Install
git clone https://github.com/Dadmin88/hermes-profile-packsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Hermes Profile Packs
Curated profile packs for Hermes Agent.
This repository is the public upstream home for reusable Hermes profile distributions maintained as coherent teams rather than isolated prompts.
Packs
| Pack | Namespace | Purpose |
|---|---|---|
| Hermes Agency | agency-* |
Professional specialists for engineering, product, design, QA, operations, marketing, content, and coordinated project work. |
| Hermes Council | council-* |
Personal specialists for growth, health, fitness, parenting, relationships, communication, community, faith, finances, home stewardship, personal admin, career, learning, recreation, travel, nutrition, sleep, and preparedness. |
| Hermes Academy | academy-* |
Professors and instructors for academic, technical, vocational, and professional learning. |
The packs deliberately separate durable context domains. Agency executes professional work, Council supports the person, and Academy teaches. A work profile should not need private life context, a personal profile should not inherit repository state merely because both run on Hermes, and a teaching profile should not silently become a production executor.
Hermes Agency contains 113 professional specialists. Hermes Council contains 21 focused profiles and 84 purpose-built personal-life skills. Hermes Academy contains 30 faculty profiles and 120 purpose-built teaching skills.
Academy Continuing Education
Hermes Academy Continuing Education lets a profile learn a reusable capability from an installed instructor. A request such as Go learn API security routes through the Academy Dean, creates a learning goal, supports study and demonstrated transfer through Bot Chat, and saves the capability to the learner's skill store through /learn. It requires no separate training or distributed runtime.
The flow requires a Hermes build that supports goal_manage, profile-distribution preload_skills, bounded goal-judge feedback, and the associated Bot Chat behavior. Confirm those capabilities in your Hermes release before using Continuing Education; compatibility with the standard Hermes release is not yet guaranteed.
See the Continuing Education guide and architecture contract.
Start small with Team Recipes
You rarely need all 164 profiles. Team Recipes are validated compositions of existing profiles for common outcomes, with minimal, recommended, and expanded tiers.
The main installer understands them directly:
python install.py --list-recipes
python install.py --recommend "build and ship a web app"
python install.py --recipe software-delivery --tier minimal --dry-run
python install.py --recipe software-delivery --tier recommended --yes
Recommendation is confidence-aware. A recipe is promoted only when one formation is a strong, unambiguous fit; otherwise the installer falls back to individual profile matches instead of forcing a template.
Recipes are portable selection guidance only. They do not create memory, cron jobs, Bot groups, Kanban state, credentials, or other runtime state. Installation still uses the normal Profile Packs/Hermes distribution path.
See docs/TEAM_RECIPES.md and docs/FIRST_TEAM.md.
Repository layout
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…