yolo-detection-2026

YOLO 2026 — state-of-the-art real-time object detection

Quality

57%

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/SKILL.md

Quality

Content

65%

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 and well-structured with concrete protocol and deploy guidance, but it is held back by missing in-body executable code, dead bundle references, and the absence of explicit validation checkpoints in the deploy workflow.

Suggestions

Add an explicit validation step in 'How It Works' (e.g. wait for the 'ready' event / confirm the optimized model loaded before processing frames) to introduce a feedback loop.

Resolve or remove broken references — deploy.sh, requirements_*.txt, and ../../lib/env_config.py are referenced but not present in the bundle; either include them or correct the paths.

Include at least one runnable Python snippet (e.g. loading the model and emitting a detections event) so the actionability anchor for executable code is met.

Dimension	Reasoning	Score
Conciseness	The body is lean and information-dense — tables for model sizes and backends, exact JSONL protocol examples — with no padding or explanation of concepts Claude already knows, matching the 'every token earns its place' anchor.	3 / 3
Actionability	It gives concrete commands (./deploy.sh) and exact message formats, but there is no in-body executable code snippet and several referenced files (deploy.sh, requirements_*.txt, ../../lib/env_config.py) are not present in the bundle.	2 / 3
Workflow Clarity	The 'How It Works' section gives a clear 5-step sequence with a fallback, but the model-optimization/deploy workflow has no explicit validation checkpoint (e.g. confirm the 'ready' event or optimized model loaded before processing), which caps clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized and references are clearly signaled, but multiple referenced paths do not resolve against the actual bundle (no references/ dir, deploy.sh, requirements_*.txt, or ../../lib/env_config.py), weakening navigation.	2 / 3
	Total	9 / 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 accurate and domain-specific but terse, stating what the skill does without listing multiple concrete actions or any explicit 'when to use' trigger guidance.

Suggestions

Add a 'Use when...' clause with natural triggers, e.g. 'Use when detecting objects in images, video, or live camera feeds, or when the user mentions YOLO, bounding boxes, or real-time detection.'

List 2-3 concrete actions (e.g. 'detect objects, emit bounding boxes with confidence scores, optimize models per hardware') to lift specificity to the top anchor.

Include common user phrasings like 'detect people/vehicles/animals' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("real-time object detection") but does not enumerate multiple specific actions, matching the 'names domain and some actions' anchor rather than the multi-action level above.	2 / 3
Completeness	It states what the skill does but lacks any 'Use when...' trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"object detection" is a natural user term, but common variations (bounding boxes, detect objects in images/video, camera feeds) are missing, so it sits at the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The YOLO/object-detection niche is somewhat specific but the terse description could still overlap with other vision skills and lacks distinctive trigger phrasing.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: SharpAI/DeepCamera
Path: skills/detection/yolo-detection-2026/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.