BD trtllm-codebase-exploration
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.
The skill teaches systematic exploration of the TensorRT-LLM codebase before writing new code. It promises to save time on rewrites—the author references a real case where 250 lines got deleted because the needed function already existed. The file contains guidance on finding existing infrastructure and tracing code paths, nothing fancy.
Checks show: grade B, quality 85/100, no critical errors. No critical findings, lint is clean. Works across all major platforms and models. The downside: process score is only 44, suggesting no automation or runnable examples. This is documentation, not a tool—but it's solid documentation.
Install it if you regularly add features to TRT-LLM and want to dodge obvious mistakes. If you touch the project sporadically, you'll memorize it and forget it.
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations.
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 85Steps. 22 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2131 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
- +2Single-language instructions
- +3Description length 442: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.