AB perf-optimization
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.
The skill promises to coordinate performance optimization: route requests to specialists, execute a two-step TileIR pipeline, select kernel generators, and run iterative autopilot optimization. Files contain routing tables, prioritization criteria, and safe modification workflows—no scripts or runnable examples. Quality score 88/100, process score 83, no critical findings. Works across all major platforms including Claude and Cursor.
You'll need to understand the routing logic yourself—the skill outlines structure but doesn't provide ready commands. Useful if you already work with TensorRT-LLM and want to systematize optimization. Install it if this is your existing toolkit.
Performance optimization coordination playbook.
As a process B 76/100 · Nearly there — weak spots: progress reporting
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 76/100
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 82 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3044 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +2Single-language instructions
- +3Description length 376: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 82 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.