add-core-op

Adds a core operator to the OpenVINO toolkit. Use when asked to implement a new operation into OpenVINO.

Quality

67%

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-core-op/SKILL.md

Quality

Content

68%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 content is a well-structured, largely actionable guide for adding an OpenVINO op with exact paths and real code fragments. Its main weakness is the absence of explicit build/test validation checkpoints in the workflow, which caps workflow clarity.

Suggestions

Add explicit validation checkpoints to the workflow — e.g., 'Build openvino', then 'Run `**/openvino/src/core/tests/type_prop`' and only proceed when tests pass — to establish a fix→re-run feedback loop.

Provide a single copy-paste-ready constructor + evaluate skeleton in the Core Op Class Pattern instead of describing them in prose, closing the actionability gap.

Deduplicate the file-path listings: keep one canonical 'Files to create/update' table and have the per-step sections reference it rather than repeating the paths.

Dimension	Reasoning	Score
Conciseness	The body is largely lean instruction with exact file paths and code fragments, assuming OpenVINO familiarity; minor over-explanation (e.g., the serialization-mechanism aside and the Constant-axis example) could be trimmed.	4 / 5
Actionability	It supplies concrete file paths, real macros (OPENVINO_OP, OV_OP_SCOPE, on_attribute), and an itemized class pattern, but full constructor/evaluate implementations are described in prose rather than given as copy-paste-ready code.	4 / 5
Workflow Clarity	A clear four-step sequence is present (analysis, update files, tests, spec), but there are no explicit validation checkpoints (build, run type_prop/visitor tests, conformance) — a gap that caps this batch, multi-file operation at 3.	3 / 5
Progressive Disclosure	Content is well-sectioned with clear headers and no nested external references; the only organization gap is redundant file-path listings between the 'Create Header/Source' sections and the 'Files to create/update' checklist.	4 / 5
	Total	15 / 20 Passed

Description

66%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 cleanly answers both what and when with an explicit 'Use when' trigger and a distinctive OpenVINO niche. It is held back from the top by thin action coverage and a single trigger phrasing lacking synonyms.

Suggestions

Expand the 'what' with 1-2 more concrete actions (e.g., create header/source files, register the op in the latest opset, add tests and an .rst spec) to lift specificity.

Add synonym trigger terms such as 'add a new op' or 'new OpenVINO operator' alongside 'implement a new operation' for broader keyword coverage.

Consider a second trigger condition (e.g., 'when a missing op is found at model conversion and decomposition is not viable') to make the 'when' more concrete.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenVINO toolkit') and one concrete action ('Adds a core operator'), but coverage is not comprehensive — it does not enumerate the constituent sub-tasks (header/source creation, registration, tests, spec).	3 / 5
Completeness	It states both what ('Adds a core operator to the OpenVINO toolkit') and when ('Use when asked to implement a new operation into OpenVINO'), but the 'when' is a single trigger and the 'what' is one action rather than an explicit enumeration.	4 / 5
Trigger Term Quality	The single trigger phrase 'asked to implement a new operation into OpenVINO' is reasonably natural, but it offers only one phrasing with no synonyms ('add a new op', 'operator'), variants, or file extensions.	3 / 5
Distinctiveness Conflict Risk	The pairing of 'core operator' with 'OpenVINO toolkit' carves a clear, narrow niche with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openvinotoolkit/openvino
Path: .github/agents-prototype/skills/add-core-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.