witcheer's Wingtips for Hermes Agent

Wingtips

1. #111 · name the skill, then call it

   Oct 26, 2026 · Skills & instructions · CLI / Desktop / Gateway

   when you and your agent finish a task you will do again, ask it to keep the steps as a skill:

   save what we did as a skill called weekly-update

   it writes the steps from the chat you had and saves them. the name you pick becomes a slash command, so in a new chat you type /weekly-update with your notes and it follows the same steps.

   great for a weekly update, a report you format the same way every time or a setup you repeat on each new project!

   docs: https://hermes-agent.nousresearch.com/docs/guides/tips#when-to-create-skills

   SourcesHermes docs: Tips

2. #107 · skill installs on a shared connection

   Oct 20, 2026 · Skills & instructions · CLI

   the skills hub reads skills through the GitHub API, and without a token GitHub allows 60 requests an hour per network address.

   one line moves your Hermes Agent onto its own budget of 5,000 an hour:

   hermes config set GITHUB_TOKEN <your token>

   docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills

   SourcesHermes docs: Skills

3. #93 · let your Hermes Agent install its own skills

   Oct 6, 2026 · Skills & instructions · CLI / Desktop / Gateway

   your Hermes Agent can find a skill and run the install itself, so you don't need the skill's name or the command. ask in plain words:

   "find a skill for flashcards and install it."

   it picks a match, runs the security scan and then tells you what to say to use the new skill.

   handy when you want your agent to pick up something new, or when you're setting up a fresh profile!

   it knows how because every Hermes Agent ships with a built-in skill called hermes-agent, which covers how Hermes works and how to configure it.

   docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills

   SourcesHermes docs: Skills

4. #80 · skills.auto_load, the skills you want in every session, pinned

   Sep 22, 2026 · Skills & instructions · CLI / Desktop / Gateway · Hermes v0.21.4+

   Hermes Agent loads a skill when a task calls for it. some skills you want in every session whatever the task: a house style, a review checklist, the way you write commits.

   new in Hermes Agent (v0.21.4 and newer): this key pins them. every name on the list is fully loaded at the start of every new session, on the CLI, on every gateway platform, in cron jobs.

   Copy code

   skills:
     auto_load:
       - my-workflow
       - github-pr-workflow
   

   resolved once, when the prompt is first built, so the prompt stays cache-stable. an edit to the skill shows up in the next session.

   hermes -s <skill> does the same for one launch. per profile, empty by default.

   docs: https://hermes-agent.nousresearch.com/docs/user-guide/configuration#auto-loading-skills-every-session

   SourcesHermes docs: Configuration

5. #72 · skills.create_dir, where new skills land

   Sep 14, 2026 · Skills & instructions · CLI / Desktop / Gateway

   your agent writes itself a new skill after a good session, and it lands in the profile's own skills folder, on that machine, for that profile.

   Show full tip

   create_dir under skills in config.yaml moves that.

   every skill the agent creates from then on is written to the folder you name, a shared repo or a folder every profile can see. the agent's own instructions follow the setting, so it knows where new skills go without being told each time.

   skills you already have stay where they are and are edited in place.

   Copy code

   # in ~/.hermes/config.yaml
   skills:
     create_dir: /opt/brain/skills
   
   # or from the terminal
   hermes config set skills.create_dir /opt/brain/skills
   

   the folder is created on the first write. skills under it still show in hermes skills list, skill_view and as /skill-name slash commands. ~ and ${VAR} expand, and a relative path resolves against your Hermes home. this is the write side of #70 skills.external_dirs, which is where Hermes also reads skills from; point both at the same shared folder and you have one place for everything.

   docs: redirecting skill creation

   hand this to your agent: "set skills.create_dir to a folder of my choice, then create a two-line test skill and tell me the path you wrote it to."

   Sourcesnotwitcheer.github.ioHermes docs: Skills

6. #70 · skills.external_dirs, one shared skills folder

   Sep 12, 2026 · Skills & instructions · CLI / Desktop / Gateway

   you keep your skills in one folder for every agent tool you use, or your team keeps them in a shared repo.

   Show full tip

   Hermes Agent can scan those folders too.

   add external_dirs under skills in config.yaml and every skill it finds there joins the index, shows up in hermes skills list, and answers to its /skill-name slash command, the same as a skill you installed yourself.

   if a skill with the same name lives in both places, your local copy wins.

   Copy code

   skills:
     external_dirs:
       - /home/shared/team-skills
       - ${SKILLS_REPO}/skills
   

   or from the terminal:

   Copy code

   hermes config set skills.external_dirs '["/home/shared/team-skills"]'
   

   paths take ~ and environment variables; a folder that does not exist is skipped. a writable external folder can be edited by the agent's skill_manage tool, so use filesystem permissions if the shared set must stay read-only.

   docs: external skill directories

   hand this to your agent: "list every folder on this machine that holds SKILL.md files outside ~/.hermes/skills and tell me which ones are worth adding to skills.external_dirs. change nothing."

   SourcesHermes docs: Skills

7. #68 · /skill-name

   Sep 10, 2026 · Skills & instructions · CLI / Desktop / Gateway

   Hermes Wingtips #68: /skill-name

   you installed a skill, told your agent to use it, and the replies still come back the same.

   every installed skill is also a slash command. /humanizer rewrite this reply in my voice loads the skill for that turn and then runs your request with it. the bare name on its own loads it and the agent asks what you need.

   several skills stack in one message: every leading /skill is loaded, the rest of the line is the instruction.

   for the agent to pick a skill without being told, it reads a short index of every description. a description that opens with when to use the skill gets picked up. one that opens with background does not get that far.

