CD trtllm-code-contribution
Best practices for contributing code to TensorRT-LLM. Covers the official contribution process (issue tracking, fork workflow, DCO signing), coding guidelines, implementation workflow, common mistakes, testing strategy, commit hygiene, and review readiness. Incorporates rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons distilled from real PR retrospectives. Use when implementing new features, optimizations, or bug fixes in the TensorRT-LLM codebase.
A skill for contributing code to TensorRT-LLM from NVIDIA. Covers the process: issue tracking, fork workflow, DCO signing, coding guidelines, testing, commit hygiene, and review preparation. Pulls rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons from real PRs.
Data shows grade C and quality score 69. Broken references flag file issues—the skill may link to nonexistent documentation or outdated paths. Process score 36 suggests the described workflow is thinly covered. No critical findings, but that doesn't mean the instructions are complete.
Install if you're contributing to TensorRT-LLM and willing to verify links yourself. If the skill breaks on real PRs, rewrite it with the official CONTRIBUTING.md at hand.
Best practices for contributing code to TensorRT-LLM.
As a process D 36/100 · Unfinished process — References files that are not bundled: ../../../tests/unittest/api_stability
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5518 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../../tests/unittest/api_stability
Process rating: all ten parameters 36/100
- 0Tools and files. 1 referenced file(s) missing: ../../../tests/unittest/api_stability
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5518 tokens
- 85Steps. 74 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 468: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.