Documentation
Everything you need to use the registry — and to publish into it when submissions open.
Getting started
The registry has one primitive: a skill — a documented, versioned capability you can install and pin. Browse the catalog, open a listing, read its README, and install the exact version you want.
$ skillbank search solana $ skillbank show solana-rpc-toolkit $ skillbank install solana-rpc-toolkit@1.0.0
skillbank CLI shown here describes the registry's intended install interface.Using a skill
Every listing page follows the same README shape:
- Overview — what the skill does and doesn't do.
- Installation — the exact pinned install command.
- Configuration — a commented config file with defaults.
- Inputs — a table of every input, its type, and whether it's required.
- Changelog — the full version history, breaking changes flagged.
Read the inputs table before first use; several skills (e.g. ssh-fleet-commander) ship with safety notes you should understand.
Version pinning & semver policy
All skills follow strict semantic versioning. The registry enforces the policy at publish time:
- Major (
2.0.0) — breaking changes: renamed inputs, removed behavior, new required config. Old majors stay installable forever. - Minor (
2.1.0) — backwards-compatible additions: new optional inputs, new features. - Patch (
2.1.1) — bug fixes and maintenance only. No new inputs, no behavior changes.
Pin production to an exact version (solana-rpc-toolkit@1.0.0). Use a minor range (ionos-dns-manager@1) only in development — minor releases add features, and features can surprise you.
Publishing a skill
Submissions are open, and the bar is set. A publishable skill is a single directory:
my-skill/ SKILL.md # frontmatter (name, description, license) + the 5 README sections CHANGELOG.md # every version, newest first LICENSE # MIT or Apache-2.0 scripts/ # executable code (optional) references/ # extra docs, loaded on demand (optional)
The SKILL.md frontmatter pins the name, description, and license; the body carries the five required README sections. The registry validates the package, renders the listing page, and freezes the version — published versions are immutable. The format follows the agentskills.io open specification.
Naming rules
- Lowercase, hyphen-separated:
invoice-parser, notInvoiceParser. - Descriptive of the job, not the model:
email-triage, notgpt-email. - No squatting on generic single words, no trademarks, no misleading prefixes like
official-. - Names are first-come within the registry; disputes go through the takedown process (to be published with the pipeline).
README requirements
A listing is rejected without all five sections:
- Overview — one paragraph, honest scope, explicit non-goals.
- Installation — the pinned install command, in a code block.
- Configuration — a complete config file with every default visible.
- Inputs — a table: name, type, required, description.
- Examples — at least one end-to-end worked example with expected output shape.
MCP server spec notes
Skills flagged MCP map onto Model Context Protocol tool surfaces. If you maintain both a skill and a server:
- Server and skill versions move independently — the directory lists server versions, the catalog lists skill versions.
stdioservers must document every environment variable they read;SSEservers must document their auth scheme.- Tool names on the MCP surface should match the skill's input names where the semantics are identical, so agents can transfer knowledge.
- Destructive tools (write, delete, send) must be marked as such in the server's README and require explicit confirmation by default.
See the server directory for the listing format.