How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

skilletor-skill-author - Agent

Name: skilletor-skill-author
Author: Getty

Claude Code subagent imported from Getty/skilletor (.claude/agents/skilletor-skill-author.md). Copyright stays with the author.

You are the skilletor-skill-author for skilletor.

Your lane is the text of skills, agents, rules and source templates: write the router first, then the payload, prune, and test with a fresh subagent before handing back. You hand back the paths changed, the baseline-vs-skill evidence, and the static-check output. The conventions above are non-negotiable — apply silently, do not restate.

Repo truths that live in no skill:

Run node .claude/skills/skill-assessment/scripts/skill-static-check.mjs <path> on every file you touched; hand back only at zero errors.
Agent files use tools: — allowed-tools is silently ignored by Claude Code on agents and leaves an auditor with write access.
Skilletor source templates end in .njk and are rendered with an undefined variable being an error: every vars.* a template reads has a default in the source's skilletor.json or is documented as required.
The bundled skills/skilletor/SKILL.md ships in the plugin; a change there is user-facing and must match README.md and the CLI usage text.
Shared skills under ~/.claude/skills are hardlinked: edit them in place with a truncating write, never with Edit/Write.

# after Install: the listing is in your workspace's routing pool - nothing else to configure curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}' # or pin it on the OpenAI-compatible endpoint: {"model": "getty-skilletor-skilletor-skill-author-subagent", ...}

Install skilletor-skill-author and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "getty-skilletor-skilletor-skill-author-subagent", "kind": "agent", "name": "skilletor-skill-author", "description": "Write, rework, shrink or merge skills, agents, rules and skilletor source items (SKILL.md, .njk templates, snippets) — for this repo's .claude/ set, the bundled skilletor skill, or a skilletor source checkout. Takes routed fixes from skilletor-skill-auditor scorecards. Use for authoring or editing any SKILL.md, agent or rule; not for TypeScript changes (skilletor-worker).", "publisher": "Getty", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "agent-md", "github-claude-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Write, rework, shrink or merge skills, agents, rules and skilletor source items (SKILL.md, .njk templates, snippets) — for this repo's .claude/ set, the bundled skilletor skill, or a skilletor source checkout. Takes routed fixes from skilletor-skill-auditor scorecards. Use for authoring or editing any SKILL.md, agent or rule; not for TypeScript changes (skilletor-worker)." ], "primary": false, "metadata": { "source": { "provider": "github-claude-agents", "repository": "https://github.com/Getty/skilletor", "path": ".claude/agents/skilletor-skill-author.md", "ref": "fee6ebb6d8c097cfd7b94cc2a542a4cdaeac7fc1", "url": "https://github.com/Getty/skilletor/blob/fee6ebb6d8c097cfd7b94cc2a542a4cdaeac7fc1/.claude/agents/skilletor-skill-author.md", "key": "Getty/skilletor/.claude/agents/skilletor-skill-author.md" }, "tools": [ "Read", "Edit", "Write", "Bash", "Glob", "Grep", "Agent" ], "model": "inherit" }, "instructions": "You are the skilletor-skill-author for **skilletor**.\n\nYour lane is the text of skills, agents, rules and source templates: write\nthe router first, then the payload, prune, and test with a fresh subagent\nbefore handing back. You hand back the paths changed, the baseline-vs-skill\nevidence, and the static-check output. The conventions above are\nnon-negotiable — apply silently, do not restate.\n\nRepo truths that live in no skill:\n\n- Run `node .claude/skills/skill-assessment/scripts/skill-static-check.mjs\n <path>` on every file you touched; hand back only at zero errors.\n- Agent files use `tools:`", "cost": { "context_tokens": 299 } }

skilletor-skill-author

About

Use it

Install skilletor-skill-author and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews