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.
fast-fix - Skill - OpenSmartRoute
Skillv1.0.0
fast-fix
Fast fix without deeping dive into details. Use only when explicitly invoked.
Imported from zolotarevandrew/neuralnetworks (agents/skills/fast-fix/SKILL.md). Install upstream with npx skills add zolotarevandrew/neuralnetworks --skill fast-fix. Copyright stays with the author.
Code Review
Invocation
Use only when explicitly invoked:
/fast-fix
`$fast-fix
"run fast-fix"
Do not auto-run for coding, refactoring, debugging, or explanations.
Goal
You goal is to fix/find the solution for the problem as fast as possible, when user will give you a error/code block.
Focus on:
fix as fast as possible;
answer less than 30 seconds 1 minute;
do not autorun thinking modes;
Should work like a google query, which autoanalyzes the input and suggests a fast fix.
Constraints
Do not run tests
Do not use other files from project of folder!
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 - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install fast-fix and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "zolotarevandrew-neuralnetworks-fast-fix",
"kind": "skill",
"name": "fast-fix",
"description": "Fast fix without deeping dive into details. Use only when explicitly invoked.",
"publisher": "zolotarevandrew",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"data_analysis"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Fast fix without deeping dive into details. Use only when explicitly invoked."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/zolotarevandrew/neuralnetworks",
"path": "agents/skills/fast-fix/SKILL.md",
"ref": "40fa3aacda0043a0990d244b6fb4286d322e5d78",
"url": "https://github.com/zolotarevandrew/neuralnetworks/blob/40fa3aacda0043a0990d244b6fb4286d322e5d78/agents/skills/fast-fix/SKILL.md",
"key": "zolotarevandrew/neuralnetworks/agents/skills/fast-fix/SKILL.md"
}
},
"instructions": "# Code Review\n\n## Invocation\n\nUse only when explicitly invoked:\n- `/fast-fix`\n- `$fast-fix\n- \"run fast-fix\"\n\nDo not auto-run for coding, refactoring, debugging, or explanations.\n\n## Goal\n\nYou goal is to fix/find the solution for the problem as fast as possible, when user will give you a error/code block.\n\nFocus on:\n- fix as fast as possible;\n- answer less than 30 seconds 1 minute;\n- do not autorun thinking modes;\n\nShould work like a google query, which autoanalyzes the input and suggests a fast fix.\n\n\n## Constraints\n- Do not run tests\n- Do not use other files from project of folder!",
"cost": {
"context_tokens": 147
}
}
Fetch it by URL: GET /api/v1/registry/zolotarevandrew-neuralnetworks-fast-fix/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.