yolo-detection-2026-coral-tpu-win-wsl

Google Coral Edge TPU — real-time object detection natively via Windows WSL

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/detection/yolo-detection-2026-coral-tpu-win-wsl/SKILL.md

Quality

Content

50%

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

The content is well-structured and reasonably concise, with clear process sequences for detection and installation. Its main weaknesses are the absence of executable code/event schemas, missing validation checkpoints in the install flow, and unreferenced or missing bundle files.

Suggestions

Add an executable example: a minimal detect.py invocation and a sample JSONL detections event so the guidance is copy-paste ready.

Insert validation checkpoints into the installation workflow (e.g. verify the TPU is visible, confirm the venv import of pycoral succeeds) before declaring success.

Signpost the existing bundle scripts with one-level-deep links, and remove or create the missing deploy.bat and assets/icon.png references.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (compact table + ASCII diagram, no tutorializing of TPU/WSL), but the opening sentence restates the description and marketing padding ("natively utilizing", "exclusively within WSL", "seamlessly") keeps it from a 3.	2 / 3
Actionability	It gives a concrete command ("Run deploy.bat") and specific hardware IDs/paths, but offers no executable Python, JSONL event schema, or detection-output example, so guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	Both the detection and install flows are clearly sequenced in numbered steps, but there are no validation/verification checkpoints for a USB-device-bind plus venv install, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the body never signposts the existing bundle scripts (compile_model.py, tpu_probe.py, install_pycoral.py) and references deploy.bat and assets/icon.png that are absent from the bundle.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 about the hardware/runtime niche and a single core action, but it stops short of listing multiple actions, omits common trigger variations, and lacks any explicit "Use when" guidance. It is a competent-but-incomplete description rather than a model one.

Suggestions

Add a "Use when…" clause naming concrete triggers, e.g. "Use when running object detection on a Google Coral Edge TPU attached to Windows via WSL."

Expand the action list beyond "object detection" to mention detecting/tracking 80 COCO classes on live camera frames, so specificity can reach 3.

Include natural user terms like "detect objects", "YOLO", or "COCO classes" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"real-time object detection" names one concrete action plus the Coral TPU/WSL domain, but no second action is listed, so it is not comprehensive enough for a 3 and not vague enough for a 1.	2 / 3
Completeness	It answers what the skill does but provides no "Use when…" or equivalent explicit trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	It surfaces relevant natural terms ("object detection", "real-time", "Edge TPU", "Windows WSL") but omits common variations a user might actually say (detect objects, YOLO, COCO, camera feed).	2 / 3
Distinctiveness Conflict Risk	The Coral Edge TPU + WSL hardware niche is fairly specific, but the "object detection" trigger is generic and the lack of a when-clause leaves overlap risk with other detection skills.	2 / 3
	Total	8 / 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-coral-tpu-win-wsl/SKILL.md
Commit: 2264fcb

Reviewed: about 23 hours 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.