CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 content is concise, well-structured, and actionable with concrete hardware-specific details, but it lacks explicit validation checkpoints in its workflows and does not clearly navigate to the provided bundle scripts. Signaling the bundle files and adding a verification step would raise the weaker dimensions.

Suggestions

Add an explicit validation checkpoint to the installation workflow, e.g., "Verify the TPU is visible: `wsl -e lsusb` should list 18d1:9302" before proceeding to detection.

Clearly link and label the bundle scripts in the body (e.g., "Detection engine: see [scripts/detect.py](scripts/detect.py)"; "Model compilation: see [scripts/compile_model.py](scripts/compile_model.py)") so the file structure is navigable.

Resolve the missing referenced files: either add `deploy.bat` and `assets/icon.png` to the bundle or update the references to point at the assets that actually exist.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (it does not explain what WSL or object detection is), with a compact diagram and table that earn their place; only minor trims would tighten it further.

4 / 5

Actionability

Provides the executable entry point "Run `deploy.bat`" plus concrete specifics (hardware IDs 18d1:9302 / 1a6e:089a, shared path /tmp/aegis_detection/, JSONL protocol), with only minor gaps in full command detail.

4 / 5

Workflow Clarity

The How-It-Works and Installation sections are clearly numbered and sequenced, but there are no explicit validation checkpoints (e.g., confirm the TPU is attached via lsusb or test inference), fitting the 'steps listed but validation gaps' anchor.

3 / 5

Progressive Disclosure

Sections are well organized, but the body references `deploy.bat` (not present in the bundle) and `assets/icon.png` (missing), while most bundle scripts (compile_model.py, tpu_probe.py, install_pycoral.py) are not signaled or linked, fitting 'references present but not clearly signaled'.

3 / 5

Total

14

/

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 clearly identifies a distinct hardware-specific niche, but it only states one action and omits any explicit "Use when..." trigger guidance. Adding trigger phrases and one or two more concrete capabilities would lift completeness and specificity.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g., "Use when running real-time object detection on a Google Coral Edge TPU attached to a Windows machine via WSL").

Expand the action list beyond a single verb to mention key capabilities (e.g., detecting 80 COCO classes, ~4ms inference, configurable FPS/input size).

Include common synonyms/users' phrasings such as "Coral USB Accelerator", "Edge TPU", and "WSL2" to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("Google Coral Edge TPU") and one concrete action ("real-time object detection") but stops there without enumerating further capabilities, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

The description clearly states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.

3 / 5

Trigger Term Quality

Includes relevant terms like "Coral Edge TPU", "object detection", and "Windows WSL", but lacks common synonyms or variations users might naturally say, fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The Coral Edge TPU + WSL niche is narrow and largely distinct, with only minor overlap risk against sibling detection skills, fitting 'mostly distinct; minor overlap risk'.

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-coral-tpu-win-wsl/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.