senior-computer-vision

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.

Quality

65%

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 ./bundled/skills/senior-computer-vision/SKILL.md

Quality

Content

46%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 body is well-structured for progressive disclosure with real bundle files referenced one level deep, but it is weighed down by generic, non-CV-specific boilerplate bullet lists and lacks concrete executable CV code and validation checkpoints in its workflows. Actionability and workflow clarity are mid-range; conciseness is the weakest dimension.

Suggestions

Cut generic sections ('Core Expertise', 'Best Practices', 'Senior-Level Responsibilities') that restate what Claude already knows and replace them with concrete CV-specific guidance.

Add copy-paste-ready code examples for the core workflows (e.g., a minimal YOLO training snippet, a SAM segmentation call) instead of one-line CLI hints.

Add explicit validation checkpoints to training and deployment workflows (e.g., validate dataset, evaluate metrics before deploy, rollback on drift) to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic bullet lists ('Advanced production patterns', 'Scalable system design', 'Team leadership and mentoring') that explain nothing CV-specific Claude does not already know, with several unnecessary boilerplate sections; noticeably below the efficient midpoint.	2 / 5
Actionability	Provides real executable script invocations ('python scripts/vision_model_trainer.py --input data/ --output results/') and common commands, but most guidance is abstract bullet lists rather than concrete, copy-paste CV code, leaving it incomplete.	3 / 5
Workflow Clarity	Training and deployment are presented as one-liners with no sequenced steps or validation checkpoints; for batch/destructive operations like model training and production deployment the missing validation/feedback loops cap this at 3 per the rubric.	3 / 5
Progressive Disclosure	The overview points to three real, one-level-deep reference files (confirmed present in references/) and the scripts/ directory, clearly signaled and listed in both a Reference Documentation section and a Resources section; held at 4 because some reference summaries repeat inline rather than being fully split out.	4 / 5
	Total	12 / 20 Passed

Description

83%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 strong: it covers a concrete, well-scoped capability set, uses third person throughout, and includes an explicit 'Use when' trigger clause. It is slightly held back by missing synonyms/file extensions and minor overlap with general ML skills.

Suggestions

Add natural synonyms and file extensions to trigger terms (e.g., 'images, video frames, .mp4, .jpg') to reach comprehensive coverage.

Tighten distinctiveness by leading with the most CV-specific actions (detection, segmentation, tracking) rather than broad 'visual AI systems'.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities (object detection, segmentation, 3D vision, video analysis, inference optimization) plus named tools (PyTorch, OpenCV, YOLO, SAM), with minor coverage gaps; not a full 5 because some actions are framed as domain nouns rather than discrete actions.	4 / 5
Completeness	Clearly answers 'what' with concrete capabilities and explicitly answers 'when' via the 'Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('object detection', 'training custom vision models', 'inference pipelines'), but omits common synonyms and file extensions, so it falls short of the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clearly niched to computer vision with distinct triggers and minimal conflict risk; held at 4 rather than 5 because the broad ML/deployment language has minor overlap with a general ML skill.	4 / 5
	Total	17 / 20 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/senior-computer-vision/SKILL.md
Commit: ddcaa2a

Reviewed: 7 days 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.