analyze-and-convert

Analyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.github/agents-prototype/skills/analyze-and-convert/SKILL.md

Quality

Content

65%

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

A concise, well-structured orchestration overview with clear sequencing, but its value is undermined by four referenced bundle files that are missing and by the absence of explicit validation/retry checkpoints. Providing the referenced files and at least one inline executable command would substantially improve it.

Suggestions

Add the four referenced bundle files (probe-model.md, try-conversion.md, classify-failure.md, build-report.md); none currently exist, so the progressive-disclosure links are broken.

Add an explicit validation/retry checkpoint, e.g. 'if every conversion strategy fails, record the failure mode before proceeding to classify-failure', instead of only the success-skip branch.

Include at least one concrete executable command inline (such as the optimum-cli or ovc invocation) so the overview is actionable without opening every referenced file.

Dimension	Reasoning	Score
Conciseness	The body is ~18 lines with no concept padding and every line earning its place (lean 'When to use' plus a purpose table), matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It names concrete tools ('optimum-cli / ovc / convert_model') and signal names, but provides no inline executable command and delegates the actual runnable steps to referenced files that are not present, fitting 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	A strict ordered sequence with a 'skip on full success' branch is present, but there is no explicit validate→fix→retry checkpoint or error-recovery loop, matching 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	The overview is well structured with one-level-deep, clearly signaled references in a table, but the referenced files (probe-model.md, try-conversion.md, classify-failure.md, build-report.md) do not exist, so the navigation is broken rather than functional.	2 / 3
	Total	9 / 12 Passed

Description

67%

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, well-scoped description with concrete actions and a clear niche, but it lacks an explicit 'Use when...' trigger clause and leans on pipeline jargon over natural user phrasing. Adding trigger guidance and plain-language keywords would raise completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasing, e.g. 'Use when converting a HuggingFace model to OpenVINO IR, or when a conversion fails and you need to diagnose why'.

Pair pipeline jargon ('strategy matrix', 'routing signals') with plain-language terms a user would actually say, such as 'HuggingFace model', 'OpenVINO', and 'conversion fails'.

Include common keyword variations (e.g. 'HF model', 'convert to OpenVINO', 'IR format') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'probe properties, run strategy matrix, classify failures, and produce a structured routing report' — in third-person voice, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger; the judging guidelines cap completeness at 2 when trigger guidance is absent.	2 / 3
Trigger Term Quality	'HuggingFace model' and 'OpenVINO conversion' are natural user terms, but 'strategy matrix' and 'routing report' are pipeline-internal jargon and common variations are missing, so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The HuggingFace-to-OpenVINO conversion niche is specific and distinct, with triggers unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: openvinotoolkit/openvino
Path: .github/agents-prototype/skills/analyze-and-convert/SKILL.md
Commit: 4c20980

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.