trtmc-agent-skills
v0.1.0Repo-local Codex skills for TensorRT-Model-Connect developer workflows.
273 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Codex
- Parsed components
- 12 skill or MCP entries
- Source updated
- Oct 8, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install trtmc-agent-skills for Codex
codex plugin marketplace add NVIDIA/TensorRT-Model-Connect
codex plugin marketplace upgrade trtmc-agent-skills
codex plugin add trtmc-agent-skills@trtmc-agent-skillsPaste and run these commands in a terminal with Codex. They add and refresh the trtmc-agent-skills catalog, then install this plugin.
Compatibility: the page URL and API slug “trtmc-agent-skills” remain stable.
- Codex:
trtmc-agent-skills@agent-plugin-marketplace→trtmc-agent-skills@trtmc-agent-skills
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/NVIDIA/TensorRT-Model-ConnectClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/trtmc-agent-skills/.
Plugin files
├── .codex-plugin/plugin.json├── skills/debug-trt-mismatch/SKILL.md├── skills/doc-sync/SKILL.md├── skills/fp16-trt-network/SKILL.md├── skills/optimize-model-precision/SKILL.md├── skills/pr-babysitter/SKILL.md├── skills/profile-model/SKILL.md├── skills/review-trtmc-pr/SKILL.md├── skills/setup-trtmc-environment/SKILL.md├── skills/submit-github-bug-issue/SKILL.md├── skills/submit-github-pr/SKILL.md├── skills/transform-model/SKILL.md└── skills/write-git-messages/SKILL.md
Included Skills12
Diagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.
Audit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.
Implement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.
Evaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.
Use when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.
Measure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.
Review a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, and exact-head validation evidence. Use for contributor self-review before marking a PR ready, or when deciding whether a community PR is compliant, decoupled, merge-ready, or needs maintainer feedback. The review is read-only unless the user separately asks to publish it or change the contribution.
Prepare a TensorRT-Model-Connect development or validation environment from a fresh checkout on a host without a known working setup.
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the bug label, and verifying the created issue.
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.
Add a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.
Draft, revise, or review Git commit messages, PR titles, PR descriptions, and squash or rebase merge messages. Use when Codex needs to summarize a diff for reviewers, convert rough notes into a commit or PR message, check a message against Git and Conventional Commits style, or prepare repository contribution text before pushing/opening a PR.
Plugin manifests1
{
"name": "trtmc-agent-skills",
"version": "0.1.0",
"description": "Repo-local Codex skills for TensorRT-Model-Connect developer workflows.",
"repository": "https://github.com/NVIDIA/TensorRT-Model-Connect",
"keywords": [
"codex",
"skills",
"git",
"github",
"pull-requests",
"developer-workflow",
"tensorrt",
"model-development",
"profiling",
"documentation"
],
"skills": "./skills/",
"interface": {
"displayName": "TensorRT-Model-Connect Skills",
"shortDescription": "Repo skills for models, docs, profiling, and GitHub",
"longDescription": "Installs concise TensorRT-Model-Connect skills for family development, precision, debugging, profiling, documentation, environment setup, and GitHub workflows.",
"developerName": "NVIDIA",
"category": "Development",
"capabilities": [
"Interactive",
"Write"
],
"defaultPrompt": [
"Use $write-git-messages to draft a PR message from my diff.",
"Use $review-trtmc-pr to self-review my branch before marking its PR ready.",
"Use $submit-github-pr to push this branch and open a PR.",
"Use $transform-model to add this checkpoint as one self-contained family.",
"Use $debug-trt-mismatch to locate this family's first output divergence.",
"Use $profile-model to measure this model through its public Task API.",
"Use $setup-trtmc-environment to prepare this checkout for one family."
],
"brandColor": "#76B900"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[trtmc-agent-skills on Agent Plugins Marketplace](https://pluginsmp.com/plugins/trtmc-agent-skills)