agentleFS
NVIDIAKnown publisherNVIDIA/TensorRT-Model-Connect/plugins/trtmc-agent-skills/skills/transform-model/SKILL.md

transform-model

Skill290 starsChanged 45 days agoApache-2.0View on GitHub

Add a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep model behavior inside the owner even when another family looks similar.

    line 32
  2. Distinctive:

    Do not modify core merely to reduce duplicated lines.

    line 33
  3. Distinctive:

    Do not weaken the family oracle or add configuration for an unrequested future case.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Transform a Model

Define the checkpoint, revision, task, target hardware, requested precision, and required evidence. Read the upstream config and reference implementation, then inspect the closest family only as a pattern.

Extend an owner only when checkpoint identity, weight mapping, graph dataflow, native request lifecycle, and correctness contract genuinely match. Otherwise create one new families/<family>/ directory.

Implement one vertical slice

  • support.py recognizes exact model metadata and declares supported tasks plus one meaningful default. Zero or multiple owners are errors.
  • model.py exposes one plain build(request, writer) function. It owns model config, weights, TensorRT graphs, precision, parallelism, and bundle section semantics. It must not inherit a builder or import another family.
  • runtime/CMakeLists.txt builds trtmc_model_<family>. The family factory and pipeline implement the required abstract interface from trtmc/task.h and drive engines through the public backend contract.
  • requirements.txt contains only optional packages needed by this family.
  • tests/ owns direct build/runtime E2E, manifests, thresholds, fixtures, and focused Python or C++ tests.

Keep model behavior inside the owner even when another family looks similar. Do not modify core merely to reduce duplicated lines. If the requested user behavior cannot be expressed by an existing Task interface, stop and describe the required shared contract before expanding scope.

Prove the smallest real path

First make one exact testcase work end to end:

checkpoint -> support resolution -> family build -> bundle
           -> family DSO -> abstract Task API -> real output

Then run repository ownership checks and the selected family tests:

PYTHONPATH=core/builder:apps/benchmark:. python3 -m tools.model_ci validate
PYTHONPATH=core/builder:apps/benchmark:. python3 -m pytest \
  families/<family>/tests --e2e-model <family> -q
git diff --check

Do not weaken the family oracle or add configuration for an unrequested future case. Report the exact checkpoint, commands, results, hardware, and checks not run before claiming support.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.