SKILLEMALL.ai
GitHub ↗ RU Sign in

BC trtllm-flashinfer-upgrade

Upgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a target version, and updates all version references across the repo. Use when the user wants to bump or upgrade flashinfer.

The skillemall take

The skill updates flashinfer-python in TensorRT-LLM: fetches releases from GitHub, compares against the current version, lets you pick a target, and rewrites version references across the repo. Single file with broken references—some paths point nowhere. Quality scores: 74 for quality, 59 for process. No critical findings, safety at 100. It works, but you'll need to fix missing paths manually as you go. Worth installing if you're prepared to patch file references on the fly.

NVIDIA/TensorRT-LLM Agent Skills author: NVIDIA NOASSERTION 1 file body ≈ 2 926 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Upgrade flashinfer-python version in TensorRT-LLM.

As a process C 59/100 · Has gaps — References files that are not bundled: [^/]+

ProcedureGitHubSoftware developmentWriting and documentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
C
59/100
Has gaps
References files that are not bundled: [^/]+
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 missing-ref reference to a missing file: [^/]+
  • note edit-residue the text marks something as outdated (lines 210): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 59/100

Will not run. References files that are not bundled: [^/]+
  • 0Tools and files. 1 referenced file(s) missing: [^/]+
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 24 steps
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2926 tokens
  • 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
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +3Description length 298: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (16 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.