CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

yolo-detection-2026-openvino

OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU)

Quality

68%

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 ./skills/detection/yolo-detection-2026-openvino/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a lean, well-structured overview with concrete commands and protocol examples, scoring well on conciseness, actionability, and progressive disclosure. Its main weakness is workflow clarity: the detection pipeline is described but lacks validation checkpoints or error-recovery guidance, and a couple of referenced deploy scripts are missing from the bundle.

Suggestions

Add an explicit validation/verification step to the workflow, e.g. after deploy run `python scripts/device_probe.py` to confirm the chosen device is available before expecting detections, with guidance on what to do if the device is absent.

Include the missing deploy.sh / deploy.bat as bundle scripts, or replace the bare './deploy.sh' references with the actual commands the deployer runs so the instructions are fully executable.

Reference the existing device_probe.py and compile_model_colab.py from the body (e.g. a 'Device probing' and 'Compile on Colab' note) so all bundle files are discoverable rather than orphaned.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence (no explaining what OpenVINO or object detection is), with only minor trimmable redundancy such as the device list in the intro repeating the 'Supported Devices' table and a time-sensitive 'Docker Desktop 4.35+' version number not placed in a deprecated section.

4 / 5

Actionability

It gives concrete, mostly executable commands ('./deploy.sh', 'python scripts/compile_model.py --model yolo26n --size 640 --precision FP16') and concrete JSONL examples, but the referenced deploy.sh/deploy.bat do not exist in the bundle, leaving a minor execution gap.

4 / 5

Workflow Clarity

The 'How It Works' section lays out a clear 5-step numbered sequence for the detection pipeline, but there are no validation/verification checkpoints or error-recovery feedback loops, matching the 'steps listed but checkpoints missing or implicit' anchor.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections and appropriately points to real script files (scripts/compile_model.py, scripts/detect.py); minor gaps are that scripts/device_probe.py and scripts/compile_model_colab.py exist but are not referenced, and assets/icon.png is named in frontmatter with no assets/ directory present.

4 / 5

Total

15

/

20

Passed

Description

53%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 concise and specific about what the skill does and on which hardware, but it omits any explicit 'when to use it' trigger guidance, which caps its completeness and limits trigger-term coverage. Adding a Use-when clause with natural synonyms would raise the weakest dimensions.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when running real-time object detection on Intel hardware (NCS2/GPU/CPU) via OpenVINO, or when the user asks for YOLO detection in Docker.'

Add common synonyms/users' phrasing such as 'YOLO', 'detect objects', or 'computer vision' so the trigger terms match what users actually say.

Differentiate explicitly from the sibling yolo-detection-2026 skill in the description to reduce conflict risk (e.g. 'OpenVINO variant of yolo-detection-2026 for Intel accelerators').

DimensionReasoningScore

Specificity

Quotes 'real-time object detection via Docker (NCS2, Intel GPU, CPU)' name the domain plus one concrete action (detection) and its delivery mechanism, but it does not list several distinct capabilities, so it sits at the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

It gives a clear 'what' (real-time object detection via Docker on named hardware) but has no 'Use when...' or equivalent trigger clause, so per the cap it cannot exceed 3 and fits the 'clear what, missing when' anchor exactly.

3 / 5

Trigger Term Quality

Natural terms like 'real-time object detection' are present, but common variations/synonyms a user might say (e.g. 'YOLO', 'detect objects', 'vision') are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The OpenVINO + Intel hardware + Docker framing is a fairly distinct niche, but the body itself notes it shares the same JSONL protocol as the sibling 'yolo-detection-2026' skill, leaving minor overlap risk with that closely related skill.

4 / 5

Total

13

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

SharpAI/DeepCamera

Path

skills/detection/yolo-detection-2026-openvino/SKILL.md

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.