CtrlK
BlogDocsLog inGet started
Tessl Logo

conversion-issues

Investigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary lean routing skill: a concise overview with clearly signaled one-level references to per-framework workflows, plus explicit validation gates (verify-first, test-must-pass-full-suite) and a deferred pre-submission checklist. It assumes Claude's intelligence and every section earns its place.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — a one-line Goal, two compact routing tables, and three terse Notes with no padding or explanation of concepts Claude already knows; every token earns its place.

3 / 3

Actionability

As an instruction/routing skill it gives concrete, specific guidance ("verify the model works with the framework's reference runtime ... before investigating OpenVINO code", "root-cause fixes", "Every fix needs a test and must pass the full frontend test suite") and defers executable steps to the referenced files, which the rubric does not penalize for instruction skills.

3 / 3

Workflow Clarity

The investigation arc (triage → debugging → accuracy comparison → pre-submission checklist) is surfaced via the table and gated by explicit validation checkpoints (verify reference runtime first; fix must pass the full test suite); as a sub-50-line single-purpose skill this qualifies for top marks under the simple-skills scoring note.

3 / 3

Progressive Disclosure

Clean overview with well-signaled, one-level-deep references: each table row links a per-framework file with a "What it covers"/"When to use" column, keeping detail out of the overview while making navigation obvious; no bundle files exist to contradict this.

3 / 3

Total

12

/

12

Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, third-person description with strong capability listing and a well-defined niche, but it omits an explicit "Use when..." trigger clause so the "when to use" guidance is only implied. Adding a use-when phrase would lift completeness to the top level.

Suggestions

Append an explicit trigger clause, e.g. "Use when a model fails to convert to OpenVINO IR via the ONNX or PyTorch frontend, or produces incorrect inference results after conversion."

Mirror a couple of natural user phrasings (e.g. "model won't convert", "conversion produces wrong results") to broaden trigger-term surface area.

Consider naming the output artifact ("OpenVINO IR") in the description so the target of conversion is unambiguous at a glance.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Investigate and fix", "triage, debugging, accuracy comparison, and pre-submission verification" — matching the anchor that rewards several specific capabilities rather than vague language.

3 / 3

Completeness

Clearly answers "what" (investigate/fix/triage/debug/verify) but lacks any explicit "Use when..." trigger clause; per the judging guideline, a missing Use-when clause caps completeness at 2 rather than 3.

2 / 3

Trigger Term Quality

Covers natural terms a user would actually say for this domain — "model conversion issues", "ONNX", "PyTorch", "debugging" — alongside the precise "OpenVINO Frontends" term, giving good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

Targets a clearly bounded niche — "model conversion issues in OpenVINO Frontends (ONNX, PyTorch)" — with distinct triggers unlikely to fire for unrelated skills; the separate add-op skill is distinguished in the body.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing, 2 suspicious

Warning

Total

15

/

16

Passed

Repository
openvinotoolkit/openvino
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.