CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

model-training

Agent-driven YOLO fine-tuning — annotate, train, export, deploy

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/training/model-training/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured and token-efficient with a clear protocol interface and pipeline diagram, but it lacks an executable example of the core training/export action and does not frame the batch training workflow with explicit validation checkpoints.

Suggestions

Add a concrete runnable example for the core action, e.g. a `python scripts/train.py --dataset ... --base-model yolo26n --epochs 50` invocation and an export command.

Express the training workflow as an explicit numbered sequence with a validation gate, e.g. train -> validate mAP -> only export when mAP meets threshold.

Either include the referenced files (scripts/train.py, env_config.py, requirements.txt) in the bundle or note that they are generated/provided separately so navigation is not broken.

DimensionReasoningScore

Conciseness

The body is lean with no over-explanation of concepts Claude already knows, but the intro paragraph restates the 'What You Get' bullets, a minor redundancy that keeps it below anchor 5.

4 / 5

Actionability

Concrete JSONL protocol examples and setup commands are present, but the core training action is never shown executably (no train.py invocation or export command), leaving key details missing versus anchor 4.

3 / 5

Workflow Clarity

The training-loop diagram and protocol events convey a flow and a validate event exists, but there is no explicit sequenced workflow with validation checkpoints/gates for this batch operation, matching anchor 3 rather than 4.

3 / 5

Progressive Disclosure

The short body is well-organized into clear sections (What You Get, Training Loop, Protocol, Setup), but it references files that are not present in the bundle (scripts/train.py, env_config.py, requirements.txt), a minor navigation gap below anchor 5.

4 / 5

Total

14

/

20

Passed

Description

66%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 names a clear, distinctive niche with several concrete actions and natural trigger terms, but it omits any 'when to use' guidance and uses bare verbs without objects, capping completeness and specificity.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when fine-tuning a YOLO model on a custom COCO dataset or retraining for new object classes.'

Attach objects to the verbs, e.g. 'annotate images, train YOLO weights, export to TensorRT/CoreML, deploy as a detection skill' to lift specificity.

Drop or contextualize 'annotate' to reduce overlap with the separate dataset-annotation skill.

DimensionReasoningScore

Specificity

Lists four concrete actions ('annotate, train, export, deploy') covering the full pipeline, but they are bare verbs lacking objects, leaving minor specificity gaps versus the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear (YOLO fine-tuning pipeline) but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms a user would say are present ('YOLO', 'fine-tuning', 'train', 'export', 'deploy', 'annotate'), but synonyms (retrain, custom model) and file extensions (.pt, .engine) are missing, stopping short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

'Agent-driven YOLO fine-tuning' is a clear niche with minimal conflict risk, but the 'annotate' verb overlaps with the separate dataset-annotation skill, leaving minor overlap risk.

4 / 5

Total

15

/

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/training/model-training/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.