   /humanizer <your request>

   SourcesHermes docs: Skills

8. #64 · AGENTS.override.md

   Sep 6, 2026 · Skills & instructions · CLI / Desktop / Gateway

   Hermes Wingtips #64: AGENTS.override.md

   Show full tip

   when you open Hermes Agent inside a project, it reads the project's AGENTS.md on every turn. that file is where a team keeps its rules: how the code is laid out, what to never touch, which commands to run.

   but what if you want your own rules in that project?

   maybe you prefer shorter answers, or you want the agent to always run the tests before it reports back. editing the shared AGENTS.md pushes your habits onto everyone else.

   this file is the way round it. put an AGENTS.override.md next to the team's AGENTS.md and Hermes loads yours instead of theirs. the tracked file stays exactly as your teammates wrote it.

   touch AGENTS.override.md

   add it to .gitignore and it never leaves your machine. it works in any folder that has an AGENTS.md, including subfolders the agent walks into during a session.

   SourcesHermes docs: Context Files

9. #53 · SOUL.md, AGENTS.md, MEMORY.md, USER.md

   Aug 24, 2026 · Skills & instructions · CLI / Desktop / Gateway

   Hermes Wingtips #53: SOUL.md, AGENTS.md, MEMORY.md, USER.md

   Show full tip

   four markdown files shape your Hermes Agent. what each one does:

   (1) SOUL.md is who your agent is: personality, tone, how it speaks. it exists so your agent stays the same agent everywhere, in every project and on every channel. it lives in ~/.hermes/.

   (2) AGENTS.md is how one project works: structure, conventions, the commands that matter. it exists so project rules stay with the project instead of following your agent around. it lives in the project folder, loads only when your agent works there, and you write one per project.

   (3) MEMORY.md is what your agent has learned by itself: environment facts, conventions it picked up, lessons from past work. it exists so your agent stops rediscovering the same things every session. your agent writes and maintains it, not you.

   (4) USER.md is who you are to your agent: your preferences, your style, how you like your answers. it exists so you never have to introduce yourself twice. your agent maintains this one too.

   the rule of thumb: everywhere means SOUL.md, one project means AGENTS.md, and the memory pair takes care of itself.

   SourcesHermes docs: Context Files

10. #44 · your skills library has an undo button

    Aug 12, 2026 · Skills & instructions · CLI

    Hermes Wingtips #44: your skills library has an undo button.

    the curator is a background pass that tidies the skills your agent creates for itself: stale ones get archived, overlapping ones get merged.

    worried it might archive a skill you cared about? it snapshots your whole skills folder before every pass, automatically.

    hermes curator rollback --list shows every snapshot.

    hermes curator rollback restores the newest one, and even the rollback takes a snapshot first, so you cannot lose anything trying.

    SourcesHermes docs: Curator

11. #35 · hermes bundles

    Jul 30, 2026 · Skills & instructions · CLI / Desktop / Gateway

    Hermes Wingtips #35: hermes bundles

    if you keep loading the same skills together for the same kind of job, group them under one command:

    hermes bundles create <name> --skill <a> --skill <b>

    typing /<name> in the CLI or any chat platform then loads every skill in the bundle at once.

    a bundle is a tiny yaml file under ~/.hermes/skill-bundles/, so you can check it into a dotfiles repo and share a whole task profile with your team.

    super cool for recurring jobs and tasks you perform every day, see below for a quick example :)

    SourcesHermes docs: Skills

12. #5 · /learn

    Jun 24, 2026 · Skills & instructions · CLI / Desktop / Gateway

    Hermes Wingtips #5: /learn

    Show full tip

    it turns a source into a reusable skill in one command.

    four ways to feed it: a local code/docs folder, a doc url, a workflow you just ran, or pasted notes. reach for it once you've done something non-trivial and don't want to re-explain it next time.

    the skill lands in ~/.hermes/skills/ and auto-loads only when a task calls for it, so it's procedural memory that doesn't bloat every prompt.

    I used it today and it drafted a genuinely good skill, even pulling in a real adjacent feature I hadn't mentioned.

    Copy code

    what you need to know: it currently ignores its own <=60-char description rule (mine came out 123 and 202 chars). 
    
    since a skill's description loads every session, a 200-char one is dead weight. open the SKILL.md, tighten it, fix the author, before you rely on it or share it.
    

    SourcesHermes docs: Skills

13. #4 · which file is your agent's brain

    Jun 23, 2026 · Skills & instructions · CLI / Desktop / Gateway

    Hermes Wingtips #4: which file is your agent's brain

    ~ SOUL.md is who the agent is: slot #1 in the system prompt, it replaces the default identity.

    ~ USER.md is who you are.

    ~ MEMORY.md is the facts it keeps about your work.

    ~ AGENTS.md is your project's rules, found by walking the directory.

    Copy code

    what you need to understand is that project rule files are first-match-wins. 
    Hermes loads only one of .hermes.md, AGENTS.md, CLAUDE.md, .cursorrules, in that order. 
    
    a .hermes.md in the repo shadows your AGENTS.md with no warning, and the rules you wrote never load.
    
    SOUL.md is exempt, it always loads on its own from ~/.hermes/SOUL.md. 
    
    if Hermes is ignoring your project instructions, check for a higher-priority file next to them. and it caps every one of these at 20,000 characters, then truncates the rest.
    

    SourcesHermes docs: Context Files