MIT · agent skills

◈ You are in The Armory — What will you teach it?

Skills your agent can actually run

Operational glue extracted from a real fleet: recovery routines, deploy helpers and secret-safety checks — packaged as skills an agent can load on demand.

Get started View source

bash

# clone the pack
git clone https://github.com/Aitherium/aither-skills.git

# skills are plain markdown — point your agent at them
ls aither-skills/skills/

55skills

MITlicense

0dependencies

Anyagent

Read the pack before you run it

Every skill in the distribution, with its own one-line summary. These are procedures written from incidents on a real fleet — open one and read it before you let an agent act on it in your environment.

skills/55 of 55

search

adversarial-verificationstop grading your own homeworkadversarial-verification agent-disk-hygieneyour coding agents are quietly eating your diskagent-disk-hygiene agent-integrationsaither talks to everything, everything talks to aitheragent-integrations aither-adkrun your own AI agent, on your machine, in three commandsaither-adk aither-agent-notebookturn "build X" into a reviewable, re-runnable planaither-agent-notebook aither-code-intelligencestand up agent code-search, and prove it actually worksaither-code-intelligence aither-codegrapha call-graph-aware code index your agents can queryaither-codegraph aither-headroomcut agent token cost with reversible context compressionaither-headroom aither-powered-codingmake any coding agent use AitherOS as its brainaither-powered-coding aither-prospectora semantic file-explorer that tells agents WHERE to lookaither-prospector aither-startyou have a computer and an AI agent; let's make it yoursaither-start aitherconnectwire your machine, agent, and browser into AitherOSaitherconnect aithermeshstand up a private mesh and onboard nodes + agents to itaithermesh aithernodeturn a machine's hardware into something your agents can useaithernode aitherzeroprovision any machine from one config fileaitherzero bonsai-27brun a 27B model in ~3.8 GB on a plain CPU boxbonsai-27b claude-model-switcherkeep coding when Claude hits limitsclaude-model-switcher Code Like Davidan operating doctrine you can installcode-like-david Compare two commitscompare-versions Concurrent-safe gitconcurrent-safe-git Debt Ledgerdebt-ledger deer-flowa long-running research/coding harness you host yourselfdeer-flow Check outdated packagesdependencies docker-network-opsdiagnose container DNS and networking without fooling yourselfdocker-network-ops docker-wsl2-build-safetystop bulk builds from killing Docker Desktop (and don't blame the disk)docker-wsl2-build-safety docker-wsl2-disk-reclaimyour drive is full and `docker system df` is lying to youdocker-wsl2-disk-reclaim event-loop-debuggerevent-loop-debugger Fail-Closed Authz Reviewfail-closed-authz gpu-vram-attributionwhen the platform cannot tell you who is using the GPUgpu-vram-attribution or directly: adk ingest ./docs --agent research --chunk-size 1500 --chunk-overlap 200graph-a-repo graph-rag-agentbuild a knowledge graph and an agent that owns itgraph-rag-agent hermes-agentNous Research's self-improving agent, on your hardwarehermes-agent hetzner-fleetprovision bare metal and VPS directly into your mesh from Hetzner Cloudhetzner-fleet install-skillsput these skills inside your agentinstall-skills local-inferencea model on your box, for $0local-inference moat-guardmoat-guard model-quantizationmodel-quantization odsturn a box you already own into a private AI serverods omninode-nodejoin the OmniNode P2P inference mesh in one commandomninode-node openclawa personal assistant that runs on your machineopenclaw Profile CPU usageperformance pooled-inferencerun a model no single box can hold, across every tier you ownpooled-inference Prove It Liveprove-it-live Ramble-Driven Developmentramble-driven-development recover-dockerrecover-docker Beforerefactor repo-is-not-a-runtimethe architecture doctrine for agent-driven reposrepo-is-not-a-runtime repo-to-websiterepo-to-website resume-allresume-all secretguardsecretguard VULNERABLEsecurity-audit ship-an-app-freeidea → public URL, $0, no server to rentship-an-app-free split-inferencesplit-inference taua minimalist terminal coding agent you can actually readtau website-as-codewebsite-as-code

What is in the pack

Each skill is a single markdown file describing a procedure precisely enough for an agent to execute it.

format

Plain markdown

No runtime, no framework, no build. A skill is a file — readable by a human and loadable by any agent that can read text.

recovery

Recovery routines

Procedures for getting wedged infrastructure back, written from incidents rather than from imagination.

deploy

Deploy helpers

The deploy-time checks and sequences that keep a change from being declared live before it actually is.

safety

Secret safety

Guardrails for handling credentials — what never goes in a commit, a log, or a tool argument.

portable

Agent-agnostic

Nothing here binds to one vendor's skill format; the content is the product.

free

MIT licensed

Free to use, fork and adapt, including commercially.

Quick start

Clone the pack and point your agent's skill loader at the skills directory.

bash

git clone https://github.com/Aitherium/aither-skills.git
cd aither-skills

# browse what is available
ls skills/

# for Claude Code, copy into your skills directory
cp skills/*.md ~/.claude/skills/

These are procedures, not scripts. Read a skill before letting an agent act on it in your environment — they encode how this fleet is operated, and your topology may differ.

One estate, six doors

These projects are organs of the same system — the same identity plane, the same agent runtime, the same operational discipline. Follow any of them.

the osaitherium.comThe Living OS these four repos are cut from. Open, no login.pythonAither ADKBuild agent fleets. Any backend, effort-routed, real memory.markdownaither-skillsOperational procedures an agent can load and run. MIT.cudaaither-kvcacheSub-byte KV cache compression for LLM inference.powershellAitherZeroNumbered, discoverable automation and declarative playbooks.writingThe BlogHow all of it is actually built, measured and operated.