add-gpu-op

Add a new operation to the OpenVINO GPU plugin — OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

A well-structured orchestration hub that is concise and excellently organized with clear one-level-deep references. The body itself is mostly an index, so executable depth and feedback loops rely on the linked step files.

Dimension	Reasoning	Score
Conciseness	Extremely lean — a 'When to use' line, a compact steps table, and an entry-point note — with no padding and no explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Concrete navigation guidance: an ordered step table mapping each file to its purpose plus a clear orchestrator entry point, though all executable detail is deferred to the linked (absent-in-bundle) step files.	4 / 5
Workflow Clarity	Clear ordered sequence (0a through 5) with the note that each step produces artifacts consumed by the next and an embedded verify step (3c 'Run and verify tests'), but explicit feedback loops live in the linked files rather than the body.	4 / 5
Progressive Disclosure	Textbook progressive disclosure: a concise overview table with one-level-deep, well-signaled links to per-step files plus a separate orchestrator entry point, making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

75%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.

A specific, distinctive description that clearly conveys the domain and concrete actions, but it omits any explicit 'when to use' trigger guidance, which caps completeness. Adding a 'Use when...' clause would raise the score.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when implementing GPU plugin support for a new op after the Core OpSpec agent has produced an op spec.'

Include a natural-language synonym such as 'GPU op' or 'primitive' alongside 'operation' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests' — giving comprehensive coverage of the operation's workflow, matching the multiple-specific-actions anchor.	5 / 5
Completeness	Clearly states what ('Add a new operation to the OpenVINO GPU plugin...') but has no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Strong domain-natural terms ('OpenVINO GPU plugin', 'OpenCL kernel', 'oneDNN', 'sub-group/LWS tuning') that a GPU-plugin developer would say, but missing common synonyms like 'GPU op' or 'primitive'.	4 / 5
Distinctiveness Conflict Risk	Highly specific to the OpenVINO GPU plugin niche with distinct technical triggers, making conflict with other skills minimal.	5 / 5
	Total	17 / 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: 11 missing	Warning

	Total	15 / 16 Passed

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