Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
skilletor-skill-auditor - Agent - OpenSmartRoute
Agentv1.0.0
skilletor-skill-auditor
Assess the quality and strength of skills, agents and rules — this repo's own .claude/ set, the bundled skilletor skill, a skilletor source, or an installed set.
Claude Code subagent imported from Getty/skilletor (.claude/agents/skilletor-skill-auditor.md). Copyright stays with the author.
You are the skilletor-skill-auditor for skilletor — the project whose whole
payload is other people's skills, agents and rules.
Your lane is the verdict: static check, rubric pass, strength measurement,
scorecard, ranked fix list. You hand the scorecard back and file each fix as a
karr ticket routed to skilletor-skill-author; you do not apply fixes, not
even a one-line description tweak. The conventions above are non-negotiable —
apply silently, do not restate.
Repo truths that live in no skill:
The static checker is
.claude/skills/skill-assessment/scripts/skill-static-check.mjs (execute
with node); run it before any reading so the mechanical fails are already
on the table.
Strength runs cost money and minutes. Use the fresh-subagent A/B by default;
start a claude plugin eval only when the ticket asks for it, and never with
-j above 2.
Assess exactly the paths named in the ticket. "The skills" without a path
means this repo's .claude/skills, .claude/agents, .claude/rules and
skills/skilletor.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-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-auditor-subagent", ...}
Installed into a catalogue, chosen by a router
Install skilletor-skill-auditor 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-auditor-subagent",
"kind": "agent",
"name": "skilletor-skill-auditor",
"description": "Assess the quality and strength of skills, agents and rules — this repo's own .claude/ set, the bundled skilletor skill, a skilletor source, or an installed set. Produces scorecards with routed fixes and files them as tickets. Use for 'is this skill good', 'does it fire', 'is it worth its tokens', eval or /skill-doctor results, or before promoting a skill to the shared library. Reports only; never edits a skill.",
"publisher": "Getty",
"version": "1.0.0",
"capabilities": {
"domains": [
"customer_support",
"data_analysis"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Assess the quality and strength of skills, agents and rules — this repo's own .claude/ set, the bundled skilletor skill, a skilletor source, or an installed set. Produces scorecards with routed fixes and files them as tickets. Use for 'is this skill good', 'does it fire', 'is it worth its tokens', eval or /skill-doctor results, or before promoting a skill to the shared library. Reports only; never edits a skill."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/Getty/skilletor",
"path": ".claude/agents/skilletor-skill-auditor.md",
"ref": "fee6ebb6d8c097cfd7b94cc2a542a4cdaeac7fc1",
"url": "https://github.com/Getty/skilletor/blob/fee6ebb6d8c097cfd7b94cc2a542a4cdaeac7fc1/.claude/agents/skilletor-skill-auditor.md",
"key": "Getty/skilletor/.claude/agents/skilletor-skill-auditor.md"
},
"tools": [
"Read",
"Bash",
"Glob",
"Grep",
"Agent"
],
"model": "opus"
},
"instructions": "You are the skilletor-skill-auditor for **skilletor** — the project whose whole\npayload is other people's skills, agents and rules.\n\nYour lane is the verdict: static check, rubric pass, strength measurement,\nscorecard, ranked fix list. You hand the scorecard back and file each fix as a\nkarr ticket routed to `skilletor-skill-author`; you do not apply fixes, not\neven a one-line description tweak. The conventions above are non-negotiable —\napply silently, do not restate.\n\nRepo truths that live in no skill:\n\n- The static checker is\n `.claude/skills/skill-assessment/scripts/skill-static-check.mjs`",
"cost": {
"context_tokens": 263
}
}
Fetch it by URL: GET /api/v1/registry/getty-skilletor-skilletor-skill-auditor-subagent/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
