inference-latency-profiler
Inference Latency Profiler - Auto-activating skill for ML Deployment. Triggers on: inference latency profiler, inference latency profiler Part of the ML Deployment skill category.
35
3%
Does it follow best practices?
Impact
92%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/inference-latency-profiler/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a placeholder that names the skill and its category but provides no substantive information about what it does or when it should be used. It lacks concrete actions, meaningful trigger terms, and explicit usage guidance. The self-referential trigger ('inference latency profiler' repeated) provides no value for skill selection.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Profiles model inference latency, identifies performance bottlenecks, measures throughput and response times for deployed ML models.'
Add a 'Use when...' clause with natural trigger terms like 'slow inference', 'model latency', 'response time optimization', 'deployment performance', 'profiling', 'throughput analysis'.
Include relevant file types, frameworks, or tools (e.g., 'TensorFlow Serving', 'ONNX Runtime', 'TorchServe') to improve distinctiveness and trigger matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain ('ML Deployment') and a tool name ('Inference Latency Profiler') but describes no concrete actions whatsoever. There are no verbs indicating what the skill actually does—no 'profiles latency', 'measures response times', 'identifies bottlenecks', etc. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming itself, and the 'when' clause is just a self-referential trigger on its own name. There is no explicit 'Use when...' guidance with meaningful trigger scenarios. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'inference latency profiler' repeated twice. There are no natural user keywords like 'slow inference', 'model latency', 'response time', 'throughput', 'profiling', 'deployment performance', or similar terms a user would naturally say. | 1 / 3 |
Distinctiveness Conflict Risk | The name 'Inference Latency Profiler' is fairly specific and unlikely to conflict with many other skills, but the lack of concrete actions and meaningful trigger terms means it could overlap with other ML deployment or performance profiling skills without clear differentiation. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an empty template with no substantive content. It contains only generic boilerplate descriptions that repeat the skill name without providing any actual guidance on inference latency profiling—no code, no tools, no workflows, no concrete techniques. It fails on every dimension of the rubric.
Suggestions
Add concrete, executable code examples for profiling inference latency (e.g., using Python's time module, torch.cuda.Event for GPU timing, or tools like NVIDIA Nsight/TensorRT profiler).
Define a clear multi-step workflow: instrument model, collect latency metrics, identify bottlenecks, optimize (with specific techniques like batching, quantization, graph optimization), and validate improvements.
Include specific tool recommendations and configurations (e.g., Triton Inference Server metrics, Prometheus/Grafana dashboards for latency monitoring, percentile-based SLA definitions).
Remove all generic boilerplate sections ('When to Use', 'Example Triggers', 'Capabilities') and replace with actionable content that teaches Claude something it doesn't already know.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats the phrase 'inference latency profiler' excessively, and provides zero domain-specific information. Every section is generic padding. | 1 / 3 |
Actionability | There is no concrete code, no commands, no specific techniques, no examples of profiling inference latency. The content only describes what the skill claims to do in abstract terms without any executable or actionable guidance. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. The skill claims to provide 'step-by-step guidance' but contains none. There are no validation checkpoints or any sequenced instructions. | 1 / 3 |
Progressive Disclosure | No references to external files, no structured content hierarchy, and no meaningful organization. The sections are just generic headings with placeholder text that convey no real information. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
87f14eb
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.