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.
read-through-codebase - Skill - OpenSmartRoute
Skillv1.0.0
read-through-codebase
Create a comprehensive understanding of the codebase overview and functionality by reading through the codebase. Use when `docs/ai/*` does not exist.
Imported from xcc-zach/prompt-to-ai (src/assets/skills/read-through-codebase/SKILL.md). Install upstream with npx skills add xcc-zach/prompt-to-ai --skill read-through-codebase. Copyright stays with the author.
Research the codebase comprehensively. Write to the following files under project's .aidocs/ directory (create if not exists; If the documents below already exist, skip writing and directy output a message indicating their existence):
codebase-overview.md: Refer to instructions/codebase-overview.md for instructions.
After creating the above files, commit with ai-docs-commit skill with arguments "add docs after reading through codebase".
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}'
Installed into a catalogue, chosen by a router
Install read-through-codebase 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": "xcc-zach-prompt-to-ai-read-through-codebase",
"kind": "skill",
"name": "read-through-codebase",
"description": "Create a comprehensive understanding of the codebase overview and functionality by reading through the codebase. Use when `docs/ai/*` does not exist.",
"publisher": "xcc-zach",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Create a comprehensive understanding of the codebase overview and functionality by reading through the codebase. Use when `docs/ai/*` does not exist."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/xcc-zach/prompt-to-ai",
"path": "src/assets/skills/read-through-codebase/SKILL.md",
"ref": "8967a4157158b893dbfb63ea87ff402c8ccadec3",
"url": "https://github.com/xcc-zach/prompt-to-ai/blob/8967a4157158b893dbfb63ea87ff402c8ccadec3/src/assets/skills/read-through-codebase/SKILL.md",
"key": "xcc-zach/prompt-to-ai/src/assets/skills/read-through-codebase/SKILL.md"
}
},
"instructions": "Research the codebase comprehensively. Write to the following files under project's `.aidocs/` directory (create if not exists; If the documents below already exist, skip writing and directy output a message indicating their existence):\n- `codebase-overview.md`: Refer to `instructions/codebase-overview.md` for instructions.\n\nAfter creating the above files, commit with `ai-docs-commit` skill with arguments \"add docs after reading through codebase\".",
"cost": {
"context_tokens": 112
}
}
Fetch it by URL: GET /api/v1/registry/xcc-zach-prompt-to-ai-read-through-codebase/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.
