add-fe-op

Adds a new operation to OpenVINO Frontend pipelines with translator updates, registration, and tests.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/agents-prototype/skills/add-fe-op/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The body is an efficient, well-structured instruction-only workflow with concrete identifiers and explicit validation checkpoints across six sequenced steps. Its main weaknesses are a redundant note, slightly abstract build/validation commands, and references to framework-specific files that are not present in the bundle.

Suggestions

Remove the duplicate "Keep this skill instruction-only in markdown" note (it appears at both line 29 and line 95).

Make build and validation commands concrete (e.g. name the CMake targets and the conversion-check command) instead of leaving them as "run conversion check from generated <frontend> model".

Add a short fix-and-retry loop in step 6 for when the conversion check fails, so the validation feedback loop is fully explicit.

Provide the referenced pytorch.md / onnx.md / conversion-issues files or remove/qualify the links so navigation does not dead-end.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining OpenVINO concepts; the only over-explanation is the redundant "Keep this skill instruction-only in markdown" note repeated at lines 29 and 95, which keeps it just below a 5.	4 / 5
Actionability	Guidance is concrete with specific identifiers (e.g. "aten::op", "aten.op.default", "ONNX_OP" macro), and absence of code is acceptable for an instruction-only skill; minor gaps remain where build and conversion-check commands are left abstract.	4 / 5
Workflow Clarity	A clear six-step sequence includes explicit validation checkpoints and blocked-state handling ("mark validation as blocked", "mark as skipped with explicit reason", "Confirm rerun is idempotent"), falling just short of 5 due to no explicit fix-and-retry loop on conversion failure.	4 / 5
Progressive Disclosure	Structure is well-organized with one-level-deep, clearly signaled references (pytorch.md, onnx.md, conversion-issues/*) and the generic workflow inlined; the referenced bundle files do not exist on disk, a minor organization gap that prevents a 5.	4 / 5
	Total	16 / 20 Passed

Description

58%Weight 40%Scale 1-5

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

The description is specific and clearly occupies a distinct niche, but it omits any explicit "when to use" trigger guidance, which caps its completeness. Adding a "Use when..." clause with natural trigger terms would meaningfully raise the score.

Suggestions

Append an explicit "Use when..." trigger clause, e.g. "Use when adding a new op to an OpenVINO Frontend, or when translator/registration/test scaffolding for a new op is needed."

Include natural synonyms a user might actually say, such as "op" alongside "operation" and "frontend" variations, to broaden trigger-term coverage.

Mention validation explicitly in the description so the listed actions match the body's six-step workflow more comprehensively.

Dimension	Reasoning	Score
Specificity	Names the domain ("OpenVINO Frontend pipelines") and lists several concrete actions ("translator updates, registration, and tests"), with minor gaps in coverage such as validation not being enumerated here.	4 / 5
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Terms like "OpenVINO Frontend", "translator", "registration", and "tests" are domain-accurate but mostly technical, lacking common synonyms such as "op" and broader natural phrasing a user would say.	3 / 5
Distinctiveness Conflict Risk	"OpenVINO Frontend pipelines" with "translator updates, registration, and tests" defines a clear niche with minimal overlap risk; not a 5 because the trigger phrasing leans technical rather than conversational.	4 / 5
	Total	14 / 20 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: 2 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: openvinotoolkit/openvino
Path: .github/agents-prototype/skills/add-fe-op/SKILL.md
Commit: 688569c

Reviewed: 1 day 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.