install-skills
Skill32 starsChanged 25 days agoMITView on GitHub
Install skills of the ai-maxxing package on the user's VPS so their Hermes agent (and Claude Code on the server) can use them - connect-tool, create-landing, create-software, verify, grill-me, lumail, stripe-checkout and more. Shows what can go on the server, lets the user pick, installs and checks. Use after setup-vps, when the user wants Hermes to have more skills or asks how to give it one.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- alo-exp/silver-bullettheir own version, first seen Nov 1, 2026
- AndrewBrown-USDA/aigb-skills-usdatheir own version, first seen Oct 31, 2026
- trapple/skillstheir own version, first seen Jul 21, 2026
- Lukasedv/skillstheir own version, first seen Jan 24, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Lukasedv/skills★ 21same name
- alo-exp/silver-bullet★ 7same name
- AndrewBrown-USDA/aigb-skills-usda★ 7same name
- trapple/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- skills/setup-my-hermes-dashboard/template/AGENTS.mdAGENTS.md
- audit-safetySkill
- betterSkill
- cleanupSkill
- create-projectSkill
- doneSkill
- dreamSkill
- projectsSkill
- setup-brainSkill
- cloudflareSkill
- code-debugSkill
- codex-imagesSkill
- connect-googleSkill
- connect-instagram-developer-platformSkill
- connect-toolSkill
- connect-vpsSkill
- connect-youtube-developer-platformSkill
- convexSkill
- create-internal-appSkill
- create-landingSkill
- create-softwareSkill
- dev-browserSkill
- grill-meSkill
- initializeSkill
- lumailSkill
- safe-shipSkill
- setup-cloudflareSkill
- setup-convexSkill
- setup-dev-browserSkill
- setup-githubSkill
- setup-lumailSkill
- dashboardSkill
- setup-my-hermes-dashboardSkill
- setup-nodeSkill
- setup-stripeSkill
- setup-vpsSkill
- show-meSkill
- skill-managerSkill
- stripe-checkoutSkill
- use-styleSkill
- verifySkill
- wait-whatSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Run every remote command as ssh hermes '<command>' < /dev/null.
- Very specific: line 12
Check what is ready: ssh -o BatchMode=yes hermes true (otherwise run connect-vps), then ssh hermes 'hermes-setup check' lists hermes and …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Give the user's Hermes agent the skills they pick from the ai-maxxing package. They land in ~/.agents/skills on the server, the folder Hermes reads (Claude Code there reads it through ~/.claude/skills). The arguments are skill names (none: let the user choose) and the alias (default hermes; use it everywhere below). Talk to the user in their language, short messages, no jargon (say "your agent", "the server", never "symlink", "gateway" or "frontmatter").
Run every remote command as ssh hermes '<command>' < /dev/null.
- Check what is ready:
ssh -o BatchMode=yes hermes true(otherwise runconnect-vps), thenssh hermes 'hermes-setup check'lists hermes and gateway as ok and itsskills=line hasai-maxxing-skills(otherwise runsetup-vps, or only its steps 2 and 10 when Hermes already works). - Show the catalog:
ssh hermes 'hermes-setup catalog'. It updates the package on the server and prints one line per skill that works there:installed,available, orown(the user's own skill under that name, never replaced). Skills that need their computer (connect-vps, everysetup-*,dev-browser) are not in it. - Unless they named skills, ask which to install and recommend the default pack of Hermes, the lines marked
base(the list and why each one is in it: ../setup-vps/hermes-pack): the server's tool skills,create-dashboard(Hermes puts their personal dashboard online, then builds its modules),connect-tool(connect any tool, Notion, Stripe, a CRM...) andcreate-internal-app(private apps on the server). Most of the kit is made for Claude Code on their computer: add more only when they want Hermes to do that job too, for examplecreate-landingorcreate-softwareto build sites,lumailfor their emails. Show the otheravailableones in one short list with what each lets them ask Hermes. They answer "the default pack", "all", or names, or a mix. - Install:
ssh hermes 'hermes-setup add <base|all|skill>...', for exampleadd base lumail. Each line saysinstalled=,kept=(their own skill, left as it is) orskipped=(needs their computer). Exit code 4 names a skill that is not in the package: check the spelling against the catalog. Hermes picks them up on its own, no restart. - Prove it:
ssh hermes 'hermes skills list'lists each new skill aslocal, andssh hermes 'hermes -z "Which skills do you have from ~/.agents/skills? Names only." < /dev/null'names them.
End with one line per skill, a check or a cross. Then tell the user in 3 lines: from now on they can simply message Hermes on Telegram or Discord "install the default pack", "install the connect-tool skill", "which skills can you install?", "update your skills" or "remove create-landing" (it has the ai-maxxing-skills skill for that); a new skill is ready from their next conversation (/new in the chat starts one); and their own skills are never touched.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

