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.
investigate - Skill - OpenSmartRoute
Skillv1.0.0
investigate
Diagnose a bug or behavior without writing code changes.
Imported from wcoreiron-rgb/regentclaw (.agents/skills/investigate/SKILL.md). Install upstream with npx skills add wcoreiron-rgb/regentclaw --skill investigate. Copyright stays with the author.
Reproduce or restate the issue with exact route/module context.
Identify likely code paths and inspect only relevant files first.
Output:
observed behavior
root-cause hypothesis
confidence level
validation plan
Do not implement fixes in this skill.
Flag security or tenant-isolation risk immediately if present.
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 slot
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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
wcoreiron-rgb-regentclaw-investigate.ocm.jsonjson
{
"ocm": "1",
"id": "wcoreiron-rgb-regentclaw-investigate",
"kind": "skill",
"name": "investigate",
"description": "Diagnose a bug or behavior without writing code changes.",
"publisher": "wcoreiron-rgb",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Diagnose a bug or behavior without writing code changes."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/wcoreiron-rgb/regentclaw",
"path": ".agents/skills/investigate/SKILL.md",
"ref": "fc46b0b87e8bc745da9321c918fa3ee16e3d0c08",
"url": "https://github.com/wcoreiron-rgb/regentclaw/blob/fc46b0b87e8bc745da9321c918fa3ee16e3d0c08/.agents/skills/investigate/SKILL.md",
"key": "wcoreiron-rgb/regentclaw/.agents/skills/investigate/SKILL.md"
}
},
"instructions": "1. Reproduce or restate the issue with exact route/module context.\n2. Identify likely code paths and inspect only relevant files first.\n3. Output:\n - observed behavior\n - root-cause hypothesis\n - confidence level\n - validation plan\n4. Do not implement fixes in this skill.\n5. Flag security or tenant-isolation risk immediately if present.",
"cost": {
"context_tokens": 86
}
}
Fetch it by URL: GET /api/v1/registry/wcoreiron-rgb-regentclaw-investigate/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.
