CtrlK
BlogDocsLog inGet started
Tessl Logo

add-cpu-op

Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/agents-prototype/skills/add-cpu-op/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A concise, well-organized overview that sequences a multi-step process and cleanly defers detail to one-level-deep references, but it lacks explicit validation/verification checkpoints and provides only directional (not executable) inline guidance.

Suggestions

Add explicit validation/verification checkpoints to the workflow (e.g., build/compile and run single-layer tests after step 4, with a fix-and-retry loop before proceeding).

Include at least one concrete executable snippet or command inline (e.g., the test invocation command or factory-registration code line) so the body is actionable on its own.

Confirm the four referenced step*.md files exist alongside SKILL.md so the progressive-disclosure references resolve.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or re-explanation of concepts Claude already knows; every line ("When to use", the step table, the ordering contract) earns its place.

3 / 3

Actionability

Gives concrete step sequencing with named files and purposes, but the inline body is directional rather than executable code or commands, deferring actionable detail to the referenced step files.

2 / 3

Workflow Clarity

Presents a clear ordered sequence with a stated artifact-consumption contract, but includes no validation or verification checkpoints for code-generation steps, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Clear overview with a well-signaled, one-level-deep reference table (step1–step4 files) and easy navigation; structurally matches the intended progressive-disclosure pattern.

3 / 3

Total

10

/

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 that names concrete actions and a distinct niche, but it omits an explicit "Use when..." trigger clause and relies on technical jargon rather than natural user phrasing.

Suggestions

Add an explicit "Use when..." clause stating when Claude should invoke this skill (e.g., after a Core OpSpec agent produces a new op spec for the CPU plugin).

Broaden trigger terms to include natural phrasings a user might say, such as "add a CPU operation", "implement an OpenVINO op", or "CPU op support".

Keep the existing concrete action list and ISA specificity, which already distinguish the skill well.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "node registration", "JIT/oneDNN executors (AVX2/AVX-512/AMX)", and "functional tests" — covering registration, execution, and testing comprehensively.

3 / 3

Completeness

Clearly answers "what" the skill does, but lacks any "Use when..." clause or equivalent explicit trigger for "when" to use it, capping completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Contains relevant domain keywords ("OpenVINO CPU plugin", "op", "JIT/oneDNN", ISA targets) but they are technical jargon lacking common natural variations a user would phrase.

2 / 3

Distinctiveness Conflict Risk

The "OpenVINO CPU plugin" niche with specific ISA targets is a clear, distinct trigger unlikely to overlap with other skills.

3 / 3

Total

10

/

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: 4 missing

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.