yolo-detection-2026-coral-tpu-macos

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

Quality

53%

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-macos/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 provides a clear overview with concrete protocol details, but it relies on a missing deploy.sh, includes some redundant prose, and lacks explicit validation checkpoints in its workflow.

Suggestions

Add the missing `deploy.sh` to the bundle (or correct the references to the actual script) so the documented setup commands are real and runnable.

Tighten the 'Important Deployment Notice' by removing redundant adverbs ('natively', 'securely') to improve token efficiency.

Add an explicit verification step after deployment (e.g. running `tpu_probe.py` to confirm the Edge TPU is visible) to give the workflow a validation checkpoint.

Remove the stray `detect.py.bak` from the scripts/ bundle to keep progressive disclosure clean.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with useful tables and an ASCII diagram, but the 'Important Deployment Notice' is padded with redundant wording ('natively halt', 'prompt you securely', 'securely register') that could be tightened.	2 / 3
Actionability	Concrete commands (`./deploy.sh`) and a specific JSONL protocol are present, but the actual detection invocation and arguments live in the bundled detect.py rather than as inline executable examples, leaving guidance incomplete.	2 / 3
Workflow Clarity	The 'How It Works' section lists a clear 1-4 sequence, but there are no explicit validation or verification checkpoints, so it sits at the 'steps listed but checkpoints missing' anchor rather than a 3.	2 / 3
Progressive Disclosure	Sections are well organized and the overview stays shallow, but the body repeatedly references `./deploy.sh` which is not present in the bundle, and `detect.py.bak` is stray noise in scripts/, so navigation is not cleanly resolved.	2 / 3
	Total	8 / 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 distinctive for its hardware niche, but it only names one action and entirely omits any 'when to use it' trigger guidance, leaving completeness and trigger-term coverage incomplete.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when running object detection on a Google Coral Edge TPU, or when the user mentions Coral, Edge TPU, or USB AI accelerator detection.'

List concrete actions beyond detection, such as 'detects 80 COCO classes and streams JSONL detections to Aegis', to raise specificity.

Include common user-facing terms like 'YOLO', 'real-time camera detection', and 'USB AI accelerator' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Google Coral Edge TPU') and one concrete action ('real-time object detection'), but lists a single action rather than multiple specific concrete actions, so it stops short of a 3.	2 / 3
Completeness	It clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Terms like 'Coral Edge TPU' and 'object detection' are natural for the niche, but common variations (e.g. 'YOLO', 'camera detection', 'Edge TPU') are missing and there is no explicit trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The Coral Edge TPU qualifier carves out a clear niche unlikely to trigger for unrelated skills, and the specificity distinguishes it from generic detection skills.	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-coral-tpu-macos/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.