Use this skill when reviewing TensorRT or TensorRT-LLM deployment artifacts statically - ONNX/PyTorch export pipelines, precision selection (FP16/BF16/INT8/FP8/INT4), calibration cache integrity, dynamic shape profiles, custom plugin loading, engine cache and serialized engine provenance, runtime memory pool sizing. Trigger when the user asks whether a TensorRT build script, calibration pipeline, or trtexec invocation follows NVIDIA's published guidance.
◌ Vettd does not install assets; this record describes a copy you obtain yourself.
Custody chainSource ↗○ linked, not verified by Vettd
github: TechTide○→techtideohio/techtide-harness-kit○→v0.1.0 = 31f8699◐→sha256:432f…5c0f◐→signature △ not assessed|Apache-2.0○record 358fd32e-0b63-41e8-9a00-5f19e5eeee79 · live
◌ public recordYou are signed out, so you see the record and nothing else. sign in
▲Skill does not specify a licenseflaggedSKILL.md — Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.cisco · scan · 2wInfo
◌Secrets scan passednothing foundNo secrets or unsafe code patterns were detected.vettd · scan · 2wnothing found
◌behavioral scan passednothing foundNo prompt-injection or jailbreak signals were detected.vettd · scan · 2wnothing found
◌External URL scan passednothing foundNo external URLs were found in scanned skill text.vettd · scan · 2wnothing found
◌Name validation passednothing foundThe declared skill name follows the supported naming rules.vettd · scan · 2wnothing found
Not assessed; no producer has emitted into cost for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
assessed2w ago · Cisco AI Defense · Vettd core● current
source stateThe source matches what was scanned. No changes detected.Up to date
re-check policyre-checked against the upstream source on the scheduler's cadencenext check in 24h
re-run whena new release ships, the upstream source changes, or the scanner ruleset is revisedauto-scheduled
Limitations & open conflicts
limitationCost is not assessed: behaviour there is unmeasured, not clean△ gap
limitationReliability & Quality carries rows but no severity-bearing one: nothing has been graded there△ gap
conflictno two sources report the same quantity on this record
Verify: does this record describe your copy?
What record 358fd32e-0b63-41e8-9a00-5f19e5eeee79 covers
scannerv11● current
validityassessed 2w ago · Up to date
$vettd scan folder <path>
this record was taken at digest sha256:432f1e873733… compare it against the digest your own scan prints
Reproduce: re-run the evidence yourself
$vettd scan folder /path/to/your/copy
runs the same scanners against your own copy; the published record is never overwritten
How this record comparesagainst other published records · full comparison →
Signal kinds
▲ finding: something to act on, carries a severity● measurement: a reproducible quantityƒ estimate: inferred from a sample▪ fact: read directly off the artifact◆ classification: assigned from a taxonomy◌ nothing found: a producer looked and emitted no object◇ context only: described, never graded
Custody marks
◐ computed by vettd○ declared by the publisher, as-is△ not assessed: nothing looked
Weigh techtide-nvidia-tensorrt-llm-deployment-review against other published skills: the safety grade, its finding counts and each category’s verdict, one row apiece. The full comparison page carries every signal and framework coverage.