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.
pytorch3 - Skill - OpenSmartRoute
Skillv1.0.0
pytorch3
This is the only AGENTS.md, there are no recursive AGENTS.md - When you are working on a bug, first create a standalone file that reproduces the bug and verify it fails in the expected way. Use this t
Imported from zhengly1/pytorch3 (AGENTS.md). Install upstream with npx skills add zhengly1/pytorch3. Copyright stays with the author.
This is the only AGENTS.md, there are no recursive AGENTS.md
When you are working on a bug, first create a standalone file that
reproduces the bug and verify it fails in the expected way. Use this to
test if your changes work. Once the change is passing, find an appropriate
test file to add the test to and make sure to follow local conventions on
the test file.
If you are running the real test suite, DO NOT run the entire test suite.
Instead run only a single test case, e.g., 'python test/test_torch.py TestTorch.test_dir'
Do NOT run setup.py, you do not have a working build environment
Do NOT run pre-commit, it is not setup
To run lint, run 'lintrunner -a' (which will autoapply changes)
Do NOT attempt to install dependencies, you do not have Internet access
When you are ready to make a PR, do exactly these steps:
git stash -u
git reset --hard $(cat /tmp/orig_work.txt) # NB: reset to the LOCAL branch, do NOT fetch
git stash pop
Resolve conflicts if necessary
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 pytorch3 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.
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
zhengly1-pytorch3-pytorch3.ocm.jsonjson
{
"ocm": "1",
"id": "zhengly1-pytorch3-pytorch3",
"kind": "skill",
"name": "pytorch3",
"description": "This is the only AGENTS.md, there are no recursive AGENTS.md - When you are working on a bug, first create a standalone file that reproduces the bug and verify it fails in the expected way. Use this to test if your changes work. Once the change is passing, find an appropriate test file to add the test to and make sure to follow local conventions on the test file. - If you are running the real test suite, DO NOT run the entire test suite. Instead run only a single test case, e.g., 'python test/test_torch.py TestTorch.test_dir' - Do NOT run setup.py, you do not have a working build environment - Do NOT run pre-commit, it is not setup - To run lint, run 'lintrunner -a' (which will autoapply changes) - Do NOT attempt to install dependencies, you do not have Internet access - When you are ready to make a PR, do exactly these steps: - git stash -u - git reset --hard $(cat /tmp/orig_work.txt) # NB: reset to the LOCAL branch, do NOT fetch - git stash pop - Resolve conflicts if necessary",
"publisher": "zhengly1",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"This is the only AGENTS.md, there are no recursive AGENTS.md - When you are working on a bug, first create a standalone file that reproduces the bug and verify it fails in the expected way. Use this to test if your changes work. Once the change is passing, find an appropriate test file to add the test to and make sure to follow local conventions on the test file. - If you are running the real test suite, DO NOT run the entire test suite. Instead run only a single test case, e.g., 'python test/test_torch.py TestTorch.test_dir' - Do NOT run setup.py, you do not have a working build environment - Do NOT run pre-commit, it is not setup - To run lint, run 'lintrunner -a' (which will autoapply changes) - Do NOT attempt to install dependencies, you do not have Internet access - When you are ready to make a PR, do exactly these steps: - git stash -u - git reset --hard $(cat /tmp/orig_work.txt) # NB: reset to the LOCAL branch, do NOT fetch - git stash pop - Resolve conflicts if necessary"
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/zhengly1/pytorch3",
"path": "AGENTS.md",
"ref": "ad2f7315ca66b42497047bb7951f696b50f1e81b",
"url": "https://github.com/zhengly1/pytorch3/blob/ad2f7315ca66b42497047bb7951f696b50f1e81b/AGENTS.md",
"key": "zhengly1/pytorch3/AGENTS.md"
}
},
"instructions": "- This is the only AGENTS.md, there are no recursive AGENTS.md\n- When you are working on a bug, first create a standalone file that\n reproduces the bug and verify it fails in the expected way. Use this to\n test if your changes work. Once the change is passing, find an appropriate\n test file to add the test to and make sure to follow local conventions on\n the test file.\n- If you are running the real test suite, DO NOT run the entire test suite.\n Instead run only a single test case, e.g., 'python test/test_torch.py TestTorch.test_dir'\n- Do NOT run setup.py, you do not have a working build",
"cost": {
"context_tokens": 253
}
}
Fetch it by URL: GET /api/v1/registry/zhengly1-pytorch3-pytorch3/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.
