 10,000 official shapes.
An agentic evolver that automates skill deduplication and quality improvement through background evolution loops. It unifies skill libraries across different agents and teams while natively integrating with Hermes and OpenClaw.
A content auditing tool that eliminates detectable AI writing patterns through rewrite, detect, and edit modes. It utilizes a tiered replacement table of 109 words and 10 phrases to ensure human-like output.
A cross-platform library of modular skills based on industry guidelines and established texts. It is compatible with Claude Code and agentskills.io agents, offering installation via a plugin marketplace or npx.
A meta-skill plugin that monitors active workflows to automatically detect and propose reusable skills. It generates both the necessary Python plugin scaffolds and SKILL.md documentation for seamless saving.
Provides type-safe agentskills.io support for Pydantic AI. It employs progressive disclosure of skill metadata to reduce token usage and supports both programmatic and filesystem-based definitions.
A suite of tools for extracting YouTube transcripts, captions, and timestamps without relying on yt-dlp. It enables Hermes Agent to perform video searches, browse channels, and extract playlists.
A community hub for browsing and one-click installation of skills, featuring automated security scanning with 65+ threat detection rules. It includes a creator marketplace with crypto and Stripe payment support.
A set of skills that teaches Hermes Agent to write its own analytical prompts and custom thinking instructions. It helps agents identify structural conservation laws and generate reports on analysis blind spots.
A harness for long-running agents that provides structured memory and a plan-approve-execute lifecycle. It stores work and proof in local plain files to facilitate cross-feature learning.
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.
A literate programming skill that weaves code and documentation into .lit.md files. It uses a tangler to extract runnable source files and automatically syncs edits back to the literate document.
A memory management system that enables cross-instance shared memory via markdown files. It captures high-value decisions to create a pipeline for fine-tuning and switching to replacement models.
Provides agentskills.io compliant tools for interacting with the Chainlink oracle network. It supports integrations for CCIP, VRF, Data Feeds, and Data Streams, installable via the Vercel skills CLI.
Converts repositories, documentation, and developer discourse into agentskills.io-compliant skills. It prevents instruction rot by tracing instructions to specific file lines and pinned commits.
The official FLUX image generation skills providing standardized prompting guidelines for FLUX.1 and FLUX.2. It includes API integration patterns for webhooks, polling, and precise hex color specifications.
A registry of reusable AI skills based on the AgentSkills specification. It features an OpenAPI-driven SDK and CLI for versioned installation with recursive dependency resolution.
An execution skill for complex, multi-step tasks that features autonomous tracking and checkpoints. It includes built-in rollback procedures to ensure safe recovery during long-running tasks.
A progressive MCP client that uses three-layer lazy loading to minimize token consumption. It utilizes a socket-based daemon architecture to support hot-reloading of server configurations.
Enables Hermes Agent to manage Nextcloud files, calendars, and contacts via WebDAV and CalDAV. It ensures secure communication over HTTPS using Nextcloud App Passwords.
A C# / .NET implementation of the agentskills.io specification with MCP integration. It integrates with Microsoft.Extensions.AI for tool-based loading and supports automatic directory registration.
A plugin that rewrites and scores prompts across various surfaces like Discord and Telegram. It tailors rewrites based on model reasoning capabilities and tracks token savings in a local SQLite database.
An adversarial code review tool that uses three parallel subagents to attack code from different angles. A consolidator agent then triages the findings into risk-tiered reports without modifying the code.
An adversarial code review tool that uses three parallel subagents to attack code from different angles. A consolidator agent then triages the findings into risk-tiered reports without modifying the code.
A multi-agent swarm targeting code hygiene, clarity, and correctness to simplify codebases. It uses a risk-tiered triage system and detects language-specific anti-patterns like N+1 queries.
A multi-agent swarm targeting code hygiene, clarity, and correctness to simplify codebases. It uses a risk-tiered triage system and detects language-specific anti-patterns like N+1 queries.
An intelligent retrieval system using five layers—including FTS5 and dense embeddings—to filter 100+ skills down to the five most relevant. This reduces token consumption via a non-invasive integration.
Automates payments for HTTP 402 responses using USDC across multiple protocols like Pay Link and x402. It is compatible with the agentskills.io standard, Hermes Agent, and OpenClaw.
Automates payments for HTTP 402 responses using USDC across multiple protocols like Pay Link and x402. It is compatible with the agentskills.io standard, Hermes Agent, and OpenClaw.