Deploying AI agents for clients is a job now.
This is its toolkit.
A skill is a set of instructions your AI agent (Claude Code, Codex, Cursor…) installs and then uses. Find one here, give your agent one line, and it is installed. Free skills need no account.
What are your agents missing? One command checks the skills on your machine (Claude, Codex, Hermes, OpenCode) and compares them with the catalog.62
curated skills hosted here — free, versioned, SHA-256 checksummed
105,000+
skills indexed across federated registries — linked as-is, not vetted by us
Open source (MPL-2.0) · Free tier · Self-host the whole thing · Cancel anytime
How it works · pick a step
You have an agent. Give it skills.
Starting costs nothing. Add LoopSkill to your agent once; after that it can search for skills and install them from inside its own chat.
Step A · add LoopSkill to your agent
Paste this into your agent's chat (Claude Code, Codex, Cursor…) and press Enter:
Install the loopskill skill from https://app.loopskill.io/skill Free skills install with no account and no key. You need a free API key only for the MCP tools, saving to your Library, private bundles and fleets.
Step-by-step for your agentOptional · see the skills you already have
The free loopskill command-line tool lists the
skills in ~/.claude, ~/.codex,
~/.cursor and ~/.hermes.
loopskill import and
loopskill diff show how two machines differ.
They make zero network calls and need no account.
pip install loopskill) What you get on day one
- · One search over the curated catalog and 105,000+ skills indexed across federated registries — linked as-is, not vetted by us, never rehosted.
- · Skills that ship a runnable loop: press run, get a real pass/fail result, within fixed limits. Not a model's opinion.
- · Nothing to undo later. Everything below is the same platform.
Hand them one line. Keep your name on it.
A bundle is the unit of client work: the skills that client's agent should have, pinned at exact versions. You edit the bundle; their agent pulls. There is no push — the control plane cannot reach into a client machine, which is precisely why a client will let you near theirs.
-
step 01
Compose the bundle
Pick skills, pin versions, name it after the client. Or fork someone else's public stack and start from a working set instead of a blank page — preview the diff before you claim it. Compose one →
-
step 02
Scope a key to that bundle, and nothing else
A bundle-scoped key (
cbt_…) reaches exactly one bundle. If a client leaks it, they leak that bundle — not your catalog, not another client. Key scopes → -
step 03
Send the install line
One line, branded-neutral, key already baked in. Their agent installs and then reconciles on its own schedule — no dashboard for them to babysit, no LoopSkill branding on their side. Delivery guide →
Fork one of these instead of starting empty
All bundles →Before you run someone else's code on a client's machine
- · Skills can run in an ephemeral, syscall-audited sandbox with a network allowlist.
- · Anonymous contributions land as drafts and need a human reviewer before promotion.
- · Packs are content-addressed: the same source rebuilds byte-identical, sha256 verifiable.
Your second client is where it breaks.
One client, one agent — easy. Two clients, five agents, and nobody knows which version of which skill runs where. A bundle lock is an immutable revision; every agent reports a three-way verdict against it — declared vs installed vs extras. Drive the matrix below.
| agent | code-review declares 1.0.0 | copywriting declares 1.0.0 | brand-rollout-meta-repo declares 1.0.0 | Super Memory declares 1.0.2 | plan-for-goal declares 1.0.1 | action |
|---|---|---|---|---|---|---|
| acme-prod-01 | ||||||
| acme-prod-02 | ||||||
| northwind-01 | ||||||
| northwind-02 | ||||||
| solo-laptop |
Hover, focus or click any cell to inspect it — or hit Converge on a drifted row.
·
- declared
- installed
- extras
The state above is simulated so you can drive it without an account. The skills named are real catalog entries — click one. Your own matrix lives behind sign-in: Your Library → Fleets · how locks and the three-way verdict work. Known gap, stated rather than hidden: an assignment that has never run once still reads healthy at the top level — see what LoopSkill does and does not do.
Immutable lock revisions
Edit a bundle and a new revision is minted. Every agent's verdict is computed against a specific revision, so "which version did they actually get" has an answer, not a guess.
Agents register themselves
An agent proves possession of an Ed25519 key and registers itself. No OAuth screen, no session, no human clicking through a console on a client's laptop. How →
Agents pull updates; nothing is pushed
Nothing is pushed to a client machine and nothing is real-time — an agent checks for updates on the schedule you install. That is a security property, and we would rather state the interval than call it "instant".
Run a Fleet — the learning track for this step
A multi-agent setup with shared memory, loop-safe Discord coordination, and per-client reporting.
Open the trackThe runbook you already wrote is the product.
Three ways the work you're already doing turns into revenue — none of them require you to stop doing client work.
01 · publish
Turn a workflow into a skill
Describe the runbook in plain language and one call scaffolds a SKILL.md draft. It goes through a quality gate and a human review before it's listed — the same gate everyone else's does.
Creator workflow02 · refer
50% recurring, then 30%
Refer a Pro subscriber and earn 50% of every invoice they pay for your first 50 referrals, 30% after — monthly, for as long as they stay. Paid out via Stripe Connect.
Referral terms03 · hand it off
Or don't run it yourself
If a client wants the outcome and not the operations, WiseChef runs the same stack as a managed service. Same skills, someone else's pager.
Publish or get helpWhat it costs to run this
The whole platform is MPL-2.0 — clone it, docker compose up, run
it on your own hardware with no LoopSkill account and nothing phoning home. Hosted Free gives you
2 private bundles and 1 API key; Pro raises that to 50 and 10.
See the ladder →
Popular skills
Browse all skills →code-review
Code-review · 8 installs
copywriting
110 installs
brand-rollout-meta-repo
Ops · 10 installs
Super Memory
Automation · 264 installs
plan-for-goal
Ops · 14 installs
multi-agent-discord-coordination
Ops · 7 installs
clean-architecture
Ops · 9 installs
humanizer
70 installs
ruthless-mentor
Ops · 13 installs
loopskill
Marketing · 17 installs
local-tts-kokoro
Marketing · 7 installs
domain-driven-design
Ops · 9 installs
What fills the bundles
A small curated core, inside a very large index.
The curated catalog is deliberately small. Each skill is reviewed before it is listed, delivered with a SHA-256 checksum, and shows its own audit status on its page. Around it sits a federated index of skills from other registries: we link to those as-is — we do not vet or rehost them, and we never count them as ours.
62
curated skills hosted here
Curated hosted skills pass an automated quality check before listing. Delivery is SHA-256-checksummed and version-pinned in bundles. A security audit is not done for every skill yet — each skill page shows its own audit status.
105,000+
skills indexed across federated registries
Linked as-is, not vetted by us. One search across upstream registries, with a per-source breakdown of what is indexed and what is actually installable.
MCP server index
Discovered servers are staged behind a human review gate. Staging is not publishing — read what is and is not shipped.
Works with every
major AI agent
Before you use this for a client
We publish what this does not do.
You are about to put this between you and someone who pays you. A marketing page that only lists wins is not enough information to make that call, so there is a page that lists the gaps — known blind spots, half-shipped surfaces, and the exact probe behind every "verified" claim.
Example: the never-run blind spot
The fleet view shows which assignments are up to date and which are failing. It does not yet age a never-run assignment into an alarm — a loop assigned and never fired looks healthy at the top level. That is on the scope page, not buried in a changelog.
Every number on this page is live
The counts above are fetched from public endpoints when this page is built, and any stat that cannot be fetched is omitted rather than guessed. Check them yourself: the API reference lists the endpoints they come from.