yolo-detection-2026-openvino

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

Quality

64%

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

Quality

Content

72%

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

The body is well-structured and highly actionable with real commands and protocol examples, but mild redundancy and the absence of validation/feedback steps in its workflows hold conciseness and workflow clarity at the mid level.

Suggestions

Collapse the duplicate 'How It Works' diagram and numbered list into one representation, and factor the repeated per-platform './deploy.sh' commands into a single command with platform notes.

Add an explicit validation/feedback step for first-run model export and device probing (e.g. verify the IR model exists and check device_probe output before proceeding).

Note the optional compile_model_colab.py and device_probe.py scripts in the body so all bundle files are surfaced for discovery.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the ASCII diagram plus the immediately following numbered list restate the same flow, and the three platform blocks repeat near-identical './deploy.sh' commands, so it could be tightened.	2 / 3
Actionability	It provides fully executable commands ('./deploy.sh', 'python scripts/compile_model.py --model yolo26n --size 640 --precision FP16'), a concrete device/flag/precision table, and copy-paste JSONL protocol examples, all specific rather than pseudocode.	3 / 3
Workflow Clarity	The 'How It Works' section gives a clear 5-step sequence, but there are no validation checkpoints or fix-and-retry feedback loops for the model auto-export or device-probe steps that can fail.	2 / 3
Progressive Disclosure	Content is organized into clearly labeled sections with one-level-deep references to real bundle scripts (scripts/detect.py, scripts/compile_model.py) and no nested reference indirection, keeping navigation easy for a skill of this scope.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 niched to OpenVINO hardware acceleration, but it lacks an explicit use-when trigger and only names a single action, capping completeness and trigger-term quality at the mid level.

Suggestions

Add a 'Use when ...' clause naming concrete triggers, e.g. 'Use when running YOLO object detection on Intel hardware (NCS2, iGPU, Arc) or when OpenVINO/Docker acceleration is requested.'

List a couple more concrete actions (e.g. 'exports YOLO models to OpenVINO IR, runs inference, streams JSONL detections') to lift specificity to the top anchor.

Include natural user variations like 'YOLO', 'computer vision', or 'camera/stream detection' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and tech tokens ("real-time object detection", "OpenVINO", "Docker", "NCS2, Intel GPU, CPU") but lists only one action rather than multiple specific concrete actions, so it stops short of the top anchor.	2 / 3
Completeness	It states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"object detection" and "Docker" are natural terms a user would say, but common variations like YOLO, computer vision, webcam/camera, or inference are missing, leaving coverage incomplete.	2 / 3
Distinctiveness Conflict Risk	The OpenVINO + NCS2/Intel GPU/CPU framing carves a clear hardware-acceleration niche with distinct triggers unlikely to fire for a generic detection skill.	3 / 3
	Total	9 / 12 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
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
Commit: 2264fcb

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.